CN114670823A - Method, device and equipment for correcting running track and automatic driving vehicle - Google Patents
Method, device and equipment for correcting running track and automatic driving vehicle Download PDFInfo
- Publication number
- CN114670823A CN114670823A CN202210400058.XA CN202210400058A CN114670823A CN 114670823 A CN114670823 A CN 114670823A CN 202210400058 A CN202210400058 A CN 202210400058A CN 114670823 A CN114670823 A CN 114670823A
- Authority
- CN
- China
- Prior art keywords
- track
- point
- position information
- obstacle
- driving
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 67
- 238000012937 correction Methods 0.000 claims description 26
- 238000004590 computer program Methods 0.000 claims description 9
- 238000012986 modification Methods 0.000 claims description 9
- 230000004048 modification Effects 0.000 claims description 9
- 238000013473 artificial intelligence Methods 0.000 abstract description 8
- 238000013135 deep learning Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 12
- 238000005516 engineering process Methods 0.000 description 12
- 238000012545 processing Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 238000013459 approach Methods 0.000 description 6
- 230000004888 barrier function Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 3
- 238000013136 deep learning model Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000006872 improvement Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000003924 mental process Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
- B60W30/095—Predicting travel path or likelihood of collision
- B60W30/0956—Predicting travel path or likelihood of collision the prediction being responsive to traffic or environmental parameters
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/0097—Predicting future conditions
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/0098—Details of control systems ensuring comfort, safety or stability not otherwise provided for
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W60/00—Drive control systems specially adapted for autonomous road vehicles
- B60W60/001—Planning or execution of driving tasks
- B60W60/0015—Planning or execution of driving tasks specially adapted for safety
- B60W60/0017—Planning or execution of driving tasks specially adapted for safety of other traffic participants
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W60/00—Drive control systems specially adapted for autonomous road vehicles
- B60W60/001—Planning or execution of driving tasks
- B60W60/0027—Planning or execution of driving tasks using trajectory prediction for other traffic participants
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2552/00—Input parameters relating to infrastructure
- B60W2552/50—Barriers
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
- B60W2554/40—Dynamic objects, e.g. animals, windblown objects
- B60W2554/402—Type
- B60W2554/4029—Pedestrians
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Human Computer Interaction (AREA)
- Traffic Control Systems (AREA)
Abstract
The disclosure provides a method, a device and equipment for correcting a driving track and an automatic driving vehicle, and relates to the technical field of artificial intelligence, in particular to the technical field of automatic driving, intelligent transportation and deep learning. The specific implementation scheme is as follows: obtaining obstacle boundary information of a road section where a predicted driving track of a driving object is located; wherein the obstacle boundary information at least includes position information of obstacle points in an obstacle boundary; and correcting the predicted driving track according to the position information of the obstacle point in the obstacle boundary, the position information of the candidate track point in the predicted driving track and the transverse safe distance of the driving object in the road section. The error of the predicted driving track can be corrected, the accuracy of the predicted driving track is improved, and the safety of automatic driving is further improved.
Description
Technical Field
The disclosure relates to the technical field of artificial intelligence, in particular to the technical field of automatic driving, intelligent transportation and deep learning, and specifically relates to a method, a device and equipment for correcting a driving track and an automatic driving vehicle.
Background
With the development of artificial intelligence technology, automatic driving technology is gradually emerging. The prediction of the driving track is a core link of the automatic driving process. For example, the travel track of the current vehicle is predicted, and the travel track of a dynamic obstacle around the current vehicle is predicted. However, the predicted driving trajectory may have errors, which seriously affect the safety of automatic driving, and thus, improvement is urgently needed.
Disclosure of Invention
The disclosure provides a method, a device and equipment for correcting a running track and an automatic driving vehicle.
According to an aspect of the present disclosure, there is provided a method of correcting a travel track, including:
obtaining obstacle boundary information of a road section where a predicted driving track of a driving object is located; wherein the obstacle boundary information at least includes position information of obstacle points in an obstacle boundary;
and correcting the predicted driving track according to the position information of the obstacle point in the obstacle boundary, the position information of the candidate track point in the predicted driving track and the transverse safe distance of the driving object in the road section.
According to another aspect of the present disclosure, there is provided an electronic device including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a method of modifying a driving trajectory according to any one of the embodiments of the present disclosure.
According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute a method of correcting a travel locus according to any one of the embodiments of the present disclosure.
According to another aspect of the present disclosure, an autonomous vehicle is provided, which includes the electronic device according to the embodiment of the present disclosure.
According to the scheme of the embodiment of the disclosure, the error of the predicted driving track can be corrected, the accuracy of the predicted driving track is improved, and the safety of automatic driving is further improved.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.
Drawings
The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
fig. 1 is a flowchart of a method for correcting a driving track according to an embodiment of the disclosure;
fig. 2A is a flowchart of a method for correcting a driving track according to an embodiment of the disclosure;
FIG. 2B is a schematic diagram of a modified track point location provided in accordance with an embodiment of the present disclosure;
fig. 3A is a flowchart of a method for correcting a driving track according to an embodiment of the disclosure;
fig. 3B is a schematic diagram of adding missing track points according to an embodiment of the present disclosure;
fig. 4A is a flowchart of a method for correcting a driving track according to an embodiment of the disclosure;
fig. 4B is a schematic diagram illustrating a missing track point screening method according to an embodiment of the disclosure;
fig. 5 is a flowchart of a method for correcting a driving track according to an embodiment of the disclosure;
fig. 6 is a schematic structural diagram of a device for correcting a driving track according to an embodiment of the present disclosure;
fig. 7 is a block diagram of an electronic device for implementing a method of correcting a travel track according to an embodiment of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Fig. 1 is a flowchart of a method for correcting a driving track according to an embodiment of the present disclosure; the embodiment of the present disclosure is applicable to a case where a predicted travel locus is corrected. The method is particularly suitable for correcting the driving track predicted by the deep learning model for the driving object. The method may be performed by a device for correcting the driving trajectory, which may be implemented in software and/or hardware. The method can be particularly integrated into an electronic device with a travel track prediction or use function. As shown in fig. 1, the method for correcting a driving trajectory according to this embodiment may include:
s101, obtaining obstacle boundary information of a road section where the predicted driving track of the driving object is located.
Here, the traveling object of the present embodiment may be any traveling object on a road, and for example, may be a vehicle, a pedestrian, or the like on the road. For example, in an autonomous driving scenario, the traveling object may be an autonomous vehicle, or may be a dynamic obstacle such as a pedestrian or another vehicle around the autonomous vehicle.
The predicted travel locus may be a travel locus predicted for the travel object in a certain manner. For example, it may be a travel locus predicted for a travel object by a deep learning model; the method can also be used for simulating a section of driving track for a driving object through a track simulator; or a section of driving track planned for the driving object according to the route planning strategy. The predicted travel locus is formed of a plurality of locus points.
The obstacle boundary may be a real object on both sides of the road for representing the road boundary (i.e., a hard boundary on both sides of the road), which corresponds to a virtual boundary (i.e., a soft boundary) on both sides of the road. For example, curbs, fences, cones, etc. at the boundary positions on both sides of a road are the obstacle boundaries (i.e. hard boundaries) of the road; the road line at the boundary position on both sides of the road is the virtual boundary (i.e. soft boundary) of the road.
The obstacle boundary information may be information describing an obstacle boundary-related attribute, which includes at least position information of an obstacle point in the obstacle boundary. For example, if the obstacle boundary is formed by sequentially arranging a plurality of obstacles (such as cone barrels), an intersection point of each obstacle (such as cone barrels) and the ground can be used as one obstacle point of the obstacle boundary. If the obstacle boundary is formed by a continuous plane, such as a curb, then several intersections with the ground may be extracted from the continuous plane as obstacle points of the obstacle boundary. The rule for extracting the obstacle point is not limited in this embodiment. For example, one point may be extracted every preset distance as an obstacle point. Alternatively, the position information of the obstacle point in this embodiment may be a lateral position coordinate and a longitudinal position coordinate of the obstacle point with respect to a reference point (e.g., a starting point of a lane line at the center of the road section) in the road section where the obstacle point is located.
Optionally, the obstacle boundary information of this embodiment may further include other attribute information of the obstacle boundary, such as the type of the obstacle boundary. Among them, obstacle boundary types may include, but are not limited to: curbs, fences or cone barrels, etc.
Optionally, in this embodiment, the predicted travel track of the travel object may be obtained first, then, according to the position information of the track point in the predicted travel track, based on the high-precision map, at least one road segment (i.e., the road segment to which the predicted travel track belongs) is determined, and then, whether an obstacle boundary exists in each road segment is sequentially determined, if so, obstacle boundary information corresponding to the road segment is obtained, otherwise, the obtaining operation of the obstacle boundary is not performed.
Optionally, in this embodiment, there may be many ways to determine whether a road segment has an obstacle boundary and obtain obstacle boundary information, which is not limited to this. Specifically, one way to implement this is: whether the road section has barrier boundaries or not is analyzed through a road panoramic image corresponding to the road section in the high-precision map or a real-time scene image of the road section, and if so, corresponding barrier boundary information is further analyzed and obtained.
The other realization mode is as follows: the method comprises the steps of constructing an obstacle boundary map containing obstacle boundary information of a global road section in advance, wherein the obstacle boundary map at least contains road segments which are associated with obstacle boundaries in a high-precision map, and marking the obstacle boundary information corresponding to each road segment in the obstacle boundary map in a certain mode. For example, obstacle boundary information may be added to each road segment by way of a Key-Value pair (Key-Value), where Key is an identifier of a road segment to be labeled (such as a road name or a serial number), and Value is obstacle boundary information corresponding to the road segment. At this time, the embodiment may search, based on the road identifier of the road segment where the predicted travel track is located, whether the road segment has an associated obstacle boundary in a pre-constructed obstacle boundary map, and if so, further obtain hard boundary information corresponding to the road segment from the obstacle boundary map.
And S102, correcting the predicted driving track according to the position information of the obstacle point in the obstacle boundary, the position information of the candidate track point in the predicted driving track and the transverse safe distance of the driving object in the road section.
The candidate track points in the predicted travel track may be each track point in the predicted travel track, or some track points extracted from each track point in the travel track according to a certain strategy. The embodiment does not limit the specific extraction strategy, and for example, a candidate track point may be extracted every preset time, or a candidate track point may be extracted every preset distance; alternatively, a candidate trace point may be extracted every predetermined number of trace points. Note that, in order to improve the smoothness of the trajectory correction result and reduce the complexity in the correction process, some trajectory points extracted from the travel trajectory are preferably used as the trajectory point candidates in the present embodiment.
The lateral safety distance may be a lateral minimum driving distance from the obstacle boundary, which is set in advance for the driving object to travel on the route, in order to ensure the driving safety of the driving object. Optionally, in this embodiment, the size of the lateral safe distance may be a preset fixed distance value, or may be adjusted in real time according to a certain policy according to the difference between the driving object, the road segment where the driving object is located, and the obstacle boundary, which is not limited to this.
Optionally, an implementation manner of this embodiment is: the method comprises the steps of determining the relative positions between candidate track points and obstacle points according to position information of the obstacle points in obstacle boundaries and position information of the candidate track points in a predicted driving track, and further analyzing and predicting whether unreasonable conditions exist in the candidate track points of the driving track according to the relative positions, for example, the conditions that the distance between the candidate track points and obstacle boundaries on two sides of a road is too short or the candidate track points cross the obstacle boundaries exist, if the unreasonable conditions exist, correcting the position coordinates of the track points with unreasonable positions according to the position information of the obstacle points, the unreasonable predicted position information of the candidate track points and the transverse safety distance of a driving object driving on the road section, and/or adding new track points in the predicted driving track to ensure the reasonability of the track points in the predicted driving track.
Another implementation manner of this embodiment is to input the position information of the candidate track point in the predicted travel track, the position information of the obstacle point in the obstacle boundary of the road segment where the predicted travel track is located, and the lateral safe distance traveled by the travel object on the road segment into a track correction model trained in advance, where the model can analyze unreasonable track points in the travel track according to the input data and output corrected position information corresponding to the unreasonable track point.
According to the scheme of the embodiment of the disclosure, the position information of the obstacle point in the obstacle boundary of the road section where the predicted driving track of the driving object is located is obtained, and the predicted driving track is corrected according to the position information of the obstacle point, the position information of the candidate track point in the predicted driving track and the transverse safe distance of the driving object in the road section. According to the scheme, the error of the predicted driving track can be corrected, in the process of correcting the predicted driving track, the obstacle boundary information of the road section is considered emphatically, unreasonable problems that the predicted track is too close to the obstacle boundary or crosses the obstacle boundary and the like are effectively solved, the accuracy of the predicted driving track is improved, and the safety of automatic driving is further improved.
Optionally, in this embodiment, a preferred determination manner of the lateral safe distance traveled by the road segment where the driving object is located is as follows: determining the driving width of the driving object according to the type of the driving object; and determining the transverse safe distance traveled by the traveling object on the road section according to the traveling width and the buffer distance.
Specifically, in this embodiment, the width of the running object is determined according to the type of the running object, and the width of the running object is taken as the running width. And then adding the running width of the running object to the buffer distance directly or adding the running width multiplied by a preset multiple (such as 0.5 time) to the buffer distance to obtain the transverse safe distance of the running object running on the road section. According to the scheme, the exclusive transverse safe distance is determined for different driving objects according to the types of the driving objects, and the accuracy and the reasonability of determining the transverse safe distance are improved.
The buffer distance in the scheme may be a fixed value set empirically in advance, or may be determined by combining an actual scene according to a certain rule. Optionally, if the buffer distance in this embodiment is determined in real time according to a certain rule, the determination method may be: and determining the buffer distance according to the road section width of the road section, the obstacle boundary type in the obstacle boundary information and the type of the driving object. Specifically, a safety distance range required to be reserved around the obstacle boundary can be determined according to the obstacle boundary type in the obstacle boundary information; and determining the driving width of the driving object according to the type of the driving object, and providing the optimal buffer distance by combining the actual road width of the current road section, the safe distance range and the constraint relation among the driving widths of the driving objects. According to the scheme, the special buffer distance is determined for the driving object by considering the road section width, the obstacle boundary type and the driving object type, the accuracy of determining the buffer distance is improved, and the accuracy of determining the transverse safe distance is further ensured.
Fig. 2A is a flowchart of a method for correcting a driving track according to an embodiment of the disclosure; fig. 2B is a schematic diagram of a principle of correcting the track point position according to an embodiment of the present disclosure. The disclosed embodiment further explains in detail how to correct the predicted travel track according to the position information of the obstacle point in the obstacle boundary, the position information of the candidate track point in the predicted travel track, and the lateral safe distance traveled by the traveling object on the road segment, on the basis of the above embodiments, and as shown in fig. 2A-2B, the method for correcting the travel track provided by this embodiment may include:
s201, obtaining obstacle boundary information of a road section where the predicted driving track of the driving object is located.
Wherein the obstacle boundary information at least includes position information of obstacle points in the obstacle boundary.
S202, determining error track points in the candidate track points according to the position information of the obstacle points in the obstacle boundary, the position information of the candidate track points in the predicted driving track and the transverse safe distance of the driving object in the road section.
The error track point of this embodiment may be a track point having a position error due to being too close to the obstacle boundary in the driving track, and preferably, the error track point may be a track point having a distance smaller than the lateral safety distance from the obstacle boundary.
Optionally, an implementation manner of this embodiment is: and inputting the position information of the obstacle point in the obstacle boundary, the position information of each candidate track point in the predicted driving track and the transverse safe distance of the driving object driving on the road section into an error analysis model, wherein the model can analyze whether the candidate track point is the error track point or not based on the information of the data.
Another way to implement this is: determining the transverse prediction distance between the candidate track point and the obstacle boundary according to the position information of the obstacle point in the obstacle boundary and the position information of the candidate track point in the predicted driving track; and if the transverse predicted distance is smaller than the transverse safe distance of the driving object in the road section, taking the candidate track point as an error track point. Specifically, for each candidate trajectory point in the predicted travel trajectory, an associated obstacle point may be determined from the obstacle points of the obstacle boundary. And calculating the transverse prediction distance between the candidate track point and the obstacle boundary by combining the position information of the candidate track point and the position information of the associated obstacle point. And then judging whether the transverse predicted distance is smaller than the transverse safe distance of the driving object driving on the road section, and if so, taking the candidate track point as an error track point. This embodiment preferably adopts this implementable mode to confirm the error track point, and this mode can realize more accurate and comprehensive definite error track point, provides the guarantee for follow-up accurate and comprehensive correction prediction orbit of going.
Illustratively, as shown in fig. 2B, B1-B3 are three obstacle points of an obstacle boundary, and p1 and p2 are two candidate track points in the predicted travel track respectively; one way to implement this embodiment is: taking the obstacle point closest to the candidate track point as an obstacle point associated with the candidate track point; for example, the obstacle point b1 is taken as the obstacle point associated with the candidate track point p 1; and taking the obstacle point b2 as an obstacle point associated with the candidate track point p 2. At this time, the difference between the lateral position coordinate of the candidate track point and the lateral position coordinate of the obstacle point associated with the candidate track point may be calculated as the lateral predicted distance between the candidate track point and the obstacle boundary. Another way to implement this is: and judging whether obstacle points with the same vertical coordinates as the candidate track points exist in the obstacle points on the obstacle boundary, if so, taking the obstacle points as the obstacle points associated with the candidate track points, otherwise, taking the two obstacle points which are closest to the front and the rear of the candidate track points as the obstacle points associated with the candidate track points. For example, the obstacle point b1 may be taken as the obstacle point associated with the candidate track point p 1; and taking the barrier points b2 and b3 as barrier points associated with the candidate track point p 2. At this time, the difference between the transverse position coordinates of the candidate track point and the transverse position coordinates of each obstacle point associated with the candidate track point can be calculated first, and if the number of the obstacle points associated with the candidate track point is one, the difference is directly used as the transverse prediction distance between the candidate track point and the obstacle boundary; if the number of the obstacle points associated with the candidate track point is multiple, the horizontal position coordinate difference value of the candidate track point and each obstacle point may be averaged or weighted to obtain the horizontal prediction distance between the candidate track point and the obstacle boundary. If the weighted average processing is performed, the weight at this time may be determined according to a difference between the longitudinal coordinates of the candidate trajectory point and the associated obstacle point, for example, the larger the longitudinal distance difference is, the smaller the weight is.
And S203, correcting the position of the error track point in the predicted running track according to the transverse safe distance.
Alternatively, the present embodiment may correct the lateral position coordinates of the error track point in the predicted travel track to the lateral safe distance. The longitudinal position coordinates of the error track points may not be adjusted, or may be adaptively adjusted according to a certain rule, which is not limited in this embodiment.
Illustratively, as shown in fig. 2B, the error trace point p1 is corrected to the position of p 1'; and correcting the error track point p2 to the position of p 2'.
In the present embodiment, the predicted travel path is mainly corrected when the distance to the obstacle boundary is too short.
According to the scheme of the embodiment of the disclosure, the position information of the obstacle point in the obstacle boundary of the road section where the predicted driving track of the driving object is located is obtained, the error track point is determined firstly according to the position information of the obstacle point, the position information of the candidate track point in the predicted driving track and the transverse safe distance of the driving object in the road section, and the correction of the predicted driving track is realized by correcting the error track point based on the transverse safe distance. According to the scheme, unreasonable estimation points which are too close to the obstacle boundary in the candidate track points can be accurately and quickly screened out according to the position information of the obstacle points, the position information of the candidate track points and the transverse safety distance, and are corrected, so that the situation that the corrected predicted driving track is too close to the obstacle boundary can be avoided, and the accuracy of the predicted driving track is greatly improved.
Fig. 3A is a flowchart of a method for correcting a driving track according to an embodiment of the disclosure; fig. 3B is a schematic diagram of a principle of adding missing track points according to an embodiment of the present disclosure. The disclosed embodiment further explains in detail how to correct the predicted travel track according to the position information of the obstacle point in the obstacle boundary, the position information of the candidate track point in the predicted travel track, and the lateral safe distance traveled by the traveling object on the road segment, on the basis of the above embodiments, and as shown in fig. 3A-3B, the method for correcting the travel track provided by this embodiment may include:
s301, obstacle boundary information of a road section where the predicted driving track of the driving object is located is obtained.
Wherein the obstacle boundary information at least includes position information of obstacle points in the obstacle boundary.
S302, determining a target track point pair in the predicted driving track and target points contained between the target track point pair according to the position information of the obstacle point in the obstacle boundary and the position information of the candidate track points in the predicted driving track.
In this embodiment, if two adjacent candidate track points in the travel track include an obstacle point of an obstacle boundary therebetween, the two adjacent candidate track points are set as a set of target track point pairs. And the obstacle point in the target track point pair is used as a target point, namely the target point belongs to the obstacle point.
Optionally, in this embodiment, the target track point pair and the target point included in the target track point pair may be determined by determining a relationship between the longitudinal position coordinates of the adjacent candidate track points in the travel track and the longitudinal position coordinates of the obstacle point of the obstacle boundary.
Specifically, the present embodiment may sequentially determine, for every two adjacent track points in the driving track, whether the longitudinal position coordinates of one or more obstacle points are included between the longitudinal position coordinates of the two adjacent track points, if so, use the two adjacent track points as a group of target track point pairs, and use the obstacle point whose longitudinal position coordinate is located between the target track point pairs as a target point included in the target track point pair.
Illustratively, as shown in fig. 3B, B4-B6 are three obstacle points of an obstacle boundary, and p3 and p4 are two adjacent candidate track points in the predicted travel track respectively; as can be seen from fig. 3B, the barrier points B4-B6 are located between the candidate track point p3 and the candidate track point p4, the candidate track point p3 and the candidate track point p4 are taken as a group of target track point pairs, and the barrier points B4-B6 are taken as target points included in the group of target track point pairs.
And S303, determining the position information of the missing track point according to the position information of the target point and the transverse safe distance of the driving object in the road section.
Optionally, an implementation manner of this embodiment is: and taking the longitudinal position coordinates of the target track points as the longitudinal position coordinates of the missing track points, and taking the transverse safe distance of the running object running on the road section as the transverse position coordinates of the missing track points, so as to obtain the position information of the missing track points.
If the number of the target points is multiple, a first realizable manner may be adopted to calculate one missing track point for each target point, and a missing track point may be determined based on multiple target points through a second realizable manner described below. The specific implementation mode is as follows: determining a risk coefficient of the target point according to the position information of the target point; specifically, the risk coefficient of each target point can be calculated by the following formula (1).
R=1/[α*lTarget+(1-α)*sTarget] (1)
Wherein R is the risk coefficient for the target point; α is a preset calculation parameter, and its value is greater than or equal to 0 and less than or equal to 1, for example, may be 0.99. l. theTargetIs the transverse position coordinate of the target point; sTargetIs the longitudinal position coordinate of the target point.
After the risk coefficient of the target point is determined, determining a dangerous point from the target point according to the risk coefficient of the target point; for example, the target point with the highest risk coefficient may be selected as the risk point; and determining the position information of the missing track point according to the position information of the dangerous point and the transverse safe distance of the driving object in the road section. For example, the longitudinal position coordinates of the dangerous points may be used as the longitudinal position coordinates of the missing track points, and the lateral safe distance traveled by the traveling object on the road section may be used as the lateral position coordinates of the missing track points.
For example, as shown in fig. 3B, assuming that the risk coefficient of the target point B5 (i.e., the obstacle point B5) is higher than that of the target point B4 (i.e., the obstacle point B4) and the target point B6 (i.e., the obstacle point B4), the longitudinal position coordinate of the missing track point q1 determined at this time is the longitudinal position coordinate of the target point B5; the transverse position coordinate of the missing track point q1 is the transverse safety distance.
According to the scheme, the missing track points are determined by determining the dangerous points from the multiple target points, a corresponding missing track point does not need to be determined for each target point, the addition number of the missing track points is reduced while the predicted driving track is corrected to cross the obstacle boundary, namely the original appearance of the predicted driving track is kept by reducing the correction of the predicted driving track as much as possible.
And S304, adding the missing track points in the predicted driving track according to the position information of the missing track points.
Specifically, in this embodiment, according to the position information of each missing track point determined in S303, a position point corresponding to the position information is found in the middle of a target track point pair corresponding to the missing track point, and a track point is added to the position point, so that after all the missing track points are added, the predicted travel track point can be corrected.
Optionally, after the step is executed, according to the position information of the missing track point, after the missing track point is added to the predicted travel track, whether the target track point pair still exists may be determined according to a manner similar to S302 described above based on the predicted travel track after the missing track point is added, if the target track point pair still exists, the target track point at this time is determined, and a new missing track point is determined again and added to the predicted travel track in a manner similar to S303 to S304 until the target track point pair does not exist in the predicted travel track after the missing track point is added.
In the present embodiment, the predicted travel path is mainly corrected when crossing an obstacle boundary. In addition, the present disclosure may also combine the embodiment with the above embodiments, and correct the situation that the predicted travel path is too close to the obstacle boundary and the situation that the predicted travel path crosses the obstacle boundary at the same time, in this case, in order to ensure the accuracy of the correction result, the situation that the predicted travel path is too close to the obstacle boundary may be corrected first, and then the situation that the predicted travel path crosses the obstacle boundary may be corrected.
According to the scheme of the embodiment of the disclosure, the position information of the obstacle point in the obstacle boundary of the road section where the predicted driving track of the driving object is located is obtained, the target track point pair and the target point contained in the target track point pair are determined according to the position information of the obstacle point and the position information of the candidate track point in the predicted driving track, the position information of the missing track point is determined firstly according to the position information of the target point and the transverse safety distance, and then the missing track point is added in the predicted driving track. According to the scheme, a mode of accurately determining the position of the missing track point by combining the obstacle boundary is provided, the problem that the predicted travelling track crosses the obstacle boundary is solved, and the accuracy of the predicted travelling track is greatly improved.
Fig. 4A is a schematic diagram of a method for correcting a driving track according to an embodiment of the present disclosure, and fig. 4B is a schematic diagram of a principle of missing track point screening according to an embodiment of the present disclosure. The embodiment of the present disclosure further explains in detail how to add missing track points in a predicted travel track according to position information of the missing track points on the basis of the above-mentioned embodiment, and as shown in fig. 4A-4B, the method for correcting a travel track provided by this embodiment may include:
s401, obtaining obstacle boundary information of a road section where the predicted driving track of the driving object is located.
Wherein the obstacle boundary information at least includes position information of obstacle points in the obstacle boundary.
S402, determining a target track point pair in the predicted driving track and a target point contained between the target track point pair according to the position information of the obstacle point in the obstacle boundary and the position information of the candidate track point in the predicted driving track.
Wherein the target point belongs to the obstacle point.
And S403, determining the position information of the missing track point according to the position information of the target point and the transverse safe distance of the driving object in the road section.
S404, determining whether the geometric relation between the position information of the missing track point and the position information of the target track point pair meets an adding rule, if so, executing S405, and if not, executing S406.
Specifically, one implementation manner of this embodiment is as follows: and judging whether the missing track point is positioned between the connecting line of the target track point pair and the lane central line according to the position information of the missing track point and the position information of the target track point pair, if so, meeting the addition rule, and if not, not meeting the addition rule.
Illustratively, as shown in fig. 4B, p3 and p4 are a set of target locus point pairs, B4-B6 are three target points located between the set of target locus point pairs, q1 and q2 are respectively position information of two missing locus points determined by S403 based on the three target points, and as shown in fig. 4B, q1 is located on the left side of the line connecting p3 and p4 (i.e., between the lane center line and the line connecting p3 and p4), and q2 is located on the right side of the line connecting p3 and p4 (i.e., between the road boundary line and the line connecting p3 and p4), it can be determined that the geometric relationship between the missing locus point q1 and the position information of the target locus point pairs p3 and p4 satisfies the addition rule, and the geometric relationship between the missing locus point q2 and the position information of the target locus point pairs p3 and p4 does not satisfy the addition rule.
Another implementation manner of this embodiment is: determining a first slope value according to the position information of a first track point and a second track point in the target track point pair; determining a second slope value according to the position information of the missing track point and the position information of the first track point; determining whether the geometric relationship between the position information of the missing track point and the position information of the target track point pair meets an adding rule or not according to the first slope value and the second slope value; the timestamp of the first track point is earlier than that of the second track point, namely, the traveling object arrives at the first track point first and then arrives at the second track point.
Specifically, if the position coordinate of the first track point is (l1, s1), the position coordinate of the second track point is (l2, s 2); the position coordinates of the missing track points are (l3, s 3); the first slope K1 ═ (l2-l1)/(s2-s 1); the second slope K1 ═ (l3-l1)/(s3-s 1); if the obstacle boundary is on the right side of the road section, the first slope and the second slope are both smaller than 0; at this time, if the second slope value K2 is greater than the first slope value K1, the addition rule is satisfied; if the obstacle boundary is on the left side of the road section, both the first slope and the second slope are greater than 0; at this time, if the second slope value K2 is less than the first slope value K1, the addition rule is satisfied.
Illustratively, as can be seen in FIG. 4B, Kq1p4>Kp3p4Then the geometric relationship between the position information of the missing track point q1 and the position information of the target track point pair (i.e., p3 and p4) satisfies the addition rule, Kq2p4<Kp3p4Then the geometric relationship between the position information of the missing track point q2 and the position information of the target track point pair (i.e., p3 and p4) does not satisfy the addition rule.
According to the method and the device, the geometric relation between the missing track point and the target track point pair is represented through the slope relation between the missing track point and the target track point pair, the accuracy of representing the geometric relation is improved, and further the efficiency and the accuracy of judging whether the adding rule is met or not in the follow-up process are improved.
And S405, if so, adding the missing track points in the predicted driving track according to the position information of the missing track points.
And S406, if the predicted driving track does not meet the requirement, missing track points are not added in the predicted driving track.
According to the scheme of the embodiment of the disclosure, the position information of the obstacle point in the obstacle boundary of the road section where the predicted driving track of the driving object is located is obtained, the target track point pair and the target point contained in the target track point pair are determined according to the position information of the obstacle point and the position information of the candidate track point in the predicted driving track, the position information of the missing track point is determined firstly according to the position information of the target point and the transverse safe distance, and the missing track point is added in the predicted driving track only under the condition that the geometric relation between the missing track point and the target track point pair meets the adding rule. According to the scheme, only the missing track points with the geometric relationship meeting the adding rule are added into the predicted driving track, and the adding accuracy of the missing track points is further guaranteed.
Fig. 5 is a flowchart of a method for correcting a driving trajectory according to an embodiment of the present disclosure. The disclosed embodiment further explains in detail how to correct the predicted travel track according to the position information of the obstacle point in the obstacle boundary, the position information of the candidate track point in the predicted travel track, and the lateral safe distance traveled by the traveling object on the road segment, based on the above embodiment, and as shown in fig. 5, the method for correcting the travel track provided by this embodiment may include:
s501, obtaining obstacle boundary information of a road section where the predicted driving track of the driving object is located.
Wherein the obstacle boundary information at least includes position information of obstacle points in the obstacle boundary.
S502 determines whether or not the predicted travel locus needs to be corrected based on the obstacle boundary type and the travel object type, and if necessary, executes S503, and if not, executes S504.
Optionally, in this embodiment, whether the vehicle is allowed to approach and to traverse is preset for different types of obstacle boundaries, in combination with obstacle characteristics, if the vehicle is allowed to approach, a type of a traveling object allowed to approach may be further defined, and if the vehicle is allowed to traverse, a maximum traveling width allowed to traverse may be further defined.
For example, if the obstacle boundary is a curb, the pedestrian is allowed to approach the road, and the vehicle is not allowed to approach the road; if the obstacle boundary is a cone, the maximum allowable transverse travel width is the distance between two adjacent cones.
In this case, the step may determine whether the obstacle boundary allows approaching travel according to the type of the obstacle boundary, and if not, perform subsequent S503 to correct the situation that the predicted travel trajectory is too close to the obstacle boundary. If the predicted travel path is allowed, further according to the type of the travel object, judging whether the travel object is allowed to approach the obstacle boundary, if not, then executing subsequent S503 to correct the situation that the predicted travel path is too close to the obstacle boundary, otherwise executing S504 to finish correcting the predicted travel path.
Whether the obstacle boundary is allowed to cross the traveling path or not can be determined according to the type of the obstacle boundary, and if not, the following S503 is executed to correct the situation that the obstacle boundary is crossed in the predicted traveling path; if the estimated travel path is allowed, determining the travel width according to the type of the travel object, and if the travel width is larger than the maximum travel width allowed by the obstacle boundary and crossing the travel, performing subsequent S503 to correct the situation that the estimated travel path crosses the obstacle boundary; otherwise, S504 is executed to end the correction of the predicted travel locus.
And S503, if necessary, correcting the predicted driving track according to the position information of the obstacle point in the obstacle boundary, the position information of the candidate track point in the predicted driving track and the transverse safe distance of the driving object in the road section.
It should be noted that, in the present embodiment, any one of the correction manners described in the above embodiments, or a combination of a plurality of correction manners may be adopted to perform the correction operation of the predicted travel trajectory in the present step, which is not limited herein.
If not, S503 ends the correction of the predicted travel locus.
According to the scheme of the embodiment of the disclosure, before the predicted driving track is corrected according to the acquired position information of the obstacle point in the obstacle boundary, the position information of the candidate track point in the predicted driving track and the transverse safe distance of the driving object in the road section, whether the correction needs to be carried out or not is determined according to the type of the obstacle boundary and the type of the driving object, if so, the follow-up track correction operation is carried out, thereby avoiding the occurrence of false correction or unnecessary correction and the like, and further ensuring the reasonability and accuracy of the track correction process.
Fig. 6 is a schematic structural diagram of a device for correcting a travel locus according to an embodiment of the present disclosure, which is suitable for correcting a predicted travel locus. The method is particularly suitable for correcting the driving track predicted by the deep learning model for the driving object. The device can be configured in an electronic device with a traveling track prediction or use function, and is realized by software and/or hardware, and the device can realize the traveling track correction method of any embodiment of the disclosure. As shown in fig. 6, the travel track correction device 600 includes:
a boundary information obtaining module 601, configured to obtain obstacle boundary information of a road segment where a predicted driving trajectory of a driving object is located; wherein the obstacle boundary information at least includes position information of obstacle points in an obstacle boundary;
and the track correction module 602 is configured to correct the predicted travel track according to the position information of the obstacle point in the obstacle boundary, the position information of the candidate track point in the predicted travel track, and the transverse safe distance traveled by the travel object on the road segment.
According to the scheme of the embodiment of the disclosure, the position information of the obstacle point in the obstacle boundary of the road section where the predicted driving track of the driving object is located is obtained, and the predicted driving track is corrected according to the position information of the obstacle point, the position information of the candidate track point in the predicted driving track and the transverse safe distance of the driving object in the road section. According to the scheme, the error of the predicted driving track can be corrected, in the process of correcting the predicted driving track, the obstacle boundary information of the road section is considered emphatically, unreasonable problems that the predicted track is too close to the obstacle boundary or crosses the obstacle boundary and the like are effectively solved, the accuracy of the predicted driving track is improved, and the safety of automatic driving is further improved.
Further, the trajectory modification module 602 includes:
the error track point determining unit is used for determining error track points in the candidate track points according to the position information of the obstacle points in the obstacle boundary, the position information of the candidate track points in the predicted driving track and the transverse safe distance of the driving object in the road section;
and the position correction unit is used for correcting the position of the error track point in the predicted driving track according to the transverse safe distance.
Further, the error trajectory point determining unit is specifically configured to:
determining the transverse prediction distance between the candidate track point and the obstacle boundary according to the position information of the obstacle point in the obstacle boundary and the position information of the candidate track point in the predicted driving track;
and if the transverse predicted distance is smaller than the transverse safe distance of the driving object in the road section, taking the candidate track point as an error track point.
Further, the trajectory modification module 602 includes:
a target point determining unit, configured to determine a target track point pair in the predicted travel track and a target point included between the target track point pair according to position information of an obstacle point in the obstacle boundary and position information of a candidate track point in the predicted travel track; wherein the target point belongs to the obstacle point;
the missing point determining unit is used for determining the position information of the missing track point according to the position information of the target point and the transverse safe distance of the driving object in the road section;
and the missing point adding unit is used for adding the missing track points into the predicted driving track according to the position information of the missing track points.
Further, the missing point determining unit is specifically configured to:
determining a risk coefficient of the target point according to the position information of the target point;
determining a dangerous point from the target point according to the risk coefficient of the target point;
and determining the position information of the missing track point according to the position information of the dangerous point and the transverse safe distance of the driving object in the road section.
Further, the missing point adding unit includes:
a rule judging subunit, configured to determine whether a geometric relationship between the position information of the missing track point and the position information of the target track point pair satisfies an addition rule;
and the missing point adding subunit is used for adding the missing track points into the predicted driving track according to the position information of the missing track points if the predicted driving track meets the requirement.
Further, the rule determining subunit is specifically configured to:
determining a first slope value according to the position information of a first track point and a second track point in the target track point pair;
determining a second slope value according to the position information of the missing track point and the position information of the first track point;
determining whether the geometric relationship between the position information of the missing track point and the position information of the target track point pair meets an adding rule or not according to the first slope value and the second slope value;
wherein the timestamp of the first track point is earlier than the timestamp of the second track point.
Further, the obstacle boundary information further includes an obstacle boundary type;
the trajectory modification module 602 is further configured to:
determining whether the predicted driving track needs to be corrected or not according to the obstacle boundary type and the driving object type;
and if so, correcting the predicted driving track according to the position information of the obstacle point in the obstacle boundary, the position information of the candidate track point in the predicted driving track and the transverse safe distance of the driving object in the road section.
Further, the apparatus 600 further includes:
the driving width determining module is used for determining the driving width of the driving object according to the type of the driving object;
and the safe distance determining module is used for determining the transverse safe distance of the driving object in the road section according to the driving width and the buffer distance.
Further, the apparatus 600 further includes:
and the buffer distance determining module is used for determining the buffer distance according to the road section width of the road section, the obstacle boundary type in the obstacle boundary information and the type of the driving object.
The product can execute the method provided by any embodiment of the disclosure, and has corresponding functional modules and beneficial effects of the execution method.
In the technical scheme of the disclosure, the acquisition, storage, application and the like of the predicted driving track, the obstacle boundary information of the road section, the type of the driving object and the like all accord with the regulations of related laws and regulations, and do not violate the good customs of the public order.
The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.
FIG. 7 illustrates a schematic block diagram of an example electronic device 700 that can be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 7, the device 700 comprises a computing unit 701, which may perform various suitable actions and processes according to a computer program stored in a Read Only Memory (ROM)702 or a computer program loaded from a storage unit 708 into a Random Access Memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the device 700 can also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other by a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.
Various components in the device 700 are connected to the I/O interface 705, including: an input unit 706 such as a keyboard, a mouse, or the like; an output unit 707 such as various types of displays, speakers, and the like; a storage unit 708 such as a magnetic disk, optical disk, or the like; and a communication unit 709 such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 709 allows the device 700 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), blockchain networks, and the internet.
The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service are overcome. The server may also be a server of a distributed system, or a server incorporating a blockchain.
Artificial intelligence is the subject of research that makes computers simulate some human mental processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.), both at the hardware level and at the software level. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing, and the like; the artificial intelligence software technology mainly comprises a computer vision technology, a voice recognition technology, a natural language processing technology, a machine learning/deep learning technology, a big data processing technology, a knowledge map technology and the like.
Cloud computing (cloud computing) refers to a technology system that accesses a flexibly extensible shared physical or virtual resource pool through a network, where resources may include servers, operating systems, networks, software, applications, storage devices, and the like, and may be deployed and managed in a self-service manner as needed. Through the cloud computing technology, high-efficiency and strong data processing capacity can be provided for technical application and model training of artificial intelligence, block chains and the like.
In addition, the embodiment of the invention also provides an automatic driving vehicle which comprises a vehicle body, wherein the vehicle body is provided with the electronic equipment provided by the embodiment of the invention.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel or sequentially or in different orders, and are not limited herein as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved.
The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.
Claims (24)
1. A method for correcting a travel track, comprising:
obtaining obstacle boundary information of a road section where a predicted driving track of a driving object is located; wherein the obstacle boundary information at least includes position information of obstacle points in an obstacle boundary;
and correcting the predicted driving track according to the position information of the obstacle point in the obstacle boundary, the position information of the candidate track point in the predicted driving track and the transverse safe distance of the driving object in the road section.
2. The method of claim 1, wherein the modifying the predicted travel path based on the position information of the obstacle point in the obstacle boundary, the position information of the candidate trajectory point in the predicted travel path, and the lateral safe distance traveled by the traveling object over the road segment comprises:
determining error track points in the candidate track points according to the position information of the obstacle points in the obstacle boundary, the position information of the candidate track points in the predicted driving track and the transverse safe distance of the driving object in the road section;
and correcting the position of the error track point in the predicted driving track according to the transverse safe distance.
3. The method according to claim 2, wherein determining an error track point in the track candidate points according to the position information of the obstacle point in the obstacle boundary, the position information of the track candidate points in the predicted driving track, and the lateral safe distance of the driving object on the road segment comprises:
determining the transverse prediction distance between the candidate track point and the obstacle boundary according to the position information of the obstacle point in the obstacle boundary and the position information of the candidate track point in the predicted driving track;
and if the transverse predicted distance is smaller than the transverse safe distance of the running object running on the road section, taking the candidate track point as an error track point.
4. The method according to claim 1 or 2, wherein the correcting the predicted travel track according to the position information of the obstacle point in the obstacle boundary, the position information of the candidate track point in the predicted travel track, and the lateral safe distance traveled by the traveling object on the road segment includes:
determining a target track point pair in the predicted driving track and target points contained between the target track point pair according to the position information of the obstacle point in the obstacle boundary and the position information of the candidate track points in the predicted driving track; wherein the target point belongs to the obstacle point;
determining the position information of the missing track point according to the position information of the target point and the transverse safe distance of the driving object in the road section;
and adding the missing track points in the predicted driving track according to the position information of the missing track points.
5. The method according to claim 4, wherein the determining the position information of the missing track point according to the position information of the target point and the transverse safe distance traveled by the traveling object on the road section comprises:
determining a risk coefficient of the target point according to the position information of the target point;
determining a dangerous point from the target point according to the risk coefficient of the target point;
and determining the position information of the missing track point according to the position information of the dangerous point and the transverse safe distance of the driving object in the road section.
6. The method according to claim 4, wherein adding missing track points in the predicted travel track according to the position information of the missing track points comprises:
determining whether the geometric relationship between the position information of the missing track point and the position information of the target track point pair meets an adding rule;
and if so, adding the missing track points into the predicted driving track according to the position information of the missing track points.
7. The method of claim 6, wherein the determining whether a geometric relationship between the location information of the missing track point and the location information of the target track point pair satisfies an addition rule comprises:
determining a first slope value according to the position information of a first track point and a second track point in the target track point pair;
determining a second slope value according to the position information of the missing track point and the position information of the first track point;
determining whether the geometric relationship between the position information of the missing track point and the position information of the target track point pair meets an adding rule or not according to the first slope value and the second slope value;
wherein the timestamp of the first track point is earlier than the timestamp of the second track point.
8. The method of any of claims 1-7, wherein the obstacle boundary information further includes an obstacle boundary type;
correspondingly, the correcting the predicted travel track according to the position information of the obstacle point in the obstacle boundary, the position information of the candidate track point in the predicted travel track, and the transverse safe distance traveled by the travel object on the road section further includes:
determining whether the predicted driving track needs to be corrected or not according to the obstacle boundary type and the driving object type;
and if so, correcting the predicted driving track according to the position information of the obstacle point in the obstacle boundary, the position information of the candidate track point in the predicted driving track and the transverse safe distance of the driving object in the road section.
9. The method according to any one of claims 1-8, further comprising:
determining the driving width of the driving object according to the type of the driving object;
and determining the transverse safe distance traveled by the traveling object on the road section according to the traveling width and the buffer distance.
10. The method of claim 9, further comprising:
and determining a buffer distance according to the road section width of the road section, the obstacle boundary type in the obstacle boundary information and the type of the driving object.
11. A travel track correction device comprising:
the boundary information acquisition module is used for acquiring obstacle boundary information of a road section where the predicted driving track of the driving object is located; wherein the obstacle boundary information at least includes position information of obstacle points in an obstacle boundary;
and the track correction module is used for correcting the predicted driving track according to the position information of the obstacle point in the obstacle boundary, the position information of the candidate track point in the predicted driving track and the transverse safe distance of the driving object in the road section.
12. The apparatus of claim 11, wherein the trajectory modification module comprises:
the error track point determining unit is used for determining error track points in the candidate track points according to the position information of the obstacle points in the obstacle boundary, the position information of the candidate track points in the predicted driving track and the transverse safe distance of the driving object in the road section;
and the position correction unit is used for correcting the position of the error track point in the predicted driving track according to the transverse safe distance.
13. The apparatus according to claim 12, wherein the error trajectory point determining unit is specifically configured to:
determining the transverse prediction distance between the candidate track point and the obstacle boundary according to the position information of the obstacle point in the obstacle boundary and the position information of the candidate track point in the predicted driving track;
and if the transverse predicted distance is smaller than the transverse safe distance of the running object running on the road section, taking the candidate track point as an error track point.
14. The apparatus of claim 11 or 12, wherein the trajectory modification module comprises:
a target point determining unit, configured to determine a target track point pair in the predicted travel track and a target point included between the target track point pairs according to position information of an obstacle point in the obstacle boundary and position information of a candidate track point in the predicted travel track; wherein the target point belongs to the obstacle point;
the missing point determining unit is used for determining the position information of the missing track point according to the position information of the target point and the transverse safe distance of the driving object in the road section;
and the missing point adding unit is used for adding the missing track points into the predicted driving track according to the position information of the missing track points.
15. The apparatus according to claim 14, wherein the missing point determining unit is specifically configured to:
determining a risk coefficient of the target point according to the position information of the target point;
determining a dangerous point from the target point according to the risk coefficient of the target point;
and determining the position information of the missing track point according to the position information of the dangerous point and the transverse safe distance of the driving object in the road section.
16. The apparatus of claim 14, wherein the missing point adding unit comprises:
a rule judging subunit, configured to determine whether a geometric relationship between the position information of the missing track point and the position information of the target track point pair satisfies an addition rule;
and the missing point adding subunit is used for adding the missing track points into the predicted driving track according to the position information of the missing track points if the predicted driving track meets the requirement.
17. The apparatus according to claim 16, wherein the rule determining subunit is specifically configured to:
determining a first slope value according to the position information of a first track point and a second track point in the target track point pair;
determining a second slope value according to the position information of the missing track point and the position information of the first track point;
determining whether the geometric relationship between the position information of the missing track point and the position information of the target track point pair meets an adding rule or not according to the first slope value and the second slope value;
wherein the timestamp of the first track point is earlier than the timestamp of the second track point.
18. The apparatus according to any one of claims 11-17, wherein the obstacle boundary information further includes an obstacle boundary type;
the trajectory modification module is further configured to:
determining whether the predicted driving track needs to be corrected or not according to the obstacle boundary type and the driving object type;
and if so, correcting the predicted driving track according to the position information of the obstacle point in the obstacle boundary, the position information of the candidate track point in the predicted driving track and the transverse safe distance of the driving object in the road section.
19. The apparatus of any of claims 11-18, further comprising:
the driving width determining module is used for determining the driving width of the driving object according to the type of the driving object;
and the safe distance determining module is used for determining the transverse safe distance of the driving object in the road section according to the driving width and the buffer distance.
20. The apparatus of claim 19, further comprising:
and the buffer distance determining module is used for determining the buffer distance according to the road section width of the road section, the obstacle boundary type in the obstacle boundary information and the type of the driving object.
21. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a method of modifying a driving trajectory according to any one of claims 1 to 10.
22. A non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute a method of correcting a travel locus according to any one of claims 1 to 10.
23. A computer program product comprising a computer program which, when executed by a processor, implements a method of modifying a driving trajectory according to any one of claims 1 to 10.
24. An autonomous vehicle comprising the electronic device of claim 21.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210400058.XA CN114670823A (en) | 2022-04-15 | 2022-04-15 | Method, device and equipment for correcting running track and automatic driving vehicle |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210400058.XA CN114670823A (en) | 2022-04-15 | 2022-04-15 | Method, device and equipment for correcting running track and automatic driving vehicle |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114670823A true CN114670823A (en) | 2022-06-28 |
Family
ID=82079038
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210400058.XA Pending CN114670823A (en) | 2022-04-15 | 2022-04-15 | Method, device and equipment for correcting running track and automatic driving vehicle |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114670823A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115639820A (en) * | 2022-10-18 | 2023-01-24 | 未岚大陆(北京)科技有限公司 | Setting method of virtual wall, autonomous mobile device, and computer-readable storage medium |
CN116331190A (en) * | 2023-03-30 | 2023-06-27 | 阿波罗智联(北京)科技有限公司 | Correction method, device and equipment for memory route of memory parking and vehicle |
CN117184060A (en) * | 2023-11-08 | 2023-12-08 | 新石器慧通(北京)科技有限公司 | Track correction method and device, unmanned vehicle and storage medium |
CN117775078A (en) * | 2024-02-28 | 2024-03-29 | 山西阳光三极科技股份有限公司 | Method for judging running direction of freight train in mine based on deep learning |
-
2022
- 2022-04-15 CN CN202210400058.XA patent/CN114670823A/en active Pending
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115639820A (en) * | 2022-10-18 | 2023-01-24 | 未岚大陆(北京)科技有限公司 | Setting method of virtual wall, autonomous mobile device, and computer-readable storage medium |
CN115639820B (en) * | 2022-10-18 | 2023-08-01 | 未岚大陆(北京)科技有限公司 | Virtual wall setting method, autonomous mobile device, and computer-readable storage medium |
CN116331190A (en) * | 2023-03-30 | 2023-06-27 | 阿波罗智联(北京)科技有限公司 | Correction method, device and equipment for memory route of memory parking and vehicle |
CN116331190B (en) * | 2023-03-30 | 2024-06-04 | 阿波罗智联(北京)科技有限公司 | Correction method, device and equipment for memory route of memory parking and vehicle |
CN117184060A (en) * | 2023-11-08 | 2023-12-08 | 新石器慧通(北京)科技有限公司 | Track correction method and device, unmanned vehicle and storage medium |
CN117184060B (en) * | 2023-11-08 | 2024-01-30 | 新石器慧通(北京)科技有限公司 | Track correction method and device, unmanned vehicle and storage medium |
CN117775078A (en) * | 2024-02-28 | 2024-03-29 | 山西阳光三极科技股份有限公司 | Method for judging running direction of freight train in mine based on deep learning |
CN117775078B (en) * | 2024-02-28 | 2024-05-07 | 山西阳光三极科技股份有限公司 | Method for judging running direction of freight train in mine based on deep learning |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN114670823A (en) | Method, device and equipment for correcting running track and automatic driving vehicle | |
CN113682318B (en) | Vehicle running control method and device | |
CN114140759A (en) | High-precision map lane line position determining method and device and automatic driving vehicle | |
CN114771572A (en) | Automatic driving track prediction method, device, equipment and storage medium | |
CN114506343A (en) | Trajectory planning method, device, equipment, storage medium and automatic driving vehicle | |
CN113119999B (en) | Method, device, equipment, medium and program product for determining automatic driving characteristics | |
CN116499487B (en) | Vehicle path planning method, device, equipment and medium | |
CN115771526A (en) | Method and device for controlling left turn of vehicle in automatic driving and automatic driving vehicle | |
CN114179805B (en) | Driving direction determining method, device, equipment and storage medium | |
CN114689061A (en) | Navigation route processing method and device of automatic driving equipment and electronic equipment | |
CN115959154A (en) | Method and device for generating lane change track and storage medium | |
KR20220098091A (en) | Method and apparatus of determining state of intersection, electronic device, storage medium | |
CN113447013A (en) | Construction road recognition method, construction road recognition apparatus, construction road recognition device, storage medium, and program product | |
CN113847923A (en) | Calculation method and device of estimated arrival time, electronic equipment and readable storage medium | |
CN113610059A (en) | Vehicle control method and device based on regional assessment and intelligent traffic management system | |
CN113361574A (en) | Training method and device of data processing model, electronic equipment and storage medium | |
CN116331190B (en) | Correction method, device and equipment for memory route of memory parking and vehicle | |
CN113447038B (en) | Route generation method, device, electronic equipment and storage medium | |
CN115716483A (en) | Obstacle trajectory prediction method and device for automatic driving vehicle and electronic equipment | |
US20230368523A1 (en) | Road network extraction method, device, and storage medium | |
CN117360548A (en) | Vehicle transverse control method, device, equipment and storage medium | |
CN118533194A (en) | Guide information evaluation method and device | |
CN116681826A (en) | Road pier generation method and device, electronic equipment and storage medium | |
CN117198040A (en) | Intersection traffic information acquisition method and device, electronic equipment and readable storage medium | |
CN116811872A (en) | Lane changing method and apparatus for vehicle, electronic device and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |