CN115246416A - Trajectory prediction method, apparatus, device and computer readable storage medium - Google Patents
Trajectory prediction method, apparatus, device and computer readable storage medium Download PDFInfo
- Publication number
- CN115246416A CN115246416A CN202110522250.1A CN202110522250A CN115246416A CN 115246416 A CN115246416 A CN 115246416A CN 202110522250 A CN202110522250 A CN 202110522250A CN 115246416 A CN115246416 A CN 115246416A
- Authority
- CN
- China
- Prior art keywords
- target
- vehicle
- obstacle
- track
- target obstacle
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 230000003993 interaction Effects 0.000 claims description 34
- 230000004888 barrier function Effects 0.000 claims description 30
- 238000012795 verification Methods 0.000 claims description 14
- 230000001133 acceleration Effects 0.000 claims description 12
- 230000015654 memory Effects 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 9
- 230000003068 static effect Effects 0.000 claims description 4
- 238000004422 calculation algorithm Methods 0.000 description 15
- 230000033001 locomotion Effects 0.000 description 15
- 230000002452 interceptive effect Effects 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000000670 limiting effect Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000011144 upstream manufacturing Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000036961 partial effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W60/00—Drive control systems specially adapted for autonomous road vehicles
- B60W60/001—Planning or execution of driving tasks
- B60W60/0011—Planning or execution of driving tasks involving control alternatives for a single driving scenario, e.g. planning several paths to avoid obstacles
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
- B60W30/095—Predicting travel path or likelihood of collision
-
- 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
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Human Computer Interaction (AREA)
- Traffic Control Systems (AREA)
Abstract
The application provides a track prediction method, which comprises the following steps: acquiring vehicle surrounding information of a target vehicle at the current moment; classifying the target obstacles around the target vehicle according to at least one preset classification mode according to information about the obstacles in the vehicle surrounding information; determining a trajectory prediction strategy of the target obstacle based on the classification result of the target obstacle; and predicting at least one future running track of the target obstacle according to a track prediction strategy, and predicting the possibility that each future running track is selected by the target obstacle. The method and the device comprehensively describe the possible track space of the target obstacle and improve the accuracy of the obstacle track prediction result. The application also provides a track prediction device, equipment and a computer readable storage medium.
Description
Technical Field
The present application relates to the field of control technologies, and in particular, to a trajectory prediction method, apparatus, device, and computer-readable storage medium.
Background
With the gradual maturity of the automatic driving technology, the applications of logistics distribution, shared trips, environmental sanitation operation and the like are safer and more efficient. The automatic driving automobile needs to sense surrounding environment information in real time, and timely makes an interactive decision according to the motion states of obstacles such as pedestrians, other vehicles and the like to ensure driving safety, so that the automatic driving automobile needs to utilize various information to accurately predict the future motion trail of the obstacles and make reasonable interactive actions such as speed reduction and way giving, parking waiting and the like.
In the automatic driving system, the prediction interactive system receives various information such as barrier states, map semantics and structures, traffic rules and the like provided by an upstream module, and realizes prediction of future movement tracks of other barriers around the automatic driving vehicle and selection of an interactive mode of the automatic driving vehicle and the barriers by using modes such as a mathematical model, rules and the like, so that the automatic driving vehicle is helped to plan reasonable driving tracks in a complex operating environment, and safety avoidance is realized when necessary.
In the prior art, obstacle trajectory prediction and interaction decisions are typically done using mathematical models or rules. Recording historical information of obstacles around the automatic driving vehicle, including position coordinates, speed, time stamps and the like, inputting the information into a model to perform regression analysis or solving according to rules so as to obtain a future movement track of the obstacles, and finishing interaction between the automatic driving vehicle and the obstacles according to the information of the position, the speed, the future track and the like of the obstacles. However, when the obstacle trajectory is predicted by adopting the prior art scheme, the predicted trajectory is mostly in a single number, and the structural hierarchy of the prediction method is simpler, so that the accuracy of the trajectory prediction result is lower.
Disclosure of Invention
In view of this, the present application provides a trajectory prediction method, apparatus, device and computer readable storage medium, which can improve the accuracy of a trajectory prediction result when predicting a moving trajectory of an obstacle.
Specifically, the method is realized through the following technical scheme:
a trajectory prediction method, comprising:
acquiring vehicle surrounding information of a target vehicle at the current moment;
classifying the target obstacles around the target vehicle according to at least one preset classification mode according to information about obstacles in the vehicle surrounding information;
determining a trajectory prediction strategy of the target obstacle based on the classification result of the target obstacle;
and predicting at least one future running track of the target obstacle according to the track prediction strategy, and predicting the possibility that each future running track is selected by the target obstacle.
A trajectory prediction device comprising:
an information acquisition unit configured to acquire vehicle surrounding information of a target vehicle at a current time;
the obstacle classification unit is used for classifying the target obstacles around the target vehicle according to at least one preset classification mode according to information about the obstacles in the vehicle surrounding information;
a strategy determination unit for determining a trajectory prediction strategy of the target obstacle based on a classification result of the target obstacle;
and the track prediction unit is used for predicting at least one future running track of the target obstacle according to the track prediction strategy and predicting the possibility that each future running track is selected by the target obstacle.
An electronic device, comprising: a processor, a memory;
the memory for storing a computer program;
the processor is used for executing the trajectory prediction method by calling the computer program.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the trajectory prediction method described above.
In the technical scheme provided by the application, one or more future running tracks of the target barrier can be predicted for each target barrier around the target vehicle, the possibility that each future running track is selected by the target barrier is predicted, uncertainty of the target barrier in actual motion can be well expressed by the predicted tracks, the possible track space of the target barrier is comprehensively described, and the accuracy of the track prediction result of the barrier is improved. Moreover, the target vehicle can obtain the estimation result of the future motion track of the target obstacle in advance by more perfect prediction of the track space, and the target vehicle and the target obstacle can be helped to realize more reasonable interaction, so that the safe operation of the target vehicle is realized.
Drawings
FIG. 1 is a schematic flow chart of a trajectory prediction method shown in the present application;
FIG. 2 is a schematic diagram of a trajectory prediction device according to the present application;
fig. 3 is a schematic structural diagram of an electronic device shown in the present application.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the application, as detailed in the appended claims.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It is to be understood that although the terms first, second, third, etc. may be used herein to describe various information, such information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present application. The word "if," as used herein, may be interpreted as "at … …" or "at … …" or "in response to a determination," depending on the context.
It should be noted that, in some existing trajectory prediction methods, when a trajectory of an obstacle is predicted, the predicted trajectory is mostly a single number, and in practice, for different types of obstacles, there are many different movement modes, for example, a pedestrian can go straight along a road or cross the road, and a vehicle can go straight through an intersection or turn into another direction, so that the future movement trajectory of the obstacle often has strong uncertainty, but the existing technical scheme only adopts a single trajectory to describe the future movement mode of the obstacle, and cannot accurately estimate the spatial position of the obstacle, which causes difficulty in interaction between an automatically-driven vehicle and the obstacle. In addition, the prediction method in the prior art is simple in structure hierarchy, cannot perform hierarchical prediction according to the environment where the autonomous vehicle and the obstacle are located, the type of the obstacle, the traffic condition and the like, and is low in refinement degree, so that low trajectory prediction accuracy is caused.
To this end, an embodiment of the present application provides a trajectory prediction method, and referring to fig. 1, the method is a schematic flow chart of the trajectory prediction method provided in the embodiment of the present application, and the method includes the following steps S101 to S104:
s101: vehicle surrounding information of the target vehicle at the current time is acquired.
Any automatic driving automobile can be defined as a target vehicle, the target vehicle can continuously acquire the information around the vehicle within a certain frequency range by utilizing the sensing module of the target vehicle in the actual running process, and then the prediction interaction system of the target vehicle receives the information around the vehicle provided by the upstream sensing module.
In the embodiment of the present application, the vehicle surrounding information may include obstacle state information around the target vehicle, and may further include, but is not limited to, map environment information around the target vehicle, traffic regulation restriction information, and other information, and the like.
Where, regarding the obstacle state information, it relates to the state information of one or more obstacles around the target vehicle, where each obstacle is defined as a target obstacle, and in order to acquire the state information of the target obstacle, the relevant calculations involved include, but are not limited to, coordinate conversion of position coordinates, velocity, acceleration, calculation of attitude angle, and the like of the target obstacle. The obstacle state information may be stored in order after completion of the calculation, and may be used as a history feature of the obstacle.
The map environment information can be obtained by caching the lane information, and related calculation includes but is not limited to lane cache construction, lane center curve fitting and other data preprocessing. For map-related information, only one copy of the cached data may be maintained to reduce duplicate computations.
The traffic regulation restriction information refers to traffic regulation restriction on the lanes around the target vehicle, and includes, but is not limited to, vehicle speed restriction, straight-ahead restriction, turning restriction, and the like.
S102: and classifying the target obstacles around the target vehicle according to at least one preset classification mode according to the information about the obstacles in the vehicle surrounding information.
In this embodiment, for each target obstacle around the target vehicle, the prediction interaction system of the target vehicle may extract state information of the target obstacle from the vehicle surrounding information, and perform type determination on the target obstacle according to the state information of the target obstacle. The classification manner of the target obstacle includes, but is not limited to, an obstacle category (such as vehicle, pedestrian, bicycle, etc.), an obstacle speed (such as high speed, low speed, etc.), and an obstacle operation intention (such as lane change, turning around, parking, etc.). When the target obstacle is classified according to one or more preset classification modes, one or more classification results of the target obstacle can be obtained correspondingly.
S103: and determining a track prediction strategy of the target obstacle based on the classification result of the target obstacle.
In the embodiment of the application, a trajectory prediction algorithm (that is, a trajectory prediction strategy) suitable for the target obstacle may be selected according to the classification result of the target obstacle, the rule according to which the selection is performed may be set through a configuration file, and a correspondence between the classification result of the obstacle and the trajectory prediction algorithm needs to be marked in the configuration file, for example, the obstacle classification result a corresponds to the trajectory prediction algorithm a, the obstacle classification result B corresponds to the trajectory prediction algorithm B, and the like. When the configuration file is read, the corresponding track prediction algorithm can be selected according to the classification result of the target obstacle and the rule in the configuration file.
In addition, the track prediction strategy of the target obstacle can be determined based on the combined classification result of the target obstacle and the surrounding environment of the vehicle. Specifically, in an implementation manner of the embodiment of the present application, the step S103 may include the following steps A1-A2:
step A1: and classifying the vehicle surrounding environment of the target vehicle according to at least one preset classification mode according to the information about the environment where the vehicle is located in the vehicle surrounding information.
In this step, the prediction interactive system of the target vehicle may extract the position coordinates, the map environment information, and the like of the target vehicle from the vehicle surrounding information, so as to perform type determination on the vehicle surrounding environment of the target vehicle according to the position coordinates, the map environment information, and the like of the target vehicle. The classification manner of the vehicle surroundings includes, but is not limited to, a region type (e.g., city, country, etc.), a traffic condition (e.g., open road, traffic jam, etc.), and a road scene (e.g., highway, intersection, parking lot, etc.). When the vehicle surroundings of the target vehicle are classified according to one or more preset classification manners, one or more classification results of the vehicle surroundings can be obtained correspondingly.
Step A2: and determining a track prediction strategy of the target obstacle according to the classification result of the target obstacle and the surrounding environment of the vehicle.
In this step, different models, different rules, and the like may be preset for the obstacle trajectory prediction, and based on this, when the classification result of the target obstacle and the vehicle surrounding environment is determined, the corresponding models, rules, and the like are called to form a trajectory prediction strategy for predicting the operation trajectory of the target obstacle in a hierarchical manner.
In an implementation manner of the embodiment of the present application, step A2 may include: and selecting a track prediction strategy of the target obstacle according to the classification result of the target obstacle and the surrounding environment of the vehicle based on the corresponding relation between the classification result of the obstacle and the surrounding environment preset in the configuration file and the obstacle track prediction strategy.
In this implementation manner, a trajectory prediction algorithm (that is, a trajectory prediction strategy) suitable for the target obstacle and the surroundings thereof may be selected according to the classification result of the target obstacle and the surroundings of the vehicle, and a rule according to the selection may be set through a configuration file, where the configuration file includes a classification result of the obstacle to be labeled, a correspondence relationship between the classification result of the surroundings of the vehicle and the trajectory prediction algorithm, for example, a trajectory prediction algorithm a corresponding to the classification result a of the obstacle and the surroundings, and a trajectory prediction algorithm B corresponding to the classification result B of the obstacle and the surroundings, and so on. When the configuration file is read, the corresponding track prediction algorithm can be selected according to the classification result of the target obstacle and the surrounding environment of the vehicle and the rule in the configuration file.
Further, the embodiment of the present application may further include: and determining an interaction strategy between the target vehicle and the target obstacle according to the classification result of the target obstacle and the environment around the vehicle. In specific implementation, the interaction strategy between the target vehicle and the target obstacle can be selected according to the classification result of the target obstacle and the surrounding environment of the vehicle based on the corresponding relationship between the classification result of the obstacle and the surrounding environment preset in the configuration file and the vehicle interaction strategy.
Similar to the selection of the trajectory prediction algorithm, an interaction scheme (i.e., an interaction strategy) suitable for the target vehicle and the target obstacle may be selected according to the classification result of the target obstacle and the vehicle surrounding environment, the rule according to which the selection is performed may be set by a configuration file, in which the classification result of the obstacle and the classification result of the vehicle surrounding environment are labeled, and the correspondence between the interaction scheme and the classification result of the vehicle surrounding environment, for example, the classification result a of the obstacle and the surrounding environment corresponds to the interaction scheme a, and the classification result B of the obstacle and the surrounding environment corresponds to the interaction scheme B, and so on. When the configuration file is read, the corresponding interaction scheme can be selected according to the classification result of the target barrier and the surrounding environment of the vehicle and the rule in the configuration file.
S104: and predicting at least one future running track of the target barrier according to the track prediction strategy of the target barrier, and predicting the possibility that each future running track is selected by the target barrier.
In the embodiment of the present application, after the trajectory prediction strategy of the target obstacle and the interaction strategy between the target vehicle and the target obstacle are determined through the above steps, the relevant feature information required by the corresponding strategy needs to be calculated. It is understood that, since the input information required by different strategy methods is different, the calculation of the input information required by the corresponding strategy may be completed by using the vehicle periphery information acquired in the above step S101 as basic information, and the input information includes, but is not limited to, features of the target obstacle itself (such as average speed, average acceleration, etc.), features between the target obstacle and the map (such as distance between the obstacle and the nearest lane, direction angle, etc.), features of the map (such as topological relation of lanes, shape features, etc.), and the like.
Then, by using the various input information provided by the above, a plurality of future operation tracks of the target obstacle are predicted by using a track prediction strategy including but not limited to rules, optimization algorithms and machine learning models, wherein each prediction algorithm can be realized and packaged into a predictor, and related functions of parameter loading, initialization, prediction and the like of various algorithms are simply and efficiently realized through a predictor manager. It should be noted that in some special road environments, only one running track may be predicted.
Actually, the uncertainty of the actual movement of the obstacle can be well expressed by the multiple predicted tracks, and compared with a single predicted track, the probability of obtaining a correct track prediction result is higher, so that the accuracy is higher, and the automatic driving vehicle is helped to realize more reasonable interaction.
In addition, after solving a plurality of possible future operation tracks of the target obstacle, the embodiment of the application may further solve a probability value of selecting each future operation track by the target obstacle, where the probability value reflects a possibility that the target obstacle selects a corresponding future operation track, and may more fully describe a possible track space of the target obstacle.
In an implementation manner of the embodiment of the present application, the "predicting the possibility of each trajectory being selected by the target obstacle" in S104 may include: and predicting the possibility that each future running track is selected by the target barrier according to the historical running track of the historical barrier, the vehicle surrounding information of the target vehicle and each predicted future running track of the target barrier.
In this implementation, the probability that each future trajectory is selected by the target obstacle may be determined using information such as a historical trajectory of the historical obstacle (e.g., a historical obstacle of the same type as the target obstacle), vehicle surrounding information of the target vehicle (e.g., map environment information in the vehicle surrounding information), predicted future trajectories of the target obstacle, and the like, using a machine learning ranking algorithm including, but not limited to, lambdamat. For example, in actual prediction, when the target obstacle is close to the intersection area, the predictor will obtain multiple possible predicted trajectories such as straight line, turning around and the like, and the trajectory distribution is relatively divergent, however, after the target obstacle shows obvious intention, the predictor will give a relatively concentrated predicted trajectory, and as above, the process from divergence to convergence can show that the multi-trajectory prediction can completely and accurately cover the trajectory space of the target obstacle.
Therefore, in the embodiment of the application, the target vehicle can obtain the estimation of the future motion track of the target obstacle earlier by performing more complete prediction on the track space of the target obstacle, so that the target vehicle can make an interactive action with the target obstacle in advance, and a safer interactive result is presented.
Further, the embodiment of the present application may further include: and carrying out validity verification on the future running track of the target obstacle, wherein the validity verification comprises verifying at least one of whether the geometrical characteristics of the track are reasonable, whether the track meets kinematic constraints and whether the track conflicts with a map structure.
Specifically, each future trajectory of the predicted target obstacle may be validated to ensure that the future trajectory provided to the downstream system is valid and reasonable to ensure safe operation of the target vehicle. For each future moving track of the target barrier, when validity verification is performed on the future moving track, if the geometrical characteristics of the track of the future moving track are reasonable, the track meets kinematic constraints, and the track does not conflict with a map structure, the future moving track is valid, and then the target vehicle can realize normal interaction with the target barrier based on the future moving track.
The content of verifying whether the trajectory geometric characteristics are reasonable may include: whether the running track forms a ring or not and whether the running track is smooth or not. Generally speaking, when a certain future operation track is verified, if the track is looped by itself, the track is unreasonable, otherwise, the track is reasonable; if the track is not smooth, the track is not reasonable, otherwise it is reasonable.
The verification content of whether the trajectory satisfies the kinematic constraint may include: whether the required acceleration of the running track exceeds the maximum acceleration when the vehicle normally runs or not and whether the track curvature exceeds at least one of the vehicle steering angle ranges. Generally speaking, when a certain future running track is verified, if the acceleration required by the track exceeds the maximum acceleration of the vehicle during normal running, the track is unreasonable, otherwise, the track is reasonable; if the curvature of the track exceeds the vehicle steering angle range, the track is not reasonable, otherwise it is reasonable.
The verification content of whether the track conflicts with the map structure may include: whether the trajectory crosses multiple lanes, whether the trajectory is retrograde, whether the trajectory is out of the terrain map region. Generally speaking, when a certain future running track is verified, if the track spans multiple lanes, the track is unreasonable, otherwise, the track is reasonable; if the track is retrograde, the track is unreasonable, otherwise it is reasonable; if the track is off of the map area, the track is not reasonable, and vice versa.
Further, the embodiment of the present application may further include: determining a reference travel route of the target vehicle based on static obstacles around the target vehicle; judging whether the target vehicle collides with the dynamic barrier within preset time or not based on the future running track of the dynamic barrier around the target vehicle; and determining the actual running route of the target vehicle according to the judgment result.
Specifically, the interaction between the target vehicle and the obstacle can be realized on the basis of the 'speed-giving-no-way'. Calculating and generating a reference driving route of the target vehicle after each static obstacle around the vehicle is considered by a path planning module of the target vehicle, wherein the target vehicle can drive along the reference driving route, and when a dynamic obstacle (namely a certain target obstacle around the target vehicle mentioned in the foregoing content) is encountered during driving, the dynamic obstacle is processed by interactive logic; in the processing, whether the target vehicle collides with the dynamic obstacle within a preset time (for example, within 10 seconds) is determined according to each predicted future moving track of the dynamic obstacle, so as to form a series of dynamic constraints, and finally, an appropriate acceleration value without collision is selected for the target vehicle by combining the acceleration constraints of the vehicle kinematics, so as to determine the final actual moving track of the target vehicle. During actual operation, the interaction between the target vehicle and the dynamic obstacle is realized based on the interaction strategy mentioned in the foregoing, wherein the interaction strategy here may adopt different strategies such as conservation, aggressiveness and the like for the dynamic obstacle in following, cut-in, crossing, reverse and other operation states.
In the trajectory prediction method provided by the embodiment of the application, one or more future running trajectories of the target obstacle can be predicted for each target obstacle around the target vehicle, the possibility that each future running trajectory is selected by the target obstacle is predicted, uncertainty of the predicted trajectories during actual movement of the target obstacle can be well expressed, possible trajectory space of the target obstacle is comprehensively described, and accuracy of an obstacle trajectory prediction result is improved. Moreover, the target vehicle can obtain the estimation result of the future motion track of the target obstacle in advance by more perfect prediction of the track space, and the target vehicle and the target obstacle can be helped to realize more reasonable interaction, so that the safe operation of the target vehicle is realized.
It should be noted that the trajectory prediction method provided by the embodiment of the present application is more suitable for the target vehicle in the low-speed scene.
Referring to fig. 2, a schematic composition diagram of a trajectory prediction apparatus provided in an embodiment of the present application is shown, where the apparatus includes:
an information acquisition unit 210 for acquiring vehicle surrounding information of a target vehicle at a current time;
an obstacle classification unit 220, configured to classify target obstacles around the target vehicle according to at least one preset classification manner according to information about obstacles in the vehicle surrounding information;
a strategy determination unit 230, configured to determine a trajectory prediction strategy of the target obstacle based on a classification result of the target obstacle;
and a trajectory prediction unit 240, configured to predict at least one future trajectory of the target obstacle according to the trajectory prediction strategy, and predict a possibility that each future trajectory is selected by the target obstacle.
In an implementation manner of the embodiment of the present application, the policy determining unit 230 includes:
the environment classification subunit is used for classifying the vehicle surrounding environment of the target vehicle according to at least one preset classification mode according to the information about the environment where the vehicle is located in the vehicle surrounding information;
and the track strategy determining subunit is used for determining a track prediction strategy of the target obstacle according to the classification result of the target obstacle and the environment around the vehicle.
In an implementation manner of the embodiment of the present application, the trajectory policy determining subunit is specifically configured to:
and selecting a track prediction strategy of the target obstacle according to the classification result of the target obstacle and the surrounding environment of the vehicle based on the corresponding relation between the classification result of the obstacle and the surrounding environment preset in the configuration file and the obstacle track prediction strategy.
In an implementation manner of the embodiment of the present application, the policy determining unit 230 further includes:
and the interaction strategy determining subunit is used for determining an interaction strategy between the target vehicle and the target obstacle according to the classification result of the target obstacle and the environment around the vehicle.
In an implementation manner of the embodiment of the present application, the interaction policy determining subunit is specifically configured to:
and selecting an interaction strategy between the target vehicle and the target obstacle according to the classification result of the target obstacle and the surrounding environment of the vehicle based on the preset classification result of the obstacle and the surrounding environment in the configuration file and the corresponding relation between the vehicle interaction strategy and the classification result of the target obstacle and the surrounding environment of the vehicle.
In an implementation manner of the embodiment of the present application, the trajectory prediction unit 240 is specifically configured to:
and predicting the possibility that each future running track is selected by the target barrier according to the historical running track of the historical barrier, the vehicle surrounding information of the target vehicle and each predicted future running track of the target barrier.
In an implementation manner of the embodiment of the present application, the apparatus further includes:
and the track verification unit is used for verifying the effectiveness of the future running track of the target obstacle, wherein the effectiveness verification comprises at least one item of verification on whether the geometrical characteristics of the track are reasonable, whether the track meets kinematic constraint and whether the track conflicts with a map structure.
In an implementation manner of the embodiment of the present application, the content of verifying whether the geometric characteristics of the track are reasonable includes: whether the running track forms a ring or not and whether the running track is smooth or not; the verification content of whether the trajectory meets the kinematic constraint includes: whether the acceleration required by the running track exceeds at least one of the maximum acceleration when the vehicle normally runs and whether the track curvature exceeds the range of the steering angle of the vehicle; the verification content of whether the track conflicts with the map structure comprises the following steps: whether the trajectory crosses multiple lanes, whether the trajectory is retrograde, whether the trajectory is out of the terrain map region.
In an implementation manner of the embodiment of the present application, the apparatus further includes:
a reference route determination unit for determining a reference travel route of the target vehicle based on static obstacles around the target vehicle;
the collision judging unit is used for judging whether the target vehicle collides with the dynamic barrier within preset time or not based on the future running track of the dynamic barrier around the target vehicle;
and the actual route determining unit is used for determining the actual running route of the target vehicle according to the judgment result.
The implementation process of the functions and actions of each unit in the above device is specifically described in the implementation process of the corresponding step in the above method, and is not described herein again.
For the device embodiments, since they substantially correspond to the method embodiments, reference may be made to the partial description of the method embodiments for relevant points. The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed 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 modules can be selected according to actual needs to achieve the purpose of the scheme of the application. One of ordinary skill in the art can understand and implement it without inventive effort.
An embodiment of the present application further provides an electronic device, a schematic structural diagram of the electronic device is shown in fig. 3, the electronic device 3000 includes at least one processor 3001, a memory 3002, and a bus 3003, and the at least one processor 3001 is electrically connected to the memory 3002; the memory 3002 is configured to store at least one computer-executable instruction, and the processor 3001 is configured to execute the at least one computer-executable instruction so as to perform the steps of any one of the trajectory prediction methods as provided in any one of the embodiments or any one of the alternative embodiments of the present application.
Further, the processor 3001 may be an FPGA (Field-Programmable Gate Array) or other devices with logic processing capability, such as an MCU (micro controller Unit) and a CPU (Central processing Unit).
By applying the method and the device, one or more future running tracks of the target obstacle can be predicted, the possibility that each future running track is selected by the target obstacle is predicted, uncertainty of the predicted tracks when the target obstacle actually moves can be well expressed, the possible track space of the target obstacle is comprehensively described, and accuracy of an obstacle track prediction result is improved. Moreover, the target vehicle can obtain the estimation result of the future motion track of the target obstacle in advance by more perfect prediction of the track space, and the target vehicle and the target obstacle can be helped to realize more reasonable interaction, so that the safe operation of the target vehicle is realized.
The embodiment of the present application further provides another computer-readable storage medium, which stores a computer program, and the computer program is used for implementing the steps of any one of the trajectory prediction methods provided in any one of the embodiments or any one of the alternative embodiments of the present application when the computer program is executed by a processor.
The computer-readable storage medium provided by the embodiments of the present application includes, but is not limited to, any type of disk including floppy disks, hard disks, optical disks, CD-ROMs, and magneto-optical disks, ROMs (Read-Only memories), RAMs (Random Access memories), EPROMs (Erasable Programmable Read-Only memories), EEPROMs (Electrically Erasable Programmable Read-Only memories), flash memories, magnetic cards, or optical cards. That is, a readable storage medium includes any medium that stores or transmits information in a form readable by a device (e.g., a computer).
By applying the method and the device, one or more future running tracks of the target obstacle can be predicted, the possibility that each future running track is selected by the target obstacle is predicted, uncertainty of the predicted tracks when the target obstacle actually moves can be well expressed, the possible track space of the target obstacle is comprehensively described, and accuracy of an obstacle track prediction result is improved. Moreover, the target vehicle can obtain the estimation result of the future motion track of the target obstacle in advance by more perfect prediction of the track space, and the target vehicle and the target obstacle can be helped to realize more reasonable interaction, so that the safe operation of the target vehicle is realized.
The above description is only exemplary of the present application and should not be taken as limiting the present application, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the scope of protection of the present application.
Claims (12)
1. A trajectory prediction method, comprising:
acquiring vehicle surrounding information of a target vehicle at the current moment;
classifying the target obstacles around the target vehicle according to information about the obstacles in the vehicle surrounding information and at least one preset classification mode;
determining a trajectory prediction strategy of the target obstacle based on the classification result of the target obstacle;
and predicting at least one future running track of the target obstacle according to the track prediction strategy, and predicting the possibility that each future running track is selected by the target obstacle.
2. The method of claim 1, wherein determining a trajectory prediction strategy for the target obstacle based on the classification of the target obstacle comprises:
classifying the vehicle surrounding environment of the target vehicle according to at least one preset classification mode according to information about the environment where the vehicle is located in the vehicle surrounding information;
and determining a track prediction strategy of the target obstacle according to the classification result of the target obstacle and the environment around the vehicle.
3. The method of claim 2, wherein determining a trajectory prediction strategy for the target obstacle based on the classification of the target obstacle and the vehicle surroundings comprises:
and selecting a track prediction strategy of the target obstacle according to the classification result of the target obstacle and the surrounding environment of the vehicle based on the corresponding relation between the classification result of the obstacle and the surrounding environment preset in the configuration file and the obstacle track prediction strategy.
4. The method of claim 2, further comprising:
and determining an interaction strategy between the target vehicle and the target obstacle according to the classification result of the target obstacle and the environment around the vehicle.
5. The method of claim 4, wherein determining an interaction strategy between the target vehicle and the target obstacle based on the classification of the target obstacle and the vehicle surroundings comprises:
and selecting an interaction strategy between the target vehicle and the target obstacle according to the classification result of the target obstacle and the surrounding environment of the vehicle based on the preset classification result of the obstacle and the surrounding environment in the configuration file and the corresponding relation between the vehicle interaction strategy and the classification result of the target obstacle and the surrounding environment of the vehicle.
6. The method of claim 1, wherein the predicting the likelihood of each trajectory being selected by the target obstacle comprises:
and predicting the possibility that each future running track is selected by the target barrier according to the historical running track of the historical barrier, the vehicle surrounding information of the target vehicle and each predicted future running track of the target barrier.
7. The method according to any one of claims 1-6, further comprising:
and performing validity verification on the future operation track of the target obstacle, wherein the validity verification comprises verifying at least one of whether the geometrical characteristics of the track are reasonable, whether the track meets kinematic constraints and whether the track conflicts with a map structure.
8. The method of claim 7,
the contents of verifying whether the geometrical characteristics of the track are reasonable comprise: whether the running track forms a ring or not and whether the running track is smooth or not;
the verification content of whether the trajectory meets the kinematic constraint includes: whether the acceleration required by the running track exceeds at least one of the maximum acceleration when the vehicle normally runs and whether the track curvature exceeds the range of the steering angle of the vehicle;
the verification content of whether the track conflicts with the map structure comprises the following steps: whether the trajectory crosses multiple lanes, whether the trajectory is retrograde, and whether the trajectory departs from a terrain map region.
9. The method of any one of claims 1-6, further comprising:
determining a reference travel route of the target vehicle based on static obstacles around the target vehicle;
judging whether the target vehicle collides with the dynamic barrier within preset time or not based on the future running track of the dynamic barrier around the target vehicle;
and determining the actual running route of the target vehicle according to the judgment result.
10. A trajectory prediction device, comprising:
an information acquisition unit configured to acquire vehicle surrounding information of a target vehicle at a current time;
the obstacle classification unit is used for classifying the target obstacles around the target vehicle according to at least one preset classification mode according to the information about the obstacles in the vehicle surrounding information;
a strategy determination unit for determining a trajectory prediction strategy of the target obstacle based on a classification result of the target obstacle;
and the track prediction unit is used for predicting at least one future running track of the target obstacle according to the track prediction strategy and predicting the possibility that each future running track is selected by the target obstacle.
11. An electronic device, comprising: a processor, a memory;
the memory for storing a computer program;
the processor configured to execute the trajectory prediction method according to any one of claims 1 to 9 by calling the computer program.
12. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the trajectory prediction method according to any one of claims 1 to 9.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110522250.1A CN115246416B (en) | 2021-05-13 | 2021-05-13 | Track prediction method, track prediction device, track prediction equipment and computer readable storage medium |
| PCT/CN2022/070452 WO2022237208A1 (en) | 2021-05-13 | 2022-01-06 | Trajectory prediction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110522250.1A CN115246416B (en) | 2021-05-13 | 2021-05-13 | Track prediction method, track prediction device, track prediction equipment and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115246416A true CN115246416A (en) | 2022-10-28 |
| CN115246416B CN115246416B (en) | 2023-09-26 |
Family
ID=83696158
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110522250.1A Active CN115246416B (en) | 2021-05-13 | 2021-05-13 | Track prediction method, track prediction device, track prediction equipment and computer readable storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN115246416B (en) |
| WO (1) | WO2022237208A1 (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116821266B (en) * | 2022-12-30 | 2024-03-29 | 北京易航远智科技有限公司 | Semantic map construction method and automatic driving system with acquaintance road mode |
| CN117909895A (en) * | 2023-12-22 | 2024-04-19 | 曙光云计算集团股份有限公司 | Vehicle management method, device, computer equipment and storage medium |
Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3376330A1 (en) * | 2017-03-17 | 2018-09-19 | TTTech Computertechnik AG | Fault-tolerant method for detecting faults in an electronic system for controlling a controlled object |
| CN108985171A (en) * | 2018-06-15 | 2018-12-11 | 上海仙途智能科技有限公司 | Estimation method of motion state and state estimation device |
| CN109313445A (en) * | 2016-03-23 | 2019-02-05 | 优特诺股份有限公司 | The promotion of vehicle drive and automatic Pilot |
| CN109583151A (en) * | 2019-02-20 | 2019-04-05 | 百度在线网络技术（北京）有限公司 | The driving trace prediction technique and device of vehicle |
| US20190367021A1 (en) * | 2018-05-31 | 2019-12-05 | Nissan North America, Inc. | Predicting Behaviors of Oncoming Vehicles |
| CN111427369A (en) * | 2020-06-08 | 2020-07-17 | 北京三快在线科技有限公司 | Unmanned vehicle control method and device |
| US20200262448A1 (en) * | 2019-02-19 | 2020-08-20 | Baidu Online Network Technology (Beijing) Co., Ltd. | Decision method, device, equipment in a lane changing process and storage medium |
| US20200269873A1 (en) * | 2019-02-22 | 2020-08-27 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and apparatus for planning speed of autonomous vehicle, and storage medium |
| US20200269874A1 (en) * | 2019-02-26 | 2020-08-27 | Baidu Online Network Technology (Beijing) Co., Ltd. | Track prediction method and device for obstacle at junction |
| CN111857160A (en) * | 2020-08-17 | 2020-10-30 | 武汉中海庭数据技术有限公司 | Unmanned vehicle path planning method and device |
| CN111982143A (en) * | 2020-08-11 | 2020-11-24 | 北京汽车研究总院有限公司 | Vehicle and vehicle path planning method and device |
| KR102192348B1 (en) * | 2020-02-24 | 2020-12-17 | 한국과학기술원 | Electronic device for integrated trajectory prediction for unspecified number of surrounding vehicles and operating method thereof |
| US20210001884A1 (en) * | 2020-06-27 | 2021-01-07 | Intel Corporation | Technology to generalize safe driving experiences for automated vehicle behavior prediction |
| CN112193244A (en) * | 2020-09-30 | 2021-01-08 | 浙江大学 | Automatic driving vehicle motion planning method based on linear constraint |
| US20210027629A1 (en) * | 2019-07-25 | 2021-01-28 | Baidu Usa Llc | Blind area processing for autonomous driving vehicles |
| US20210046926A1 (en) * | 2019-08-13 | 2021-02-18 | Zoox, Inc. | Feasibility validation for vehicle trajectory selection |
| US10928820B1 (en) * | 2019-11-12 | 2021-02-23 | Baidu Usa Llc | Confidence levels along the same predicted trajectory of an obstacle |
| US20210078592A1 (en) * | 2019-09-14 | 2021-03-18 | Honda Motor Co., Ltd. | Trajectory planner |
| CN112519765A (en) * | 2019-09-03 | 2021-03-19 | 北京百度网讯科技有限公司 | Vehicle control method, apparatus, device, and medium |
| DE102019125401A1 (en) * | 2019-09-20 | 2021-03-25 | Technische Universität Darmstadt | Module and method for validating target trajectories for automated driving |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6809890B2 (en) * | 2016-12-15 | 2021-01-06 | 日立オートモティブシステムズ株式会社 | Vehicle control device |
| CN109213134B (en) * | 2017-07-03 | 2020-04-28 | 百度在线网络技术（北京）有限公司 | Method and device for generating automatic driving strategy |
| US11679764B2 (en) * | 2019-06-28 | 2023-06-20 | Baidu Usa Llc | Method for autonomously driving a vehicle based on moving trails of obstacles surrounding the vehicle |
| CN110371112B (en) * | 2019-07-06 | 2021-10-01 | 深圳数翔科技有限公司 | Intelligent obstacle avoidance system and method for automatic driving vehicle |
| CN110929702B (en) * | 2020-01-22 | 2020-05-08 | 华人运通(上海)新能源驱动技术有限公司 | Trajectory planning method and device, electronic equipment and storage medium |
| CN112255628A (en) * | 2020-10-09 | 2021-01-22 | 新石器慧义知行智驰(北京)科技有限公司 | Obstacle trajectory prediction method, apparatus, device, and medium |
| CN112364997B (en) * | 2020-12-08 | 2021-06-04 | 北京三快在线科技有限公司 | Method and device for predicting track of obstacle |
| CN113335276A (en) * | 2021-07-20 | 2021-09-03 | 中国第一汽车股份有限公司 | Obstacle trajectory prediction method, obstacle trajectory prediction device, electronic device, and storage medium |
-
2021
- 2021-05-13 CN CN202110522250.1A patent/CN115246416B/en active Active
-
2022
- 2022-01-06 WO PCT/CN2022/070452 patent/WO2022237208A1/en active Application Filing
Patent Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109313445A (en) * | 2016-03-23 | 2019-02-05 | 优特诺股份有限公司 | The promotion of vehicle drive and automatic Pilot |
| EP3376330A1 (en) * | 2017-03-17 | 2018-09-19 | TTTech Computertechnik AG | Fault-tolerant method for detecting faults in an electronic system for controlling a controlled object |
| US20190367021A1 (en) * | 2018-05-31 | 2019-12-05 | Nissan North America, Inc. | Predicting Behaviors of Oncoming Vehicles |
| CN108985171A (en) * | 2018-06-15 | 2018-12-11 | 上海仙途智能科技有限公司 | Estimation method of motion state and state estimation device |
| US20200262448A1 (en) * | 2019-02-19 | 2020-08-20 | Baidu Online Network Technology (Beijing) Co., Ltd. | Decision method, device, equipment in a lane changing process and storage medium |
| CN109583151A (en) * | 2019-02-20 | 2019-04-05 | 百度在线网络技术（北京）有限公司 | The driving trace prediction technique and device of vehicle |
| US20200269873A1 (en) * | 2019-02-22 | 2020-08-27 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and apparatus for planning speed of autonomous vehicle, and storage medium |
| US20200269874A1 (en) * | 2019-02-26 | 2020-08-27 | Baidu Online Network Technology (Beijing) Co., Ltd. | Track prediction method and device for obstacle at junction |
| US20210027629A1 (en) * | 2019-07-25 | 2021-01-28 | Baidu Usa Llc | Blind area processing for autonomous driving vehicles |
| US20210046926A1 (en) * | 2019-08-13 | 2021-02-18 | Zoox, Inc. | Feasibility validation for vehicle trajectory selection |
| CN112519765A (en) * | 2019-09-03 | 2021-03-19 | 北京百度网讯科技有限公司 | Vehicle control method, apparatus, device, and medium |
| US20210078592A1 (en) * | 2019-09-14 | 2021-03-18 | Honda Motor Co., Ltd. | Trajectory planner |
| DE102019125401A1 (en) * | 2019-09-20 | 2021-03-25 | Technische Universität Darmstadt | Module and method for validating target trajectories for automated driving |
| US10928820B1 (en) * | 2019-11-12 | 2021-02-23 | Baidu Usa Llc | Confidence levels along the same predicted trajectory of an obstacle |
| KR102192348B1 (en) * | 2020-02-24 | 2020-12-17 | 한국과학기술원 | Electronic device for integrated trajectory prediction for unspecified number of surrounding vehicles and operating method thereof |
| CN111427369A (en) * | 2020-06-08 | 2020-07-17 | 北京三快在线科技有限公司 | Unmanned vehicle control method and device |
| US20210001884A1 (en) * | 2020-06-27 | 2021-01-07 | Intel Corporation | Technology to generalize safe driving experiences for automated vehicle behavior prediction |
| CN111982143A (en) * | 2020-08-11 | 2020-11-24 | 北京汽车研究总院有限公司 | Vehicle and vehicle path planning method and device |
| CN111857160A (en) * | 2020-08-17 | 2020-10-30 | 武汉中海庭数据技术有限公司 | Unmanned vehicle path planning method and device |
| CN112193244A (en) * | 2020-09-30 | 2021-01-08 | 浙江大学 | Automatic driving vehicle motion planning method based on linear constraint |
Non-Patent Citations (1)
| Title |
|---|
| 张琳;章新杰;郭孔辉;王超;刘洋;刘涛;: "未知环境下智能汽车轨迹规划滚动窗口优化", 吉林大学学报(工学版), no. 03 * |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2022237208A1 (en) | 2022-11-17 |
| CN115246416B (en) | 2023-09-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11726477B2 (en) | Methods and systems for trajectory forecasting with recurrent neural networks using inertial behavioral rollout | |
| Hubmann et al. | A POMDP maneuver planner for occlusions in urban scenarios | |
| US11465619B2 (en) | Vehicle collision avoidance based on perturbed object trajectories | |
| JP6831420B2 (en) | A method for evaluating self-driving car trajectory candidates | |
| US11851081B2 (en) | Predictability-based autonomous vehicle trajectory assessments | |
| US10969789B2 (en) | Verifying predicted trajectories using a grid-based approach | |
| JP7538893B2 (en) | Method and system for data-driven and modular decision-making and path generation for autonomous agents - Patents.com | |
| US20190155291A1 (en) | Methods and systems for automated driving system simulation, validation, and implementation | |
| JP2022536263A (en) | Apparatus, methods and articles for facilitating motion planning in environments with dynamic obstacles | |
| US11415992B2 (en) | Resource prioritization based on travel path relevance | |
| JP2023533507A (en) | Systems and methods for optimizing trajectory planners based on human driving behavior | |
| CN116323353A (en) | Allocation of security system resources based on probability of intersection | |
| CN110834631A (en) | Pedestrian avoiding method and device, vehicle and storage medium | |
| CN115246416B (en) | Track prediction method, track prediction device, track prediction equipment and computer readable storage medium | |
| Zhan et al. | Risk-aware lane-change trajectory planning with rollover prevention for autonomous light trucks on curved roads | |
| CN115230688B (en) | Obstacle trajectory prediction method, system, and computer-readable storage medium | |
| US20230053243A1 (en) | Hybrid Performance Critic for Planning Module's Parameter Tuning in Autonomous Driving Vehicles | |
| Liu et al. | Protected turning movements of noncooperative automated vehicles: Geometrics, trajectories, and saturation flow | |
| Zhong et al. | Driving with caution about fully occluded areas based on occupancy maps | |
| US11926335B1 (en) | Intention prediction in symmetric scenarios | |
| 채흥석 | Active Lane Change Decision and Control using Data-driven Safety Boundary and Collision Probability | |
| Syama et al. | Stackelberg: Hidden Markov Model Approach for Behavior Prediction of Surrounding Vehicles for Autonomous Driving | |
| CN114620058A (en) | Trajectory planning method, trajectory planning device, computing apparatus, moving object, and storage medium | |
| CN117826785A (en) | Driving speed planning method and system for collision avoidance of automatic driving automobile | |
| CN117782127A (en) | Passenger car track planning method and system based on learning network and rule mixed driving |
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 |