CN114426030B - Pedestrian passing intention estimation method, device, equipment and automobile - Google Patents
Pedestrian passing intention estimation method, device, equipment and automobile Download PDFInfo
- Publication number
- CN114426030B CN114426030B CN202011176754.4A CN202011176754A CN114426030B CN 114426030 B CN114426030 B CN 114426030B CN 202011176754 A CN202011176754 A CN 202011176754A CN 114426030 B CN114426030 B CN 114426030B
- Authority
- CN
- China
- Prior art keywords
- pedestrian
- moment
- intention
- deep
- lane
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 56
- 239000002344 surface layer Substances 0.000 claims description 32
- 238000012545 processing Methods 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 6
- 239000010410 layer Substances 0.000 claims description 5
- 230000008569 process Effects 0.000 description 17
- 230000003993 interaction Effects 0.000 description 15
- 230000006399 behavior Effects 0.000 description 10
- 230000003068 static effect Effects 0.000 description 10
- 230000008846 dynamic interplay Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 239000007787 solid Substances 0.000 description 3
- 238000009825 accumulation Methods 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 230000016776 visual perception Effects 0.000 description 1
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
- 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
-
- 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
- B60W2552/53—Road markings, e.g. lane marker or crosswalk
-
- 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
-
- 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
- B60W2554/404—Characteristics
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Human Computer Interaction (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Traffic Control Systems (AREA)
Abstract
The application provides a pedestrian passing intention estimation method, device, equipment and an automobile, and relates to the field of intelligent driving. Wherein the method comprises the following steps: the method comprises the steps of obtaining state information of at least one pedestrian around a vehicle, calculating the surface intention of a first pedestrian at a first moment according to the state information of the first pedestrian at the first moment and the deep intention of the first pedestrian at a second moment, so as to obtain a surface intention estimation result with high precision, real-time performance and accuracy, and then determining whether the first pedestrian passes through a road at the first moment according to the surface intention of the first pedestrian at the first moment.
Description
Technical Field
The invention relates to the technical field of intelligent driving, in particular to a pedestrian passing intention estimation method, device, equipment and an automobile.
Background
With the advent of intelligent driving, intelligent vehicles became the target of major research by various manufacturers. For intelligent driving, the implementation process mainly comprises the steps of positioning, sensing, predicting, planning control and the like. The prediction step is mainly used for estimating the future position and the future behavior of surrounding targets so that the planning control module makes corresponding decisions, and therefore traffic accidents are avoided.
However, predicting the motion trail and intent of pedestrians is a considerable challenge due to the characteristics of high dynamics of pedestrians, less constraints of maps and traffic rules, etc. If the prediction is inaccurate, the vehicle is easy to collide with personnel, and thus, the vehicle is hidden danger.
Disclosure of Invention
In order to solve the above-mentioned problems, embodiments of the present application provide a pedestrian passing intention estimation method, apparatus, device, and automobile.
In a first aspect, the present application provides a pedestrian crossing intention estimation method, including: acquiring state information of at least one pedestrian around the vehicle, wherein the at least one pedestrian comprises a first pedestrian; according to the state information of the first pedestrian at the first moment and the deep intention of the first pedestrian at the second moment, calculating the surface intention of the first pedestrian at the first moment, wherein the deep intention is the probability that the first pedestrian passes through the road in the whole life cycle before the first moment, and the surface intention is the probability that the first pedestrian is or is about to pass through the road at the current moment; and determining whether the first pedestrian passes through the road at the first moment according to the surface layer intention of the first pedestrian at the first moment.
In this embodiment, by continuously acquiring information such as pedestrians on a road on which a vehicle runs, lane lines, lane marks, surrounding other vehicles, and the like, and then analyzing state information such as behavior features, static interaction features, dynamic interaction features, and the like of the pedestrians at the current moment, a deep intention at the previous moment is combined, and a surface intention estimation result with high precision, real-time performance and accuracy can be obtained.
In one embodiment, before the calculating the surface layer intention of the first pedestrian at the first moment according to the state information of the first pedestrian at the first moment and the deep intention of the first pedestrian at the second moment, the method includes: according to the state information of the first pedestrian at the first moment, calculating likelihood probability of pedestrian characteristics of the first pedestrian at the first moment; the calculating the surface layer intention of the first pedestrian at the first moment according to the state information of the first pedestrian at the first moment and the deep intention of the first pedestrian at the second moment comprises the following steps: and calculating the surface layer intention of the first pedestrian at the first moment according to the likelihood probability of the pedestrian characteristic of the first pedestrian at the first moment and the deep intention of the first pedestrian at the second moment.
In this embodiment, in the process of acquiring the status information of the pedestrian, the vehicle may have errors or errors because the monitored information is not necessarily completely correct at some time, for example, because the pedestrian target is small and the movement speed is slow, the pedestrian is sometimes not necessarily detected, the speed of the pedestrian is detected to be unchanged, and other errors, which may have a great influence on the characteristics of the pedestrian, so after the status information of the pedestrian is obtained, fusion filtering is performed on various detected information, and certain smoothing is performed on the errors, so that the characteristics of the pedestrian corresponding to the detected status information of the pedestrian are more true.
In one embodiment, the method further comprises: when the surface layer intention of the first pedestrian at the first moment is larger than a set threshold value, controlling a loudspeaker to play an early warning signal and/or displaying early warning information on a display screen.
In one embodiment, before the calculating the surface intent of the first pedestrian at the first moment according to the state information of the first pedestrian at the first moment and the deep intent of the first pedestrian at the second moment, the method includes: calculating the state information of the predicted first pedestrian at the first moment according to the state information of the first pedestrian at the second moment and the surface layer intention of the first pedestrian at the second moment; and calculating the deep intention of the first pedestrian at the first moment according to the predicted state information of the first pedestrian at the first moment, the state information of the first pedestrian at the first moment and the deep intention of the first pedestrian at the second moment.
In this embodiment, the deep intention at the previous time is re-estimated and updated based on the deep intention at the previous time, the state information of the pedestrian at the current time, and the state information of the pedestrian predicted at the current time, so that the reliability of the new deep intention increases with the accumulation of the history observation information.
In one embodiment, the method further comprises: and calculating the lane intention of at least one lane of a road where the vehicle is located according to the state information of the first pedestrian at the first moment and the surface layer intention of the first pedestrian at the first moment, wherein the lane intention is the probability that the first pedestrian passes through the first lane, and the at least one lane comprises the first lane.
In this embodiment, the road structure of each lane and the static interaction feature and the dynamic interaction feature of the related vehicle at the lane level are calculated according to the state information of the first pedestrian at the first moment, and the behavior feature of the target pedestrian is extracted, and then the lane intention of the pedestrian is calculated, so that the vehicle can output the passing intention of the pedestrian relative to each lane, and the automatic driving vehicle can respond in advance.
In a second aspect, the present application also provides a pedestrian crossing intention estimation device, including: an acquisition unit configured to acquire status information of at least one pedestrian around a vehicle, the at least one pedestrian including a first pedestrian; the processing unit is used for calculating the surface layer intention of the first pedestrian at the first moment according to the state information of the first pedestrian at the first moment and the deep layer intention of the first pedestrian at the second moment, wherein the deep layer intention is the probability that the first pedestrian passes through the road in the whole life cycle before the first moment, and the surface layer intention is the probability that the first pedestrian is passing through the road at the current moment or is about to pass through the road; the processing unit is further configured to determine, according to the surface intention of the first pedestrian at the first moment, whether the first pedestrian passes through the road at the first moment.
In one embodiment, the processing unit is specifically configured to calculate likelihood probability of a pedestrian feature of the first pedestrian at the first moment according to the state information of the first pedestrian at the first moment; and calculating the surface layer intention of the first pedestrian at the first moment according to the likelihood probability of the pedestrian characteristic of the first pedestrian at the first moment and the deep intention of the first pedestrian at the second moment.
In one embodiment, the processing unit is further configured to control the speaker to play the early warning signal and/or display the early warning information on the display screen when the surface intention of the first pedestrian at the first moment is greater than a set threshold.
In one embodiment, the processing unit is further configured to calculate, according to the state information of the first pedestrian at the second moment and the surface intention of the first pedestrian at the second moment, state information of the predicted first pedestrian at the first moment; and calculating the deep intention of the first pedestrian at the first moment according to the predicted state information of the first pedestrian at the first moment, the state information of the first pedestrian at the first moment and the deep intention of the first pedestrian at the second moment.
In one embodiment, the processing unit is further configured to calculate a lane intention of at least one lane of a road where the vehicle is located according to the state information of the first pedestrian at the first moment and the surface intention of the first pedestrian at the first moment, where the lane intention is a probability that the first pedestrian passes through a first lane, and the at least one lane includes the first lane.
In a third aspect, the present application also provides an apparatus comprising at least one processor for executing instructions stored in a memory to cause a terminal to perform embodiments as possible in the first aspect.
In a fourth aspect, the present application further provides an automobile for performing the embodiments as possible in the first aspect.
In a fifth aspect, the present application also provides a computer readable storage medium having stored thereon a computer program which, when executed in a computer, causes the computer to perform the embodiments as possible in the first aspect.
In a sixth aspect, the present application further provides a computing device, including a memory and a processor, wherein the memory has executable code stored therein, and the processor, when executing the executable code, implements embodiments as possible by the embodiments of the first aspect.
Drawings
The drawings that accompany the detailed description can be briefly described as follows.
Fig. 1 is a schematic structural diagram of a vehicle according to an embodiment of the present application;
FIG. 2 is a view of a vehicle traveling on a roadway;
FIG. 3 is a process flow diagram of a pedestrian crossing intent estimation method provided in an embodiment of the present application;
FIG. 4 is a schematic diagram of modeling of surface intent and deep intent through a dynamic Bayesian network structure provided by an embodiment of the present application;
FIG. 5 is a view of a vehicle and pedestrian on a road;
fig. 6 is a schematic structural diagram of a pedestrian passing intention estimating apparatus according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.
Two concepts, the "superficial intent" and the "deep intent", will be mentioned later in this application. Wherein the surface intention is the probability that the pedestrian is or will pass through the road at the current moment, i.e. the pedestrian's instantaneous or brief-time considered travel intention; deep intent is the probability of a pedestrian crossing the road throughout the life cycle, i.e., the pedestrian's intent to cross over a long term consideration with little environmental impact.
Table 1 comparison of surface intent and deep intent
Since the surface intention represents the passing intention of the pedestrian at the current moment, the surface intention is of great importance to the real-time performance, and therefore in the embodiment of the application, the surface intention is estimated by extracting the detailed information and the interaction information of the pedestrian. However, since the extracted detail information and interaction information are usually relatively large in noise and easily influence the stability of surface intention estimation, the embodiment of the application also introduces deep intention, calculates the deep intention by using the data of the surface intention at the previous moment and the characteristic information of pedestrians, and then improves the stability of the surface intention according to the data of the deep intention, so that the calculated surface intention predicts the intention of a traveler passing through a road more accurately.
Fig. 1 is a frame structure diagram of a vehicle according to an embodiment of the present application. As shown in fig. 1, the vehicle 100 includes an input device 101, a memory 102, a processor 103, and a bus 104. Wherein the input device 101, the memory 102 and the processor 103 in the vehicle 100 may establish a communication connection through the bus 104.
The input device 101 may include an in-vehicle camera, an in-vehicle radar, an in-vehicle navigation, a global positioning system (global positioning system, GPS) sensor, etc. The vehicle-mounted camera is used for shooting the running direction of the vehicle 100 so as to acquire an image comprising information such as lane lines, lane marks, pedestrians and the like of a road; the vehicle-mounted radar may be a laser radar, a millimeter wave radar, or the like, and is configured to transmit a signal to the surroundings of the vehicle 100 and receive a returned signal, so as to obtain distance information between the vehicle 100 and other surrounding vehicles of the vehicle 100, pedestrians, and other obstacles; the vehicle navigation is used for generating a navigation route according to the position of the vehicle 100 and the destination position information input by the driver; the GPS sensor is used to obtain real-time location information of the vehicle 100.
The memory 102 may be a device having a storage function such as a random-access memory (RAM), a Hard Disk Drive (HDD), a solid state disk (solid state drive, SSD), etc., for storing a surface intention, a deep intention, a high-precision map, etc., so as to perform calculation using historically stored data in the process of calculating the surface intention and the deep intention later.
The processor 103 may be an electronic control unit (electronic control unit, ECU) of the vehicle 100, firstly, after receiving each data sent by the input device 101, process the data to obtain information such as status information of pedestrians in the road in front of the vehicle 100 and on both sides of the road, lane lines of the road, lane marks, and the like, and then calculate the surface layer intention of the pedestrian in the road in front of the vehicle 100 and on both sides of the road to obtain the probability of the pedestrian passing through the road according to the status information of the pedestrian (optionally, the surface layer intention of the pedestrian at the last time stored in the memory 102) and the surface layer intention of the pedestrian at the last time stored in the memory 102. When the probability of the pedestrian crossing the road is larger than the set threshold value, warning information is generated, and the driver is reminded of the pedestrian crossing the road on the front road through modes such as display of a display screen or playing of a loudspeaker.
The processor 103 is further configured to re-estimate and update the deep intention of the last time stored in the memory 102 according to the deep intention of the last time stored in the memory 102, the state information of the pedestrian at the current time, and the state information of the pedestrian predicted at the current time, so as to obtain a new deep intention at the current time, so that the reliability of the deep intention increases with the accumulation of the historical observation information.
The processor 103 is further configured to calculate a probability (hereinafter referred to as "lane intention") that the pedestrian passes through each lane according to the received status information of the pedestrian, the information such as the lane line of the road, the lane identification, etc., and the deep intention of the new current time stored in the memory 102, so as to determine which lanes on the current road can run, which lanes are dangerous for the pedestrian to pass through, and instruct the driver how to avoid danger when danger occurs.
The processor 103 of the present application may also be a server, and the vehicle 100 communicates with the server through a communication unit, and then the server replaces the function of the processor 103.
Fig. 2 is a view of a scene in which a vehicle is traveling on a road. The vehicle 100 runs on an inner lane of a road where the vehicle 100 runs in the same direction, no other vehicle runs on the road where the vehicle 100 runs, and a pedestrian is going to travel on the road in front of the left of the road in the running direction of the vehicle 100. The following embodiments of the present application take a scenario in which the vehicle 100 shown in fig. 2 is located as an example to explain the implementation process of the technical solution of the present application.
Fig. 3 is a process flow chart of a pedestrian passing intention estimation method according to an embodiment of the present application. As shown in fig. 3, the processor 103 is embodied as follows:
in step S301, the processor 103 acquires status information of at least one pedestrian around the vehicle 100. In the application, the extracted pedestrian state information mainly comprises three types of characteristics, namely, the behavior characteristics of the pedestrian, the static interaction characteristics of the pedestrian and the dynamic interaction characteristics of the pedestrian.
The behavior characteristics of the pedestrian represent detailed actions of the pedestrian observed by the vehicle 100, including the state of motion, body orientation, body language, etc. of the pedestrian. Illustratively, after the camera of the vehicle 100 acquires the video, the pedestrian in the video is detected by algorithms such as visual perception module region multi-person pose estimation (RMPE) (in the processor 100) to obtain bounding boxes of the pedestrians, then human keypoints are detected in each bounding box, and the keypoints in each bounding box are connected to form the pose of each pedestrian. Meanwhile, the processor 103 calculates the distance of each pedestrian from the vehicle 100 according to the algorithms of monocular ranging, binocular ranging, and the like. The processor 103 calculates the direction of the pedestrian relative to the vehicle 100 according to the key points and the gesture of the pedestrian, and further calculates the direction of the pedestrian relative to the road as the direction feature of the pedestrian; the processor 103 deduces the motion characteristics of the pedestrians by utilizing the key points and the gestures of the pedestrians, and takes the motion or static information of the pedestrians as the motion characteristics of the pedestrians; the processor 103 analyzes the key points of the hands of the pedestrian, and obtains the body language of the pedestrian, such as the actions of waving hands, pointing and the like, as the body language characteristics of the pedestrian. The three characteristics reflect the detailed information of the pedestrians, have strong real-time performance and are used for judging the surface layer intention of the pedestrians.
The static interaction characteristics of the pedestrian represent information related to the pedestrian and the surrounding road environment. The processor 103 of the vehicle 100 may obtain the distance between the pedestrian and the vehicle 100 by means of receiving and transmitting millimeter wave signals by radar (millimeter wave radar, for example), images captured by a camera, and the like, then determine the position of the pedestrian by combining map information stored in the memory 102, determine information such as the distance between the pedestrian and the road boundary, the distance between the pedestrian and the lane where the vehicle 100 is located, and the distance between the pedestrian and each lane line in the road, and then use these information as static interaction characteristics of the pedestrian.
The dynamic interaction characteristics of the pedestrian represent the pedestrian's interaction information with surrounding dynamic objects, such as with the vehicle 100. Illustratively, the processor 102 of the vehicle 100 obtains information about the distance, speed, relative position, etc. of surrounding pedestrians with respect to the vehicle 100, and other information about the distance, speed, relative position, etc. of the vehicle with respect to the vehicle 100 via a camera, radar, etc. The motion profile of pedestrians and other vehicles over a period of time is then predicted. Finally, the processor 103 calculates information such as the minimum distance between each pedestrian and each vehicle, the time of collision, and the like according to the motion trail of the pedestrians and other vehicles, and then uses the information as the dynamic interaction characteristics of the pedestrians.
In step S304, the processor 103 calculates the surface intention of the first pedestrian to travel through the road based on the state information of the first pedestrian at the present time and the deep intention of the first pedestrian at the previous time. The first pedestrian is the pedestrian in front of the road in the driving direction of the vehicle 100 in fig. 2, and the current moment corresponds to the second moment, and the previous moment corresponds to the first moment.
In the automatic driving scenario, the vehicle 100 may obtain the motion information of other surrounding vehicles and obstacles through various input devices 101, and calculate the interaction information with the pedestrian, as the basis for determining the pedestrian's passing intention. However, the information monitored by the input device 101 is sometimes not necessarily completely correct, and errors or errors may occur, for example, due to the fact that the pedestrian target is small and the movement speed is slow, the input device 101 sometimes does not necessarily detect pedestrians, detects errors such as the speed of the pedestrians is unchanged, and the characteristics of the pedestrians are greatly affected. By way of example, the present application combines three types of features, namely, a behavior feature of a pedestrian, a static interaction feature of a pedestrian, and a dynamic interaction feature of a pedestrian, and calculates likelihood probability of a pedestrian feature Z by the formula (1), namely:
wherein M is t Representing the pedestrian's travel intention at time t, DTC t Representing static interaction characteristics of pedestrians at t moment, D min t Representing dynamic interaction characteristics of pedestrians at t moment, OR t MO representing pedestrian orientation at time t t Representing the motion characteristics of pedestrians at time t, BL t The body language of the pedestrian at time t is represented. The likelihood probability of each feature is estimated through a large number of data samples, and probability parameters are calculated.
In the process of calculating the surface intention of a pedestrian passing through a road at the current moment, a dynamic Bayesian network structure is utilized to model the calculation of the surface intention of the pedestrian and the deep intention of the pedestrian, then the pedestrian characteristic Z, the observed pedestrian state information Y and the predicted pedestrian state information X are respectively taken as input information, and then a model shown in figure 4 is constructed according to the mutual influence between the deep intention and the surface intention according to the time sequence. As shown in FIG. 4, the surface intent M at time t is calculated t In the process, the last oneSkin intention M of time of day t-1 Pedestrian feature Z at time t t And deep intention D at time t t Related to the following.
Illustratively, taking the pedestrian status information as the position and speed of the pedestrian as an example, the processor 103 calculates the surface intention M at time t t The method is calculated by a formula (2), and concretely comprises the following steps:
wherein P (M t M (M) t-1 ) The transition probability of the surface intention is represented, represents the influence of the historical surface intention on the current surface intention, and plays a role in smoothing the intention; p (M) t Z is one t-1 ) The likelihood probability of the pedestrian characteristic is represented, and the likelihood probability of the pedestrian characteristic represents the observed pedestrian behavior characteristic and the interaction characteristic so as to infer real-time pedestrian passing intention; p (D) t ，D t-1 ，X t ，Y t ) Representing the deep intent, which represents the impact of the pedestrian's deep intent on the superficial intent.
If the detected pedestrian is the first detection when there is no historical deep intention of the pedestrian stored in the memory 102, an initial value of the deep intention, such as 0.5, is stored in the memory 102. When the processor 103 calculates the surface intention, the initial value is selected to calculate the surface intention, the calculated surface intention being determined mainly by the pedestrian characteristics at the present time.
After obtaining the surface intention, the processor 103 judges whether the calculated probability of the surface intention exceeds a set threshold, if the calculated probability of the surface intention is larger than the set threshold, the processor 103 can remind a driver in a mode of playing voice through a loudspeaker, displaying prompt information through a display screen and the like, and can also directly control the vehicle 100 to slow down and avoid the behaviors of walking pedestrians and the like, so that the vehicle 100 can safely run on the current running road.
In this embodiment of the present application, information such as pedestrians, lane lines of roads, lane marks, surrounding other vehicles on the roads where the vehicle 100 is traveling is continuously acquired through each type of input device 101 on the vehicle 100, and then after information such as behavior features, static interaction features, dynamic interaction features and the like of the pedestrians at the current moment are analyzed, the surface layer intention at the last moment and the deep layer intention at the last moment stored in the memory 102 are combined, so that a surface layer intention estimation result with high precision, real-time performance and accuracy can be obtained.
The accuracy means that the multi-aspect factors are utilized to predict the pedestrians, the deep intention of the pedestrians is excavated, and the influence of noise in the perception of the pedestrians is reduced. Timeliness refers to that elements with real-time performance such as detail information and interaction information are used as surface layer intention judgment basis, elements with hysteresis such as tracking information are used for adjusting deep intention, and timeliness is improved on the premise of guaranteeing prediction accuracy.
In the embodiment of the present application, before implementing the calculation of the surface layer intention at the current time in step S304, the processor 103 further implements the following procedure:
in step S302, the processor 103 determines the pedestrian status information predicted at the current time according to the pedestrian status information predicted at the previous time and the surface layer intention of the pedestrian at the previous time.
Specifically, after the processor 103 obtains the speed and the position of the pedestrian predicted at the previous moment, then determines whether the pedestrian passes through the road according to the surface intention at the previous moment, and then the processor 103 calculates the speed and the position of the pedestrian predicted at the current moment according to the speed and the position of the pedestrian predicted at the previous moment and the time difference between the previous moment and the current moment, so as to obtain the pedestrian state information at the current moment.
In step S303, the processor 103 calculates the deep intention of the pedestrian at the present moment based on the predicted pedestrian state information at the present moment, the observed pedestrian state information at the present moment, and the deep intention of the pedestrian at the previous moment.
Herein, the deep intention is whether the pedestrian actually has a walk intention, which is a long-term stable intention, in the life cycle observed by the vehicle 100. In practice, the deep intent of a pedestrian is determined and does not change over time, while in the intent estimation process, the node is a gradual, gradually converging process in the estimation process due to the non-observability of the deep intent and the reliability impact of the reference information, the reliability of which increases as the historical observation information accumulates.
Specifically, as the deep intention has higher requirements on stability and accuracy and lower requirements on real-time performance, the method and the device mainly adopt the predicted state information of the pedestrian at the previous moment, the actual state information of the pedestrian at the current moment, the surface intention at the current moment and the deep intention of the pedestrian at the previous moment to estimate and update the deep intention at the current moment.
Taking the pedestrian status information as the position and speed of the pedestrian as an example, as shown in fig. 4, the processor 103 predicts the motion trail of the pedestrian by using a uniform velocity model by combining the pedestrian position and speed information predicted at the previous time with the surface layer intention of the pedestrian at the previous time t Inputting the pedestrian position and speed information into a uniform speed model, calculating the pedestrian position and speed information predicted at the current moment, and then calculating the correction amount of the deep intention through a formula (3) according to the pedestrian position and speed information observed at the current moment, namely:
the processor 103 corrects the deep intention of the pedestrian obtained at the previous time according to the correction amount of the deep intention obtained, and obtains the deep intention at the current time.
The formula (3) may take the lane direction of the road in the direction in which the vehicle 100 travels as a reference line, and the actual position information of the pedestrian at the current time and the predicted position information of the pedestrian at the current time may be respectively in two directions, i.e., the transverse direction and the longitudinal direction, where the calculation formula is:
where x represents the predicted position of the pedestrian at the current time and y represents the time whenActual position of pedestrian at previous moment, v x Representing the predicted speed, v, of the pedestrian at the current moment y The actual speed of the pedestrian at the current time is represented by L, which is perpendicular to the lane direction, and S, which is parallel to the lane direction. The above formula (4) shows the effect of the difference between the pedestrian's movement in the lane direction and the vertical lane direction and the predicted movement on the deep intention. For example, when the movement distance of the pedestrian along the vertical lane direction is greater than the movement distance predicted by the historical intent, the probability that the deep intention is to travel is greater than the probability that the pedestrian is not to travel, and then the historical deep intention is combined, the deep intention can be corrected, and the deep intention at the current moment can be obtained.
In addition, in the embodiment of the present application, after calculating the surface intention of the pedestrian at the current moment, if it is determined that there is a pedestrian passing through the road, it is required to determine how the vehicle 100 avoids the pedestrian, and the specific implementation process is as follows:
in step S305, the processor 103 calculates lane intentions of the respective lanes of the road on which the vehicle 100 is located, based on the state information of the pedestrian at the current time and the surface intention at the current time.
Specifically, when the processor 103 determines that the probability of the surface intention is greater than the set threshold according to the surface intention at the current time, it indicates that a pedestrian is about to travel through the road, and continuously calculates the probability of collision between the vehicle 100 and the pedestrian in the own lane and the probability of collision between the vehicle 100 and the pedestrian in other lanes according to the information such as the pedestrian position, the pedestrian speed, the distance between the pedestrian and each lane, the distance between the pedestrian and the vehicle 100 in the pedestrian state information, and the like, thereby calculating the lane intention of each lane of the road where the vehicle 100 is located.
For example, as shown in fig. 5, the processor 103 obtains that the speed of the pedestrian is v1, the speed v2 of the vehicle 100, the vertical distance between the pedestrian and the vehicle 100 is L1, the lane width is L2, the boundary distance between the pedestrian and the road where the vehicle 100 is located is L3, and then determines whether the time t1=l3/v 1 when the pedestrian arrives at the road boundary where the vehicle 100 is located is greater than t2=l1/v 2, if so, and if the lane intention of the lane where the vehicle 100 is currently located calculated by combining other factors such as the movement, the orientation, the deep intention, and the like of the pedestrian is less than the set threshold, the vehicle 100 is safe to travel on the lane where the current is located; if the lane intention of the lane in which the vehicle 100 is currently located, which is calculated by combining other factors such as pedestrian movement, direction, deep intention, and the like, is smaller than the set threshold, the vehicle 100 is not safe to travel on the lane in which the vehicle 100 is currently located. Then judging whether the time t3= (l3+l2)/v 1 of the pedestrian reaching the boundary of the lane adjacent to the lane where the vehicle 100 is located is greater than t2 (for convenience of calculation, neglecting the time of the vehicle 100 turning to the adjacent lane from the current lane), if so, and if the lane intention of the lane where the vehicle 100 is currently located calculated by combining other factors such as the pedestrian movement, the direction, the deep intention and the like is less than a set threshold value, the vehicle 100 turns to the adjacent lane to run safely; if the lane intention of the lane in which the vehicle 100 is currently located, which is calculated by combining other factors such as pedestrian movement, direction, deep intention, etc., is smaller than the set threshold, the vehicle 100 is not safe to drive on the adjacent lane, and the vehicle 100 can be controlled to slow down or stop by braking.
According to the method and the system, the road structure of each lane and the related vehicles are utilized to extract the static interaction characteristics and the dynamic interaction characteristics of the lane level, the lane intention of the pedestrian is inferred by combining the behavior characteristics of the target pedestrian, the vehicle 100 can output the passing intention of the pedestrian relative to each lane, and the automatic driving vehicle can make a response in advance.
Fig. 6 is a schematic structural diagram of a pedestrian passing intention estimating apparatus according to an embodiment of the present application. As shown in fig. 6, the apparatus 600 includes an acquisition unit 601 and a processing unit 602.
The acquiring unit 601 is configured to acquire status information of at least one pedestrian around a vehicle, where the at least one pedestrian includes a first pedestrian;
the processing unit 602 is configured to calculate a surface intention of a first pedestrian at a first moment according to state information of the first pedestrian at the first moment and a deep intention of the first pedestrian at a second moment, where the second moment is before the first moment, the deep intention is a probability that the first pedestrian is traversing a road in a whole life cycle, and the surface intention is a probability that the first pedestrian is traversing the road at a current moment or is about to traverse the road;
the processing unit 602 is further configured to determine whether the first pedestrian passes through the road at the first moment according to the surface intention of the first pedestrian at the first moment.
In one embodiment, the processing unit 602 is specifically configured to calculate likelihood probability of a pedestrian feature of the first pedestrian at the first moment according to the state information of the first pedestrian at the first moment; and calculating the surface layer intention of the first pedestrian at the first moment according to the likelihood probability of the pedestrian characteristic of the first pedestrian at the first moment and the deep intention of the first pedestrian at the second moment.
In one embodiment, the processing unit 602 is further configured to control the speaker to play the early warning signal and/or display the early warning information on the display screen when the surface intention of the first pedestrian at the first moment is greater than the set threshold.
In one embodiment, the processing unit 602 is further configured to calculate the state information of the predicted first pedestrian at the first moment according to the state information of the first pedestrian at the second moment and the surface intention of the first pedestrian at the second moment; and calculating the deep intention of the first pedestrian at the first moment according to the predicted state information of the first pedestrian at the first moment, the state information of the first pedestrian at the first moment and the deep intention of the first pedestrian at the second moment.
In one embodiment, the processing unit 602 is further configured to calculate a lane intention of at least one lane of a road where the vehicle is located, where the lane intention is a probability that the first pedestrian passes through a first lane, according to the state information of the first pedestrian at the first moment and a surface intention of the first pedestrian at the first moment, and the at least one lane includes the first lane.
The present invention provides a computer readable storage medium having stored thereon a computer program which, when executed in a computer, causes the computer to perform any of the methods described above.
The invention provides a computing device comprising a memory and a processor, the memory having executable code stored therein, the processor implementing any of the methods described above when executing the executable code.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the embodiments of the present application.
Furthermore, various aspects or features of embodiments of the present application may be implemented as a method, apparatus, or article of manufacture using standard programming and/or engineering techniques. The term "article of manufacture" as used herein encompasses a computer program accessible from any computer-readable device, carrier, or media. For example, computer-readable media can include, but are not limited to, magnetic storage devices (e.g., hard disk, floppy disk, or magnetic strips, etc.), optical disks (e.g., compact disk, CD, digital versatile disk, digital versatile disc, DVD, etc.), smart cards, and flash memory devices (e.g., erasable programmable read-only memory, EPROM), cards, sticks, or key drives, etc. Additionally, various storage media described herein can represent one or more devices and/or other machine-readable media for storing information. The term "machine-readable medium" can include, without being limited to, wireless channels and various other media capable of storing, containing, and/or carrying instruction(s) and/or data.
In the above-described embodiments, the pedestrian crossing intention estimation device 600 in fig. 6 may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, produces a flow or function in accordance with embodiments of the present application, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another, for example, by wired (e.g., coaxial cable, optical fiber, digital Subscriber Line (DSL)), or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid State Disk (SSD)), etc.
It should be understood that, in various embodiments of the present application, the sequence numbers of the foregoing processes do not mean the order of execution, and the order of execution of the processes should be determined by the functions and internal logic of the processes, and should not constitute any limitation on the implementation process of the embodiments of the present application.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the embodiments of the present application may be essentially or, what contributes to the prior art, or part of the technical solution may be embodied in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, or an access network device, etc.) to perform all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The foregoing is merely a specific implementation of the embodiments of the present application, but the protection scope of the embodiments of the present application is not limited thereto, and any person skilled in the art may easily think about changes or substitutions within the technical scope of the embodiments of the present application, and all changes and substitutions are included in the protection scope of the embodiments of the present application.
Claims (14)
1. A pedestrian crossing intention estimation method, characterized by comprising:
acquiring state information of at least one pedestrian around the vehicle, wherein the at least one pedestrian comprises a first pedestrian;
calculating the surface layer intention of a first pedestrian at a first moment according to the state information of the first pedestrian at the first moment and the deep intention of the first pedestrian at a second moment, wherein the deep intention is the probability that the first pedestrian passes through a road in the whole life cycle observed by the vehicle before the first moment, and the surface layer intention is the probability that the first pedestrian is or is about to pass through the road at the current moment;
and determining whether the first pedestrian passes through the road at the first moment according to the surface layer intention of the first pedestrian at the first moment.
2. The method according to claim 1, characterized by, before the calculating the surface intent of the first pedestrian at the first moment based on the state information of the first pedestrian at the first moment and the deep intent of the first pedestrian at the second moment, comprising:
according to the state information of the first pedestrian at the first moment, calculating likelihood probability of pedestrian characteristics of the first pedestrian at the first moment;
the calculating the surface layer intention of the first pedestrian at the first moment according to the state information of the first pedestrian at the first moment and the deep intention of the first pedestrian at the second moment comprises the following steps:
and calculating the surface layer intention of the first pedestrian at the first moment according to the likelihood probability of the pedestrian characteristic of the first pedestrian at the first moment and the deep intention of the first pedestrian at the second moment.
3. The method according to claim 1, wherein the method further comprises:
when the surface layer intention of the first pedestrian at the first moment is larger than a set threshold value, controlling a loudspeaker to play an early warning signal and/or displaying early warning information on a display screen.
4. A method according to any one of claims 1-3, characterized in that before said calculating the surface intent of the first pedestrian at the first moment based on the status information of the first pedestrian at the first moment and the deep intent of the first pedestrian at the second moment, the method comprises:
calculating the state information of the predicted first pedestrian at the first moment according to the state information of the first pedestrian at the second moment and the surface layer intention of the first pedestrian at the second moment;
and calculating the deep intention of the first pedestrian at the first moment according to the predicted state information of the first pedestrian at the first moment, the state information of the first pedestrian at the first moment and the deep intention of the first pedestrian at the second moment.
5. A method according to any one of claims 1-3, characterized in that the method further comprises:
and calculating the lane intention of at least one lane of a road where the vehicle is located according to the state information of the first pedestrian at the first moment and the surface layer intention of the first pedestrian at the first moment, wherein the lane intention is the probability that the first pedestrian passes through the first lane, and the at least one lane comprises the first lane.
6. A pedestrian crossing intention estimation device characterized by comprising:
an acquisition unit configured to acquire status information of at least one pedestrian around a vehicle, the at least one pedestrian including a first pedestrian;
the processing unit is used for calculating the surface layer intention of the first pedestrian at the first moment according to the state information of the first pedestrian at the first moment and the deep layer intention of the first pedestrian at the second moment, wherein the deep layer intention is the probability that the first pedestrian passes through a road in the whole life cycle observed by the vehicle before the first moment, and the surface layer intention is the probability that the first pedestrian is passing through the road at the current moment or is about to pass through the road;
the processing unit is further configured to determine, according to the surface intention of the first pedestrian at the first moment, whether the first pedestrian passes through the road at the first moment.
7. The apparatus according to claim 6, wherein the processing unit is specifically configured to calculate likelihood probability of pedestrian characteristics of the first pedestrian at the first moment according to the status information of the first pedestrian at the first moment;
and calculating the surface layer intention of the first pedestrian at the first moment according to the likelihood probability of the pedestrian characteristic of the first pedestrian at the first moment and the deep intention of the first pedestrian at the second moment.
8. The apparatus of claim 6, wherein the processing unit is further configured to control the speaker to play the pre-warning signal and/or display the pre-warning information on the display screen when the first pedestrian's surface intention at the first moment is greater than a set threshold.
9. The apparatus according to any one of claims 6-8, wherein the processing unit is further configured to calculate the predicted first pedestrian status information at the first time based on the first pedestrian status information at the second time and the first pedestrian skin intention at the second time;
and calculating the deep intention of the first pedestrian at the first moment according to the predicted state information of the first pedestrian at the first moment, the state information of the first pedestrian at the first moment and the deep intention of the first pedestrian at the second moment.
10. The apparatus according to any one of claims 6-8, wherein the processing unit is further configured to calculate a lane intention of at least one lane of a road on which a vehicle is located, the lane intention being a probability that the first pedestrian passes through a first lane, the at least one lane including the first lane, based on the state information of the first pedestrian at the first time and a surface intention of the first pedestrian at the first time.
11. A terminal device comprising at least one processor for executing instructions stored in a memory to cause the terminal device to perform the method of any of claims 1-5.
12. An automobile for performing the method of any one of claims 1-5.
13. A computer readable storage medium having stored thereon a computer program which, when executed in a computer, causes the computer to perform the method of any of claims 1-5.
14. A computing device comprising a memory and a processor, wherein the memory has executable code stored therein, which when executed by the processor, implements the method of any of claims 1-5.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011176754.4A CN114426030B (en) | 2020-10-29 | 2020-10-29 | Pedestrian passing intention estimation method, device, equipment and automobile |
| PCT/CN2021/095259 WO2022088658A1 (en) | 2020-10-29 | 2021-05-21 | Pedestrian crossing intention estimation method and apparatus, device, and vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011176754.4A CN114426030B (en) | 2020-10-29 | 2020-10-29 | Pedestrian passing intention estimation method, device, equipment and automobile |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114426030A CN114426030A (en) | 2022-05-03 |
| CN114426030B true CN114426030B (en) | 2024-04-09 |
Family
ID=81309344
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011176754.4A Active CN114426030B (en) | 2020-10-29 | 2020-10-29 | Pedestrian passing intention estimation method, device, equipment and automobile |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN114426030B (en) |
| WO (1) | WO2022088658A1 (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117115759B (en) * | 2023-04-12 | 2024-04-09 | 盐城工学院 | Road side traffic target detection system and method based on category guidance |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102014205953A1 (en) * | 2014-03-31 | 2015-10-01 | Robert Bosch Gmbh | Method for analyzing a traffic environment situation of a vehicle |
| CN107221175A (en) * | 2017-05-31 | 2017-09-29 | 深圳市鸿逸达科技有限公司 | A kind of pedestrian is intended to detection method and system |
| CN107423679A (en) * | 2017-05-31 | 2017-12-01 | 深圳市鸿逸达科技有限公司 | A kind of pedestrian is intended to detection method and system |
| DE102018104270A1 (en) * | 2018-02-26 | 2019-08-29 | Connaught Electronics Ltd. | Method for predicting the behavior of at least one pedestrian |
| CN111008583A (en) * | 2019-11-28 | 2020-04-14 | 清华大学 | Pedestrian and rider posture estimation method assisted by limb characteristics |
| CN111497840A (en) * | 2020-04-27 | 2020-08-07 | 清华大学 | Calculation method and safety evaluation system for vehicle-pedestrian collision risk domain |
| CN111797751A (en) * | 2020-06-29 | 2020-10-20 | 中国第一汽车股份有限公司 | Pedestrian trajectory prediction method, device, equipment and medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3706034A1 (en) * | 2019-03-06 | 2020-09-09 | Robert Bosch GmbH | Movement prediction of pedestrians useful for autonomous driving |
-
2020
- 2020-10-29 CN CN202011176754.4A patent/CN114426030B/en active Active
-
2021
- 2021-05-21 WO PCT/CN2021/095259 patent/WO2022088658A1/en active Application Filing
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102014205953A1 (en) * | 2014-03-31 | 2015-10-01 | Robert Bosch Gmbh | Method for analyzing a traffic environment situation of a vehicle |
| CN107221175A (en) * | 2017-05-31 | 2017-09-29 | 深圳市鸿逸达科技有限公司 | A kind of pedestrian is intended to detection method and system |
| CN107423679A (en) * | 2017-05-31 | 2017-12-01 | 深圳市鸿逸达科技有限公司 | A kind of pedestrian is intended to detection method and system |
| DE102018104270A1 (en) * | 2018-02-26 | 2019-08-29 | Connaught Electronics Ltd. | Method for predicting the behavior of at least one pedestrian |
| CN111008583A (en) * | 2019-11-28 | 2020-04-14 | 清华大学 | Pedestrian and rider posture estimation method assisted by limb characteristics |
| CN111497840A (en) * | 2020-04-27 | 2020-08-07 | 清华大学 | Calculation method and safety evaluation system for vehicle-pedestrian collision risk domain |
| CN111797751A (en) * | 2020-06-29 | 2020-10-20 | 中国第一汽车股份有限公司 | Pedestrian trajectory prediction method, device, equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2022088658A1 (en) | 2022-05-05 |
| CN114426030A (en) | 2022-05-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11897518B2 (en) | Systems and methods for navigating with sensing uncertainty | |
| US11561551B2 (en) | Prioritized constraints for a navigational system | |
| US11815904B2 (en) | Trajectory selection for an autonomous vehicle | |
| CN108688660B (en) | Operating range determining device | |
| US11625038B2 (en) | Autonomous driving device | |
| WO2018179539A1 (en) | Method for controlling host vehicle and control system of host vehicle | |
| CN103781685A (en) | Autonomous driving control system for vehicle | |
| RU2757234C2 (en) | Method and system for calculating data for controlling the operation of a self-driving car | |
| JP2018063476A (en) | Apparatus, method and computer program for driving support | |
| CN111505690A (en) | Method and device for detecting emergency vehicle in real time and planning driving path | |
| CN114426030B (en) | Pedestrian passing intention estimation method, device, equipment and automobile | |
| CN111959482A (en) | Autonomous driving device and method | |
| CN110497906A (en) | Control method for vehicle, device, equipment and medium | |
| US20230054626A1 (en) | Persisting Predicted Objects for Robustness to Perception Issues in Autonomous Driving | |
| US20230399026A1 (en) | State Identification For Road Actors With Uncertain Measurements Based On Compliant Priors | |
| CN116001776A (en) | Automatic parking method and vehicle control device | |
| CN115635980A (en) | Vehicle passing method, device, equipment 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |