CN118170130A

CN118170130A - Driving control method and device for automatic driving and automatic driving vehicle

Info

Publication number: CN118170130A
Application number: CN202311359687.3A
Authority: CN
Inventors: 张明川
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2023-10-19
Filing date: 2023-10-19
Publication date: 2024-06-11

Abstract

The embodiment of the disclosure discloses a driving control method, a device, equipment, a storage medium, a program product and an automatic driving vehicle for automatic driving, relates to the field of automatic driving, and particularly relates to automatic driving and obstacle avoidance technology, and can be applied to an intersection obstacle avoidance scene in automatic driving. One embodiment of the method comprises the following steps: acquiring a shielding region set at the intersection where an automatic driving vehicle is currently located; acquiring a lane set at an intersection; for each shielding area and each lane, determining whether the lane is a risk lane according to the position of the shielding area and the dynamic obstacle information on the lane; determining driving control information corresponding to the lane in response to determining that the lane is a risk lane; and controlling the running of the automatic driving vehicle according to the running control information. The embodiment can realize the lane-level driving control at the intersection.

Description

Driving control method and device for automatic driving and automatic driving vehicle

Technical Field

The embodiment of the disclosure relates to the field of artificial intelligence, in particular to an automatic driving and obstacle avoidance technology, which can be applied to an intersection obstacle avoidance scene in automatic driving.

Background

When an autonomous vehicle turns through an intersection, risks such as ghost probes are likely to occur due to static shielding caused by flower beds, shrubs and the like on two sides of a lane, dynamic shielding caused by other vehicles and the like in the intersection and the like. Generally, in dangerous areas such as intersections, the running speed of an autonomous vehicle is generally limited to reduce the vehicle speed before passing through a blind area of vision, so that sufficient reaction space and time are reserved for emergency situations, and safety is ensured.

Although the defensive speed limit greatly reduces collision risks of ghost probes and the like, redundant speed limit conditions can occur, so that the passing efficiency at an intersection is affected, and even blocking conditions occur. Therefore, when defensive speed limiting is performed, higher rationality needs to be ensured so as to balance the running safety and the passing efficiency of the automatic driving vehicle at the intersection.

Disclosure of Invention

Embodiments of the present disclosure propose a travel control method, apparatus, autonomous vehicle, device, storage medium, and program product for autonomous.

In a first aspect, embodiments of the present disclosure provide a travel control method for automatic driving, the method including: acquiring a shielding region set at an intersection where an automatic driving vehicle is currently located, and acquiring the position of each shielding region in the shielding region set; acquiring a lane set at an intersection, and acquiring dynamic obstacle information on each lane in the lane set, wherein the lanes comprise lanes in the intersection and opposite lanes on the side of the intersection where the automatic driving vehicle is located; the combination result is obtained by combining the shielding areas in the shielding area set and the lanes in the lane set in any pair; for a blocking area and a lane included in the same combination in the combination result, determining whether the lane is a risk lane according to the position of the blocking area and dynamic obstacle information on the lane; determining driving control information corresponding to the lane in response to determining that the lane is a risk lane, wherein the driving control information comprises speed limiting control information; and controlling the running of the automatic driving vehicle according to the running control information.

In a second aspect, embodiments of the present disclosure provide a travel control apparatus for automatic driving, the apparatus including: the acquisition module is configured to acquire a set of shielding areas at an intersection where the automatic driving vehicle is currently located and acquire the position of each shielding area in the set of shielding areas; the acquisition module is further configured to acquire a lane set at an intersection and acquire dynamic obstacle information on each lane in the lane set, wherein the lanes comprise lanes in the intersection and opposite lanes on the side of the intersection where the automatic driving vehicle is located; the combination module is configured to obtain a combination result by combining the shielding areas in the shielding area set and the lanes in the lane set in any pair; the risk lane determining module is configured to determine whether the lane is a risk lane according to the position of the shielding area and the dynamic obstacle information on the lane for the shielding area and the lane included in the same combination in the combination result; a travel control module configured to determine travel control information corresponding to the lane in response to determining that the lane is a risk lane, wherein the travel control information includes speed limit control information; and controlling the running of the automatic driving vehicle according to the running control information.

In a third aspect, embodiments of the present disclosure provide an autonomous vehicle comprising an apparatus as described in the second aspect.

In a fourth aspect, an embodiment of the present disclosure proposes 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 the method as described in the first aspect.

In a fifth aspect, embodiments of the present disclosure propose a non-transitory computer readable storage medium storing computer instructions for causing a computer to perform a method as described in the first aspect.

In a sixth aspect, embodiments of the present disclosure propose a computer program product comprising a computer program which, when executed by a processor, implements a method as described in the first aspect.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.

Drawings

Other features, objects and advantages of the present disclosure will become more apparent upon reading of the detailed description of non-limiting embodiments, made with reference to the following drawings:

FIG. 1 is an exemplary system architecture diagram to which the present disclosure may be applied;

FIG. 2 is a flow chart of one embodiment of a travel control method for autopilot of the present disclosure;

FIG. 3a is a schematic illustration of a static occlusion region;

FIG. 3b is a schematic illustration of a dynamic occlusion region;

FIG. 4a is a schematic illustration of a lane at an intersection;

FIG. 4b is a schematic view of a lane reference and occlusion point;

FIG. 5 is a schematic structural view of one embodiment of a travel control device for autopilot in accordance with the present disclosure;

Fig. 6 is a block diagram of an electronic device for implementing a travel control method for autopilot in accordance with an embodiment of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one 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 present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

It should be noted that, without conflict, the embodiments of the present disclosure and features of the embodiments may be combined with each other. The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.

Fig. 1 illustrates an exemplary system architecture 100 to which embodiments of the travel control method for autopilot or the travel control apparatus for autopilot of the present disclosure may be applied.

As shown in fig. 1, the system architecture 100 may include an autonomous vehicle 101 and a server 102. Communication between the autonomous vehicle 101 and the server 102 may be through various communication means.

The automated guided vehicle 101 may be equipped with auxiliary devices 102 such as lidar, image acquisition devices (cameras, etc.), and sensors. The server 102 may be various servers (e.g., a data server, etc.) that provide back-end support for the autonomous vehicle 101. Both the assist device 102 and the server 103 can feed back various data information (such as the surrounding environment, the road conditions ahead, etc.) to the autonomous vehicle 101 to assist in the safe running of the autonomous vehicle.

Generally, an autonomous vehicle has a control unit (e.g., including a Central Processing Unit (CPU) or the like) to control the autonomous vehicle to execute various driving strategies. In some cases, the server 102 may not be present.

It should be noted that the running control method for automatic driving provided by the embodiment of the present disclosure is generally executed by the control unit of the automatic driving vehicle 101, and accordingly, the running control device for automatic driving is generally provided in the control unit of the automatic driving vehicle 101.

It should be understood that the number of autonomous vehicles, service devices and servers in fig. 1 is merely illustrative. There may be any number of autonomous vehicles, service devices, and servers, as desired for implementation.

With continued reference to fig. 2, a flow 200 of one embodiment of a travel control method for autopilot of the present disclosure is shown. The running control method for automatic driving includes the steps of:

step 201, acquiring a set of shielding areas at an intersection where an autonomous vehicle is currently located, and acquiring the position of each shielding area in the set of shielding areas.

In this embodiment, an intersection generally refers to a place where two or more roads (e.g., lanes) meet, such as a common intersection, a circular intersection, or the like.

The occlusion region set may consist of several occlusion regions. The occlusion area of an autonomous vehicle at an intersection may refer to the blind areas of the autonomous vehicle's view that are currently at the intersection. In general, an occlusion region of an autonomous vehicle at an intersection may include a static occlusion region caused by various static obstacles (e.g., flower beds, shrubs, etc.) at the intersection.

Optionally, the occlusion region of the autonomous vehicle at the intersection may also include a dynamic occlusion region caused by dynamic obstacles at the intersection (e.g., other vehicles, pedestrians, etc. at the intersection).

Taking fig. 3a and 3b as examples, fig. 3a shows a schematic view of a static occlusion region. As shown in fig. 3a, when an autonomous vehicle 301 turns left at an intersection, a static shielding region 303 is generated due to shielding of a flower bed or the like 302 in the vicinity of a facing lane.

Fig. 3b shows a schematic diagram of a dynamic occlusion region. As shown in fig. 3b, when an autonomous vehicle 301 turns left at an intersection, movement of other vehicles 304 subtended within the intersection creates a dynamic occlusion region 305.

The location of the occlusion region may be represented in various ways. For example, the occlusion region may be represented using its position in a specified map. For another example, the relative position of the occlusion region with respect to the current location of the autonomous vehicle may be used for representation.

In general, the occlusion region and the location of each occlusion region at the intersection where an autonomous vehicle is currently located may be determined in various ways. For example, the surrounding information may be collected by a laser radar, a camera, a sensor, and the like on the autonomous vehicle, and the position of each occlusion region and each occlusion region at the current intersection may be determined by analyzing the surrounding information, thereby forming an occlusion region set.

The determination of the occlusion region set and the position of each occlusion region may be performed by a controller of the autonomous vehicle, or may be performed by another device having a computing capability, such as a server. Thus, the autonomous vehicle may obtain the set of occlusion regions and the location of each occlusion region therein from its own memory or other device or the like.

Step 202, acquiring a lane set at an intersection, and acquiring dynamic obstacle information on each lane in the lane set.

In this embodiment, the lane set at the intersection may be composed of each lane within the intersection and each opposing lane on the side of the intersection where the autonomous vehicle is located. Typically, stop lines at an intersection are used as boundaries to distinguish between the inside and outside of the intersection. The area inside the stop line is inside the intersection, and the area outside the stop line is outside the intersection.

The lanes within the intersection typically correspond to the opposing lanes of the lane in which the autonomous vehicle is currently located. That is, although the road area in the intersection is not clearly divided into lanes, each virtual lane corresponding to the intersection may be automatically extended according to the position of each lane facing the lane where the autonomous vehicle is currently located. The opposite lanes refer to the lanes opposite to the intersection side where the lane where the automatic driving vehicle is currently located.

Dynamic obstacles may refer to any movable object on a roadway, such as other vehicles or pedestrians, and the like. Dynamic obstacle information may refer to various information related to dynamic obstacles. In general, dynamic obstacle information may be used to indicate whether a dynamic obstacle exists on a lane, and also to indicate the location of the dynamic obstacle on the lane when the dynamic obstacle exists on the lane. The dynamic obstacle information may also include various information, such as the type of dynamic obstacle, the size of the volume, the moving direction, the moving speed, and the like, according to different demands.

Taking fig. 4a as an example, fig. 4a shows a schematic view of a lane at an intersection. As shown in fig. 4a, the lanes at the intersection where the autonomous vehicle 401 makes a left turn include four opposite lanes, and the lanes within the intersection include four virtual lanes extending in the directions of the four opposite lanes, respectively.

In general, a lane set at an intersection may consist of all lanes at the intersection that may affect the travel safety of an autonomous vehicle. As shown in fig. 4a, one of the four opposite lanes is the lane in which the vehicle 402 and the vehicle 403 are located. The other of the four lanes is the lane in which the vehicle 404 and the vehicle 405 are located. Since only dynamic obstacles and the like in the two opposite lanes may affect the running safety of the autonomous vehicle 401, and various obstacles and the like in the virtual lanes 406 and 407 of the four virtual lanes within the intersection may affect the running safety of the autonomous vehicle 401, while the other two opposite lanes generally do not affect the running safety of the autonomous vehicle 401, the road set of the current autonomous vehicle 401 at the intersection may be composed of the lanes in which the vehicles 402 and 403 are located, the lanes in which the vehicles 404 and 405 are located, the virtual lanes 406 and the virtual lanes 407.

Wherein the set of lanes at the intersection and the dynamic obstacle information on each lane may be determined in various ways. For example, the set of lanes at the intersection and the dynamic obstacle information on each lane thereof may be determined by map mapping, object recognition, and the like based on a high-precision map at the intersection and an image acquired by an autonomous vehicle or the like.

For another example, lane sets corresponding to the respective positions at the intersections may be recorded in advance. At this time, the corresponding lane set may be determined according to the current position of the autonomous vehicle. Meanwhile, according to surrounding environment images and the like acquired by the automatic driving vehicle, the position of an obstacle existing on each lane in the lane set is determined by various existing target recognition methods and the like.

Step 203, obtaining a combination result by combining the shielding areas in the shielding area set and the lanes in the lane set in any two pairs.

In this embodiment, after the occlusion region set and the lane set are obtained, each occlusion region and each lane may be combined in any pair, so as to obtain a combination result formed by a plurality of combinations. In general, each combination may include one occlusion region and one lane.

And 204, for the blocking area and the lane included in the same combination in the combination result, determining whether the lane is a risk lane according to the position of the blocking area and the dynamic obstacle information on the lane.

In the present embodiment, the risk lane refers to a lane in which there are factors that may affect the running safety of the autonomous vehicle. For example, a blind field of view on a risk lane or movement of a dynamic obstacle or the like may cause an autonomous vehicle to present a collision risk or the like.

For the shielding region and the lane in the same combination, various methods can be flexibly adopted to determine whether the lane is a risk lane according to the position of the shielding region and the dynamic obstacle information on the lane.

For example, the position of the nearest dynamic obstacle to the occlusion area may be determined first according to the position of the occlusion area and the dynamic obstacle information on the lane, and then the distance between the nearest dynamic obstacle to the occlusion area and the autonomous vehicle may be determined based on the position. Then, whether the moving direction and the moving speed of the dynamic barrier closest to the shielding area and the moving direction and the moving speed of the automatic driving vehicle intersect with the moving track of the automatic driving vehicle when passing through the intersection or not is calculated, and if the moving track and the moving track intersect with the moving track, the lane is determined to be a risk lane.

And step 205, in response to determining that the lane is a risk lane, determining the driving control information corresponding to the lane.

In this embodiment, if it is determined that the lane is a risk lane, the driving control information corresponding to the lane may be further determined. At this time, the travel control information may include speed limit control information. Among them, speed limit control information is generally used to describe various speed limit controls for an autonomous vehicle. For example, the speed limit control information may indicate whether to speed limit the autonomous vehicle. For another example, when the speed limit control information indicates that the speed limit control of the automatically driven vehicle is required, the speed limit control information further includes information such as a speed limit area at the intersection.

If it is determined that the lane is not a risk lane, the travel control information corresponding to the lane may indicate that the speed of the autonomous vehicle is not required to be limited.

Step 206, controlling the running of the automatic driving vehicle according to the running control information.

In this embodiment, after the travel control information is obtained, the travel of the autonomous vehicle at the intersection may be further controlled according to the control manner indicated by the travel control information.

For example, the travel control information includes speed limit control information, and the speed limit travel of the autonomous vehicle at the intersection may be further controlled based on the speed limit control information.

As an example, when the speed limit control information includes a speed limit region, the automatically driven vehicle may be controlled to speed-limit travel in the determined speed limit region to secure travel safety.

For another example, when the travel control information indicates that there is no need to speed limit the autonomous vehicle, the autonomous vehicle may be controlled to travel normally at the intersection (e.g., maintain vehicle speed, accelerate overtake, etc.) to avoid redundant speed limits affecting the efficiency of traffic at the intersection.

In general, when an intersection includes two or more lanes, corresponding travel control information may be determined for each lane, and then travel of the autonomous vehicle may be comprehensively controlled by integrating the travel control information of each lane.

For example, if the travel control information corresponding to one lane indicates speed-limiting travel and includes a corresponding speed-limiting section, the travel control information corresponding to the other lane indicates that speed-limiting travel is not required. The autonomous vehicle can be controlled to perform speed-limiting travel in the speed-limiting section without excessive speed limiting in other travel areas.

For another example, if the travel control information corresponding to one lane indicates speed-limiting travel and includes a corresponding speed-limiting section, and the travel control information corresponding to the other lane also indicates speed-limiting travel and includes a corresponding speed-limiting section, the two speed-limiting sections may be combined as a final speed-limiting section to control the automated driving vehicle to perform speed-limiting travel in a union region of the two speed-limiting sections.

For another example, if the running control information corresponding to the two lanes indicates that speed-limiting running is not needed, the automatic driving vehicle does not need to limit speed when passing through the intersection, and traffic jam and other conditions caused by redundant speed limiting are avoided.

According to the running control method for automatic running, all lanes which possibly influence the running safety of the automatic driving vehicle at the road junction are analyzed respectively, corresponding speed limit control information is determined from the lane level, and accuracy of speed limit control of the automatic driving vehicle at the road junction can be improved. In the prior art, for each intersection, there are usually only two driving controls of speed limit or non-speed limit. Compared with the prior art, the scheme of the application analyzes the speed limit control information corresponding to different lanes respectively from the lane level, realizes the speed limit control of the lane level, and can avoid the conditions that the redundant speed limit at the intersection influences the traffic efficiency or causes traffic jam and the like while reducing the risks of ghost probes and the like possibly existing at the intersection.

In some optional implementations of this embodiment, after any two-to-two combinations of the occlusion regions in the occlusion region set and the lanes in the lane set are performed, for each directly obtained combination, it may be first determined whether the combination is a valid combination. All valid combinations can then be combined as a combined result.

Specifically, for the occlusion region and the lane in the same combination, it may be determined whether the combination is a valid combination by at least one of the following screening methods:

(1) In response to determining that the occlusion region occludes the lane, the combination is determined to be a valid combination.

In the screening method, it may be determined whether the blocking area blocks the lane, that is, whether an intersecting area exists between the blocking area and the lane. Specifically, whether the blocking area blocks the lane may be determined according to the position of the blocking area and the position of the lane.

If the occlusion region occludes the lane, the combination may be determined to be a valid combination. If the shielding area does not shield the lane, the lane does not influence the running safety of the automatic driving vehicle due to the shielding area, so that the combination can be deleted.

(2) And determining that the combination is an effective combination in response to determining that the distance between the shielding point in the shielding area and the lane reference line in the intersection is less than a preset distance threshold.

In the present screening method, the blocking point may refer to a point closest to the lane reference line in the blocking area. The lane reference line may refer to a lane reference line of a road on which the autonomous vehicle is to travel. It should be noted that, in general, the lane reference line of each road is designed in advance. For example, the lane reference may be determined directly from the corresponding high-definition map. The distance threshold may be preset by a related technician according to an actual application scenario.

Taking fig. 4b as an example, fig. 4b shows a schematic view of the lane reference line and the occlusion point. As shown in fig. 4b, the point of the autonomous vehicle 401 closest to the lane reference line 408 in the occlusion region 409 at the intersection is taken as occlusion point "a". The distance between the occlusion point "A" and the lane reference line 408 is shown at 410.

If the distance between the shielding point in the shielding area and the lane reference line in the intersection is smaller than the preset distance threshold value, the combination can be determined to be an effective combination. If the distance between the shielding point in the shielding area and the lane reference line in the intersection is not smaller than the preset distance threshold, the shielding area is far away from the lane reference line, the running safety of the automatic driving vehicle is not affected, and therefore the combination can be deleted.

(3) And in response to determining that the occlusion area of the occlusion region for the lane is less than a preset area threshold, determining that the combination is a valid combination.

In the screening method, the area of the shielding area with respect to the lane may refer to the area of the area where the shielding area intersects with the lane. The area threshold may be preset by a related technician according to an actual application scenario.

If the shielding area of the shielding area for the lane is smaller than a preset area threshold value, the combination can be determined to be an effective combination. If the shielding area of the shielding area for the lane is not smaller than the preset area threshold, the shielding area can be indicated to be too large, namely abnormal, so that the combination can be deleted.

(4) In response to determining that no non-traversable obstacle exists between the occlusion region and the lane reference line, the combination is determined to be a valid combination.

In this screening method, an obstacle that cannot be spanned by an autonomous vehicle must be bypassed. The non-traversable obstacles may be various types of non-traversable obstacles on the road. For example, some hard isolation and dead cars on the road, etc.

If no non-straddlable obstacle exists between the occlusion region and the lane reference line, the combination may be determined to be a valid combination. If an inextensible obstacle exists between the shielding area and the lane reference line, the automatic driving vehicle is required to detour, calculation such as speed limiting control is not required, and the combination can be deleted.

(5) In response to determining that a dynamic obstacle exists between the occlusion region and the lane reference line, and that a length of time required for the dynamic obstacle to leave between the occlusion region and the lane reference line is less than a preset length of time threshold, the combination is determined to be a valid combination.

In the screening method, the time period required for the dynamic obstacle to leave the blocking area and the lane reference line can be determined according to the running direction, the running speed and the like of the dynamic obstacle. If a dynamic obstacle exists between the shielding area and the lane reference line, and the length of time required for the dynamic obstacle to leave between the shielding area and the lane reference line is smaller than a preset time length threshold value, the combination can be determined to be an effective combination.

If no dynamic obstacle exists between the shielding area and the lane reference line or the required length of the existing dynamic obstacle leaving the space between the shielding area and the lane reference line is not smaller than a preset time threshold, the dynamic obstacle is indicated not to influence the running safety of the automatic driving vehicle, and therefore the combination can be deleted.

It should be noted that, the above screening methods for the combination may be flexibly selected and used according to actual application scenarios, or may be used in combination with multiple screening methods. The above various screening methods are only examples, and related technicians may flexibly set other various screening methods according to actual application scenarios.

The conditions of no need of speed limit control calculation and the like are screened out through various screening modes, subsequent useless calculation can be avoided, so that the calculation efficiency is improved, the conditions of subsequent erroneous speed limit control and the like caused by redundant calculation can be avoided, and the accuracy of speed limit control is improved.

In some optional implementations of the present embodiment, for each effective combination including an occlusion region and a lane, it may be determined whether the lane is a risk lane by:

Step one, according to the position of the shielding area and the dynamic obstacle information on the lane, taking the dynamic obstacle closest to the shielding point in the shielding area on the lane as a target obstacle, and taking the distance between the target obstacle and the shielding point as a target distance.

In this step, the dynamic obstacle information may include the position of each dynamic obstacle on the lane. The shielding point is the nearest point from the lane reference line in the shielding area.

Specifically, the corresponding shielding point may be determined according to the position of the shielding area, and then, the distance between each dynamic obstacle and the shielding point may be determined according to the position of each dynamic obstacle, so that the dynamic obstacle with the shortest distance to the shielding point is determined as the target obstacle. Meanwhile, the distance between the target obstacle and the shielding point may be determined as the target distance.

And step two, determining the lane as a risk lane in response to determining that the target distance is larger than a preset safety threshold.

In this step, it may be determined whether the target distance is greater than a preset safety threshold, and if the target distance is greater than the preset safety threshold, that is, if there is a risk such as collision between the nearest dynamic obstacle on the lane and the autonomous vehicle, it may be determined that the lane is a risk lane. Correspondingly, if the target distance is not greater than the preset safety threshold value, the fact that the latest dynamic obstacle and the automatic driving vehicle have no collision risk and the like is indicated, and the lane can be determined to be a safety lane. The safety threshold may be preset by a related technician according to an actual application scenario.

Alternatively, the safety threshold may be determined by:

Step one, determining an intersection point of the lane and a lane reference line, and determining a distance between the intersection point and an automatic driving vehicle as a first distance.

In this step, the intersection of the position of the lane and the position of the lane reference line may be calculated from the two positions. Then, the distance between the intersection and the autonomous vehicle may be calculated as the first distance based on the current location of the autonomous vehicle.

And step two, acquiring the braking distance of the automatic driving vehicle.

In this step, the corresponding braking distance may be determined according to the attribute of the autonomous vehicle.

And thirdly, determining a safety threshold according to the first distance and the braking distance.

In this step, after the first distance and the braking distance are obtained, various methods may be flexibly used to determine the safety threshold. For example, a difference between the braking distance and the first distance may be calculated as the safety buffer distance, and then the designated distance may be extended as the safety threshold based on the safety buffer distance. The specified distance can be set by a technician according to an actual application scene. As an example, the specified distance may be determined according to the braking distance.

For example, a difference between the first preset distance and the braking distance may be calculated, and then a maximum value is selected from the difference and the second preset distance as the specified distance. The first preset distance is greater than the second preset distance, and the first preset distance and the second preset distance can be preset by a technician. For example, the first preset distance is 5 meters and the second preset distance is 3 meters.

By determining the nearest dynamic obstacle on each lane to the shielding point in the corresponding shielding area and comparing the distance between the nearest dynamic obstacle and the corresponding shielding point with a preset safety threshold value, whether collision and other risks can occur between the dynamic obstacle on each lane and the automatic driving vehicle can be accurately judged, and then the running of the automatic driving vehicle is controlled to ensure safety.

In some optional implementations of this embodiment, the real-time risk information of the lane may be determined first according to the position of the shielding area and the dynamic obstacle information on the lane, and if the real-time risk information indicates that the lane is a risk lane, the lane may be determined to be a risk lane. If the real-time risk information indicates that the lane is not a risk lane, and in response to determining that the historical risk information corresponding to the lane indicates that the lane is a risk lane, the lane is also determined to be a risk lane.

The real-time risk information can be determined according to the position of the shielding area and the dynamic obstacle information on the lane by adopting the various methods.

The historical risk information for a lane may represent risk information corresponding to a time of the lane prior to the current time. For example, the historical risk information may include risk information for the lane at a time immediately preceding the current time.

Generally, an automatic driving vehicle can determine a set of shielding areas and a set of lanes at an intersection according to collected images (such as surrounding environment images and the like) and data (such as self positions, positions of surrounding obstacles and the like), so as to determine whether each lane is a risk lane in real time, and perform running control such as speed limiting at the risk lane. At this time, whether each lane is a risk lane or not may be comprehensively determined according to the real-time risk information corresponding to each lane obtained based on the current frame image and the historical risk information corresponding to the previous frame image.

For example, when it is determined in real time that a certain lane is not a risk lane based on the current frame image, historical risk information obtained based on the previous frame image may be further obtained, and if the historical risk information indicates that the lane is a risk lane, the lane may be finally determined to be a risk lane.

Correspondingly, if the real-time risk information indicates that the lane is not a risk lane and the historical risk information also indicates that the lane is not a risk lane, it may be eventually determined that the lane is not a risk lane.

By combining the historical risk information, the risk lane can be more comprehensively and accurately determined, so that the running of the automatic driving vehicle at the intersection can be more accurately controlled, and the running safety is ensured.

In some alternative implementations of the present embodiment, the speed limit control information may include a speed limit interval of the autonomous vehicle. Specifically, for each lane, the start point of the speed limit section may be determined based on the intersection of the lane and the above-described lane reference line, and the braking distance of the automatically driven vehicle. For example, the distance between the intersection point and the automatic driving vehicle may be calculated first, then the difference between the distance and the first reserved safety distance is calculated as a target difference, and then the maximum value is selected from the target difference and the braking distance, so that a point on the road to be driven, where the distance between the road to be driven and the automatic driving vehicle is the maximum value, may be determined as the starting point of the speed limit section.

Then, the end point of the speed limit section can be determined from the intersection point of the lane and the lane reference line and the determined start point of the speed limit section. For example, the distance between the intersection and the automatically driven vehicle may be calculated first, then the difference between the distance and the first reserved safety distance may be calculated as a target difference, then a point on the road to be driven, where the distance between the point and the start point of the speed limit section is the target difference, may be determined as a candidate end point, and at the same time, a point on the road to be driven, where the distance between the point and the start point of the speed limit section is the second reserved safety distance, may be determined as a candidate end point of the speed limit section. Then, a candidate end point farthest from the section of the speed limit section is selected from among the candidate end points as the end point of the speed limit section.

The first reserved safety distance and the second reserved safety distance may be preset by a related technician. The first reserved safety distance and the second reserved safety distance may be the same or different.

Optionally, the speed limit control information may also include a maximum speed limit of the autonomous vehicle. Specifically, the viewing distance of the autonomous vehicle may be acquired first, and then the maximum speed limit may be determined based on the viewing distance of the autonomous vehicle. Wherein, the driving sight distance can be determined according to the attribute of the automatic driving vehicle.

For example, if the vehicle viewing distance is less than the first viewing distance threshold, a first preset speed (e.g., 2 meters/second) may be determined as the maximum speed limit. If the driving sight distance is greater than the second sight distance threshold value, a second preset speed (such as 4 m/s) can be determined as the maximum speed limit. Typically, the second line of sight threshold is greater than the first line of sight threshold. The second preset speed is greater than the first preset speed. If the driving sight distance is between the first sight distance threshold value and the second sight distance threshold value, the maximum speed limit can be determined by a linear interpolation mode. Wherein, the first sight distance threshold value, the second sight distance threshold value, the first preset speed, the second preset speed and the like can be preset by related technicians.

On the basis of the braking distance, the speed limit section is determined by combining the intersection point of the lane and the lane reference line of the to-be-driven road of the automatic driving vehicle, so that the situations of sudden braking and the like of the automatic driving vehicle caused by too close speed limit section can be avoided. Meanwhile, more accurate speed limiting control of the automatic driving vehicle can be achieved through the control of the maximum speed limit.

With further reference to fig. 5, as an implementation of the method shown in the above figures, the present disclosure provides an embodiment of a travel control apparatus for automatic driving, which corresponds to the method embodiment shown in fig. 2, and which is particularly applicable to various electronic devices.

As shown in fig. 5, the travel control device 500 for automatic driving provided in the present embodiment includes an acquisition module 501, a combination module 502, a risk lane determination module 503, and a travel control module 504. Wherein the obtaining module 501 is configured to obtain a set of occlusion areas at an intersection where an autonomous vehicle is currently located, and obtain a position of each occlusion area in the set of occlusion areas; acquiring a lane set at an intersection, and acquiring dynamic obstacle information on each lane in the lane set, wherein the lanes comprise opposite directions of lanes in the intersection and sides of the intersection where the automatic driving vehicles are located; the combination module 502 is configured to obtain a combination result by combining the shielding areas in the shielding area set and the lanes in the lane set in any two pairs; the risk lane determining module 503 is configured to determine, for an occlusion region and a lane included in the same combination in the combination result, whether the lane is a risk lane according to a position of the occlusion region and dynamic obstacle information on the lane; the travel control module 504 is configured to determine, in response to determining that the lane is a risk lane, travel control information corresponding to the lane, wherein the travel control information includes speed limit control information; and controlling the running of the automatic driving vehicle according to the running control information.

In the present embodiment, in the travel control apparatus 500 for automated driving: the specific processing of the obtaining module 501, the combining module 502, the risk lane determining module 503 and the driving control module 504 and the technical effects thereof may refer to the relevant descriptions of steps 201 to 206 in the corresponding embodiment of fig. 2, and are not repeated herein.

In some optional implementations of the present embodiment, the occlusion regions in the occlusion region set include a static occlusion region and a dynamic occlusion region.

In some optional implementations of the present embodiments, the combinations in the combined result are valid combinations; and the risk lane determination module 503 is further configured to: for the occlusion region and the lane in the same combination obtained by any two-by-two combination, determining whether the combination is a valid combination by at least one screening method as follows: responsive to determining that the occlusion region occludes the lane, determining that the combination is a valid combination; determining that the combination is an effective combination in response to determining that the distance between the shielding point in the shielding area and the lane reference line in the intersection is smaller than a preset distance threshold, wherein the shielding point is the nearest point to the lane reference line in the shielding area; determining that the combination is an effective combination in response to determining that the occlusion area of the occlusion region for the lane is less than a preset area threshold; responsive to determining that no non-spanable obstacle exists between the occlusion region and the lane reference line, determining that the combination is a valid combination; in response to determining that a dynamic obstacle exists between the occlusion region and the lane reference line, and that a length of time required for the dynamic obstacle to leave between the occlusion region and the lane reference line is less than a preset length of time threshold, the combination is determined to be a valid combination.

In some optional implementations of the present embodiment, the risk lane determination module 503 is further configured to: according to the position of the shielding area and the dynamic obstacle information on the lane, taking the dynamic obstacle closest to the shielding point in the shielding area on the lane as a target obstacle, and taking the distance between the target obstacle and the shielding point as a target distance; and determining the lane as a risk lane in response to determining that the target distance is greater than a preset safety threshold, wherein the safety threshold is determined by the following steps: determining an intersection point of the lane and a lane reference line, and determining a distance between the intersection point and the automatic driving vehicle as a first distance; acquiring a braking distance of an automatic driving vehicle; a safety threshold is determined based on the first distance and the braking distance.

In some optional implementations of the present embodiment, the risk lane determination module 503 is further configured to:

Determining real-time risk information of the lane according to the position of the shielding area and the dynamic obstacle information on the lane;

determining that the lane is a risk lane in response to the real-time risk information indicating that the lane is a risk lane;

and in response to determining that the real-time risk information indicates that the lane is not a risk lane, and in response to determining that the historical risk information corresponding to the lane indicates that the lane is a risk lane, determining that the lane is a risk lane.

In some alternative implementations of the present embodiment, the speed limit control information includes a speed limit interval of the autonomous vehicle; and travel control module 504 is further configured to: determining the starting point of the speed limit section according to the intersection point and the braking distance of the automatic driving vehicle; and determining the end point of the speed limit section according to the intersection point and the start point of the speed limit section.

In some alternative implementations of the present embodiment, the speed limit control information includes a maximum speed limit of the autonomous vehicle; and travel control module 504 is further configured to: acquiring a driving sight distance of an automatic driving vehicle; and determining the maximum speed limit according to the driving sight distance.

According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

Fig. 6 illustrates a schematic block diagram of an example electronic device 600 that may 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 processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 6, the apparatus 600 includes a computing unit 601 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 602 or a computer program loaded from a storage unit 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 may also be stored. The computing unit 601, ROM 602, and RAM 603 are connected to each other by a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.

Various components in the device 600 are connected to the I/O interface 605, including: an input unit 606 such as a keyboard, mouse, etc.; an output unit 607 such as various types of displays, speakers, and the like; a storage unit 608, such as a magnetic disk, optical disk, or the like; and a communication unit 609 such as a network card, modem, wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks. The computing unit 601 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 601 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The calculation unit 601 executes the respective methods and processes described above, such as a running control method for automatic driving. For example, in some embodiments, the travel control method for autopilot may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as storage unit 608. In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 600 via the ROM 602 and/or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the travel control method for autopilot described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to perform the driving control method for autopilot by any other suitable means (e.g. by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code 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 code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. 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. The 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 pointing device (e.g., a mouse or 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 may 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 input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background 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 background, 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), and the internet.

The computer system may include a client and a server. The client and server are typically 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 may be a cloud server, a server of a distributed system, or a server incorporating a blockchain.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel, sequentially, or in a different order, provided that the desired results of the technical solutions provided by the present disclosure are achieved, and are not limited herein.

The above detailed description should not be taken as limiting the scope of the present disclosure. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present disclosure are intended to be included within the scope of the present disclosure.

Claims

1. A running control method for automatic driving, comprising:

Acquiring a shielding region set at an intersection where an automatic driving vehicle is currently located, and acquiring the position of each shielding region in the shielding region set;

Acquiring a lane set at the intersection, and acquiring dynamic obstacle information on each lane in the lane set, wherein the lanes comprise lanes in the intersection and opposite lanes on the side of the intersection where the automatic driving vehicle is located;

the combination result is obtained by combining the shielding areas in the shielding area set and the lanes in the lane set in any pair;

For a blocking area and a lane included in the same combination in the combination result, determining whether the lane is a risk lane according to the position of the blocking area and dynamic obstacle information on the lane;

Determining driving control information corresponding to the lane in response to determining that the lane is a risk lane, wherein the driving control information comprises speed limiting control information;

And controlling the running of the automatic driving vehicle according to the running control information.

2. The method of claim 1, wherein occlusion regions in the set of occlusion regions comprise a static occlusion region and a dynamic occlusion region.

3. The method of claim 1 or 2, wherein the combination in the combined result is a valid combination; the method further comprises:

and for the shielding areas and the lanes in the same combination obtained by any two-by-two combination, determining whether the combination is a valid combination or not by at least one screening mode as follows:

responsive to determining that the occlusion region occludes the lane, determining that the combination is a valid combination;

Determining that the combination is an effective combination in response to determining that the distance between the shielding point in the shielding area and the lane reference line in the intersection is smaller than a preset distance threshold, wherein the shielding point is the closest point to the lane reference line in the shielding area;

Determining that the combination is an effective combination in response to determining that the occlusion area of the occlusion region for the lane is less than a preset area threshold;

responsive to determining that no non-spanable obstacle exists between the occlusion region and the lane reference line, determining that the combination is a valid combination;

And in response to determining that a dynamic obstacle exists between the occlusion region and the lane reference line, and that the length of time required for the dynamic obstacle to leave between the occlusion region and the lane reference line is less than a preset duration threshold, determining that the combination is a valid combination.

4. A method according to claim 3, wherein said determining whether a lane is a risk lane based on the location of the occlusion region and dynamic obstacle information on the lane for occlusion regions and lanes included in the same combination in the combination result comprises:

according to the position of the shielding area and the dynamic obstacle information on the lane, taking the dynamic obstacle closest to the shielding point in the shielding area on the lane as a target obstacle, and taking the distance between the target obstacle and the shielding point as a target distance;

In response to determining that the target distance is greater than a preset safety threshold, determining that the lane is a risk lane, wherein the safety threshold is determined by:

determining an intersection of the lane and the lane reference line, and determining a distance between the intersection and the autonomous vehicle as a first distance;

Acquiring a braking distance of the automatic driving vehicle;

and determining a safety threshold according to the first distance and the braking distance.

5. The method of claim 1, wherein the determining whether the lane is a risk lane based on the location of the occlusion region and dynamic obstacle information on the lane comprises:

6. The method of claim 5, wherein the speed limit control information includes a speed limit interval of the autonomous vehicle; and

The determining the speed limit control information corresponding to the lane comprises the following steps:

Determining the starting point of a speed limit section according to the intersection point and the braking distance of the automatic driving vehicle;

and determining the end point of the speed limit section according to the intersection point and the start point of the speed limit section.

7. The method of claim 6, wherein the speed limit control information includes a maximum speed limit of the autonomous vehicle; and

Acquiring a driving sight distance of the automatic driving vehicle;

and determining the maximum speed limit according to the driving sight distance.

8. A travel control device for automatic driving, comprising:

The system comprises an acquisition module, a control module and a control module, wherein the acquisition module is configured to acquire a shielding region set at an intersection where an automatic driving vehicle is currently located and acquire the position of each shielding region in the shielding region set;

The acquisition module is further configured to acquire a lane set at the intersection and acquire dynamic obstacle information on each lane in the lane set, wherein the lanes comprise lanes in the intersection and opposite lanes on the side of the intersection where the autonomous vehicle is located;

The combination module is configured to obtain a combination result by combining the shielding areas in the shielding area set and the lanes in the lane set in any pair;

the risk lane determining module is configured to determine whether the lane is a risk lane according to the position of the shielding area and the dynamic obstacle information on the lane for the shielding area and the lane included in the same combination in the combination result;

A travel control module configured to determine travel control information corresponding to the lane in response to determining that the lane is a risk lane, wherein the travel control information includes speed limit control information; and controlling the running of the automatic driving vehicle according to the running control information.

9. The apparatus of claim 8, wherein occlusion regions in the set of occlusion regions comprise a static occlusion region and a dynamic occlusion region.

10. The apparatus of claim 8 or 9, wherein a combination of the combination results is a valid combination; and

The risk lane determination module is further configured to: and for the shielding areas and the lanes in the same combination obtained by any two-by-two combination, determining whether the combination is a valid combination or not by at least one screening mode as follows:

11. The apparatus of claim 10, wherein the risk lane determination module is further configured to:

Acquiring a braking distance of the automatic driving vehicle;

12. The apparatus of claim 11, wherein the risk lane determination module is further configured to: determining real-time risk information of the lane according to the position of the shielding area and the dynamic obstacle information on the lane;

13. The apparatus of claim 12, wherein the speed limit control information includes a speed limit interval of the autonomous vehicle; and

The travel control module is further configured to: determining the starting point of a speed limit section according to the intersection point and the braking distance of the automatic driving vehicle;

14. The apparatus of claim 13, wherein the speed limit control information includes a maximum speed limit of the autonomous vehicle; and

The travel control module is further configured to: acquiring a driving sight distance of the automatic driving vehicle;

15. An autonomous vehicle comprising the travel control device of any one of claims 7 to 14.

16. 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 the method of any one of claims 1-7.

17. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-7.

18. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any of claims 1-7.