CN114590275A - Method for predicting lane change intention of vehicle based on composite model - Google Patents

Method for predicting lane change intention of vehicle based on composite model Download PDF

Info

Publication number
CN114590275A
CN114590275A CN202210325865.XA CN202210325865A CN114590275A CN 114590275 A CN114590275 A CN 114590275A CN 202210325865 A CN202210325865 A CN 202210325865A CN 114590275 A CN114590275 A CN 114590275A
Authority
CN
China
Prior art keywords
vehicle
model
lane
vehicles
target
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210325865.XA
Other languages
Chinese (zh)
Inventor
黄杉
尹旭
肖友
单玉梅
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Chongqing Changan Automobile Co Ltd
Original Assignee
Chongqing Changan Automobile Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Chongqing Changan Automobile Co Ltd filed Critical Chongqing Changan Automobile Co Ltd
Priority to CN202210325865.XA priority Critical patent/CN114590275A/en
Publication of CN114590275A publication Critical patent/CN114590275A/en
Pending legal-status Critical Current

Links

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
    • B60W60/0015—Planning or execution of driving tasks specially adapted for safety
    • B60W60/0016—Planning or execution of driving tasks specially adapted for safety of the vehicle or its occupants
    • 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
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/10—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to vehicle motion
    • 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
    • B60W2420/00—Indexing codes relating to the type of sensors based on the principle of their operation
    • B60W2420/40—Photo, light or radio wave sensitive means, e.g. infrared sensors
    • B60W2420/403—Image sensing, e.g. optical camera
    • 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
    • B60W2420/00—Indexing codes relating to the type of sensors based on the principle of their operation
    • B60W2420/40—Photo, light or radio wave sensitive means, e.g. infrared sensors
    • B60W2420/408—Radar; Laser, e.g. lidar
    • 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
    • B60W2520/00—Input parameters relating to overall vehicle dynamics
    • B60W2520/06—Direction of travel
    • 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
    • B60W2520/00—Input parameters relating to overall vehicle dynamics
    • B60W2520/10—Longitudinal speed
    • 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
    • B60W2554/80—Spatial relation or speed relative to objects
    • B60W2554/801—Lateral distance
    • 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
    • B60W2554/80—Spatial relation or speed relative to objects
    • B60W2554/802—Longitudinal distance
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Human Computer Interaction (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention discloses a method for predicting a lane change intention of a vehicle based on a composite model, which comprises the following steps: collecting speed information and position information of a vehicle and surrounding vehicles; arranging the vehicle and the surrounding vehicles in the same coordinate system, and forming a training set A by the track information of all target vehicles; establishing three hidden Markov models, namely a left lane changing model, a lane keeping model and a right lane changing model; inputting the training set A into three models for preliminary prediction, and respectively outputting corresponding probabilities; combining the longitudinal distance between the neighbor vehicle and the corresponding target vehicle with the corresponding probability to form a training set B, inputting the training set B into the multilayer perceptron model, and finishing the training of the multilayer perceptron model by taking the corresponding real lane changing intention of the target vehicle as a label to obtain a training model; and acquiring speed information and position information of the target vehicle and the neighbor vehicle in real time, inputting the speed information and the position information into the training model to predict the lane changing intention of the vehicle, and outputting the lane changing intention of the target vehicle.

Description

Method for predicting lane change intention of vehicle based on composite model
Technical Field
The invention belongs to the technical field of automatic driving, and particularly relates to a method for predicting a lane change intention of a vehicle based on a composite model.
Background
Smart cars are the development direction of future vehicles, and they have great potential in improving driving safety and traffic efficiency. The decision-making module of the intelligent vehicle receives the environmental information acquired by the external sensing system and predicts the surrounding vehicles and the movement of obstacles in the environment so as to determine the following behaviors of the vehicle. The method is important for accurately predicting the intention and the track of the surrounding vehicle, because the collision is effectively avoided, the guarantee of the driving safety in a complex traffic environment is increased, and the decided behavior safety can be guaranteed and the social standard is met, so that the driving safety and the comfort can be guaranteed on the premise of no conservation, and the traffic accident can be avoided.
At present, the research on the prediction of the lane-changing intention of the surrounding vehicles does not consider the influence of interaction between vehicles on the lane-changing intention of the vehicles, but takes the target vehicle as an independent individual to predict the lane-changing intention, but under the actual driving condition, the neighbor vehicles of the target vehicle can greatly influence the lane-changing behavior.
Therefore, how to accurately predict the lane change intention of the surrounding vehicles by considering the influence of the interaction between the vehicles on the lane change intention of the vehicles and improve the running safety of the automatic driving vehicle is a technical problem to be solved by the technical personnel in the field.
Disclosure of Invention
In view of the above-mentioned shortcomings of the prior art, the present invention aims to provide a method for predicting lane change intention of a vehicle based on a composite model, which can effectively consider the influence of interaction between vehicles on the lane change intention of the vehicle, accurately predict the lane change intention of surrounding vehicles, and improve the driving safety of an automatic driving vehicle.
The technical scheme of the invention is realized as follows:
a method for predicting a lane change intention of a vehicle based on a composite model comprises the following steps:
(1) collecting speed information and position information of a vehicle and surrounding vehicles;
(2) arranging the vehicle and the surrounding vehicles in the same coordinate system according to the speed information and the position information acquired in the step (1) so as to obtain track information of the vehicle and the surrounding vehicles, wherein the surrounding vehicles adjacent to the vehicle are target vehicles, the vehicles around each target vehicle are neighbor vehicles of the target vehicles, and the track information of all the target vehicles forms a training set A;
(3) establishing three hidden Markov models, namely a left lane changing model, a lane keeping model and a right lane changing model;
(4) inputting the training set A in the step (2) into a left lane changing model, a lane keeping model and a right lane changing model for preliminary prediction, and respectively outputting corresponding probabilities PL、PK、PR；
(5) The longitudinal distance between the neighbor vehicle and the corresponding target vehicle and the corresponding probability PL、PK、PRCombining to form a training set B, inputting the training set B into the multilayer perceptron model, and finishing the training of the multilayer perceptron model by taking the real lane change intention corresponding to the target vehicle as a label to obtain a training model;
(6) and (5) acquiring speed information and position information of the target vehicle and the neighbor vehicle in real time, inputting the speed information and the position information into the training model in the step (5) to predict the lane changing intention of the vehicle, and outputting the lane changing intention of the target vehicle.
Further, in the step (1), speed information and position information of the own vehicle and surrounding vehicles are collected by using a radar device and a camera device on the own vehicle.
Still further, the radar means includes, but is not limited to, millimeter wave radar, laser radar, and ultrasonic radar.
Further, the camera device includes, but is not limited to, a look-around camera, a look-ahead camera.
Further, the speed information and the position information include, but are not limited to, the speed of the host vehicle, the heading angle of the host vehicle, the speed of the neighboring vehicle, lane line information, and the lateral distance and the longitudinal distance of the neighboring vehicle from the host vehicle.
Furthermore, the neighbor vehicles are vehicles located in the front and back of the lane where the target vehicle is located and within a set distance from the left lane and the right lane.
Compared with the prior art, the invention has the following beneficial effects:
the method comprises the steps of firstly, preliminarily identifying the lane changing intention of the vehicle by utilizing the time sequence modeling capacity of continuous observation variables such as the transverse displacement, the longitudinal speed and the like of a target vehicle through a hidden Markov model, then combining the probabilities output by LCL-HMM, LK-HMM and LCR-HMM models with the longitudinal distance between a neighbor vehicle and the corresponding target vehicle, and inputting the probabilities into a multilayer perceptron model to effectively predict the lane changing intention of the peripheral target vehicle. Therefore, the interactive influence between the target vehicle and the corresponding neighbor vehicle is used as a factor for predicting the target vehicle lane changing intention, and the accuracy of predicting the target vehicle lane changing intention and the running safety of the automatic driving vehicle can be effectively improved.
Drawings
FIG. 1-inventive modeling flow diagram.
FIG. 2-a scene diagram of the actual vehicle layout in the embodiment.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and specific embodiments.
A method for predicting lane change intention of a vehicle based on a composite model comprises the following steps:
(1) collecting speed information and position information of a vehicle and surrounding vehicles;
(2) arranging the vehicle and the surrounding vehicles in the same coordinate system according to the speed information and the position information acquired in the step (1) so as to obtain track information of the vehicle and the surrounding vehicles, wherein the surrounding vehicles adjacent to the vehicle are target vehicles, the vehicles around each target vehicle are neighbor vehicles of the target vehicles, and the track information of all the target vehicles forms a training set A;
(3) establishing three hidden Markov models, namely a left lane changing model LCL-HMM, a lane keeping model LK-HMM and a right lane changing model LCR-HMM;
(4) inputting the training set A in the step (2) into three models of LCL-HMM, LK-HMM and LCR-HMM for preliminary prediction, and respectively outputting corresponding probabilities PL、PK、PR；
(5) The longitudinal distance between the neighbor vehicle and the corresponding target vehicle and the corresponding probability PL、PK、PRCombining to form a training set B, inputting the training set B into a multilayer perceptron (MLP) model, and finishing the training of the multilayer perceptron model by taking a real lane-changing intention corresponding to a target vehicle as a label, thereby establishing a training model, namely an HMM-MLP model;
(6) and (5) acquiring speed information and position information of the target vehicle and the neighbor vehicle in real time, inputting the speed information and the position information into the training model in the step (5) to predict the lane changing intention of the vehicle, and outputting the lane changing intention of the target vehicle.
A flow chart for building the HMM-MLP model is shown in FIG. 1. The method comprises the steps of firstly, preliminarily identifying a lane changing intention of a vehicle by utilizing the time sequence modeling capacity of continuous observation variables such as transverse displacement, longitudinal speed and the like of a target vehicle through a Hidden Markov Model (HMM), then combining the likelihood probabilities output by an LCL-HMM model, an LK-HMM model and an LCR-HMM model with the longitudinal distance between a neighbor vehicle and the corresponding target vehicle, and inputting the likelihood probabilities into a multilayer perceptron (MLP) model to effectively predict the lane changing intention of the peripheral target vehicle. Therefore, the interactive influence between the target vehicle and the corresponding neighbor vehicle is used as a factor for predicting the lane changing intention of the target vehicle, and the accuracy of predicting the lane changing intention of the target vehicle and the running safety of the automatic driving vehicle can be effectively improved.
The left lane changing model LCL-HMM, the lane keeping model LK-HMM and the right lane changing model LCR-HMM are three mutually independent models, so the probability P is obtained through the prediction of the three modelsL、PK、PRThere is no necessary connection between them.
The longitudinal distance P between the target vehicle and the neighbor vehicle positioned on the left lane of the target vehicle in the step (5)LAnd in combination, the longitudinal distance P between the target vehicle and the neighboring vehicle located in the left lane of the target vehicleKAnd in combination, the longitudinal distance P between the target vehicle and the neighboring vehicle located in the left lane of the target vehicleRAnd combining to form a training set B.
In the specific implementation, in the step (1), the radar device and the camera device on the vehicle are used for collecting the speed information and the position information of the vehicle and the surrounding vehicles.
In specific implementations, the radar device includes, but is not limited to, millimeter wave radar, laser radar, and ultrasonic radar.
In specific implementation, the camera device includes, but is not limited to, a look-around camera and a look-ahead camera.
In one embodiment, the speed information and the position information include, but are not limited to, a speed of the host vehicle, a heading angle of the host vehicle, a speed of the neighboring vehicle, lane line information, and a lateral distance and a longitudinal distance between the neighboring vehicle and the host vehicle.
In specific implementation, the neighbor vehicles are vehicles located in the front and back of the lane where the target vehicle is located and within a set distance from the left lane and the right lane.
The set distance is set as needed, and is generally 120m or 90 m.
If no vehicle exists in one lane of the target vehicle or the distance between the target vehicle and the neighboring vehicle is greater than the set distance in the step (5), in order to ensure uniform format, the longitudinal distance between the neighboring vehicle of the lane and the target vehicle is considered as the set distance.
Referring to fig. 2, a vehicle 1 is a target vehicle, and vehicles 2 to 5 are neighboring vehicles of the vehicle 1, wherein the vehicles 2 and 3 are located on a left lane, the vehicle 4 is located on a local lane, and the vehicle 5 is located on a right lane. Firstly, information data of the vehicle 1 are respectively input into a left lane changing model LCL-HMM, a lane keeping model LK-HMM and a right lane changing model LCR-HMM for preliminary prediction, and left lane changing probability P is respectively obtainedLLane keeping probability PKAnd right lane change probability PRThen P is addedLIn combination with the longitudinal distance of cars 2 and 3 to car 1, respectively, will PKIn combination with the longitudinal distance of car 4 to car 1, PRAnd combining with the longitudinal distance from the vehicle 5 to the vehicle 1, inputting the distance into a multilayer perceptron model for training, and completing the establishment of the HMM-MLP model according to the method. After the HMM-MLP model is established, the acquired data are directly input into the model, and a prediction result can be obtained.
Finally, it should be noted that the above-mentioned examples of the present invention are only examples for illustrating the present invention, and are not intended to limit the embodiments of the present invention. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. Not all embodiments are exhaustive. All obvious changes and modifications of the present invention are within the scope of the present invention.

Claims (6)

1. A method for predicting a lane change intention of a vehicle based on a composite model is characterized by comprising the following steps:
(1) collecting speed information and position information of a vehicle and surrounding vehicles;
(2) arranging the vehicle and the surrounding vehicles in the same coordinate system according to the speed information and the position information acquired in the step (1) so as to obtain track information of the vehicle and the surrounding vehicles, wherein the surrounding vehicles adjacent to the vehicle are target vehicles, the vehicles around each target vehicle are neighbor vehicles of the target vehicles, and the track information of all the target vehicles forms a training set A;
(3) establishing three hidden Markov models, namely a left lane changing model, a lane keeping model and a right lane changing model;
(4) inputting the training set A in the step (2) into a left lane changing model, a lane keeping model and a right lane changing model for preliminary prediction, and respectively outputting corresponding probabilities PL、PK、PR；
(5) The longitudinal distance between the neighbor vehicle and the corresponding target vehicle and the corresponding probability PL、PK、PRCombining to form a training set B, inputting the training set B into the multilayer perceptron model, and finishing the training of the multilayer perceptron model by taking the real lane change intention corresponding to the target vehicle as a label to obtain a training model;
(6) and (5) acquiring speed information and position information of the target vehicle and the neighbor vehicle in real time, inputting the speed information and the position information into the training model in the step (5) to predict the lane changing intention of the vehicle, and outputting the lane changing intention of the target vehicle.
2. The method for predicting the lane change intention of the vehicle based on the composite model according to claim 1, wherein in the step (1), the speed information and the position information of the vehicle and the surrounding vehicles are collected by using a radar device and a camera device on the vehicle.
3. The method for predicting lane change intention of a vehicle based on a composite model according to claim 2, wherein the radar device includes, but is not limited to, millimeter wave radar, laser radar and ultrasonic radar.
4. The method for predicting the lane change intention of the vehicle based on the composite model as claimed in claim 2, wherein the camera device includes, but is not limited to, a look-around camera and a look-ahead camera.
5. The method as claimed in claim 2, wherein the speed information and the position information include, but are not limited to, the speed of the host vehicle, the heading angle of the host vehicle, the speed of the neighboring vehicles, lane line information, and the lateral distance and the longitudinal distance between the neighboring vehicles and the host vehicle.
6. The method as claimed in claim 1, wherein the neighboring vehicles are vehicles located within a set distance from the front and back of the lane where the target vehicle is located, and from the left lane and the right lane.
CN202210325865.XA 2022-03-30 2022-03-30 Method for predicting lane change intention of vehicle based on composite model Pending CN114590275A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210325865.XA CN114590275A (en) 2022-03-30 2022-03-30 Method for predicting lane change intention of vehicle based on composite model

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210325865.XA CN114590275A (en) 2022-03-30 2022-03-30 Method for predicting lane change intention of vehicle based on composite model

Publications (1)

Publication Number Publication Date
CN114590275A true CN114590275A (en) 2022-06-07

Family

ID=81821578

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210325865.XA Pending CN114590275A (en) 2022-03-30 2022-03-30 Method for predicting lane change intention of vehicle based on composite model

Country Status (1)

Country Link
CN (1) CN114590275A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115273460A (en) * 2022-06-28 2022-11-01 重庆长安汽车股份有限公司 Multi-mode perception fusion vehicle lane change prediction method, computer equipment and storage medium

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115273460A (en) * 2022-06-28 2022-11-01 重庆长安汽车股份有限公司 Multi-mode perception fusion vehicle lane change prediction method, computer equipment and storage medium

Similar Documents

Publication Publication Date Title
Yu et al. Deep learning-based traffic safety solution for a mixture of autonomous and manual vehicles in a 5G-enabled intelligent transportation system
Bachute et al. Autonomous driving architectures: insights of machine learning and deep learning algorithms
US11726477B2 (en) Methods and systems for trajectory forecasting with recurrent neural networks using inertial behavioral rollout
EP4152204A1 (en) Lane line detection method, and related apparatus
CN113954864B (en) Intelligent automobile track prediction system and method integrating peripheral automobile interaction information
CN112633176B (en) Rail transit obstacle detection method based on deep learning
He et al. Rail transit obstacle detection based on improved CNN
CN112614373B (en) BiLSTM-based weekly vehicle lane change intention prediction method
CN112258841B (en) Intelligent vehicle risk assessment method based on vehicle track prediction
Yu et al. Machine Learning-Based Vehicle Intention Trajectory Recognition and Prediction for Autonomous Driving
CN114559959A (en) Automatic driving behavior decision system and method based on driving preference
CN115743179A (en) Vehicle probability multi-mode expected trajectory prediction method
CN114590275A (en) Method for predicting lane change intention of vehicle based on composite model
Khalil et al. Exploiting multi-modal fusion for urban autonomous driving using latent deep reinforcement learning
CN114446046A (en) LSTM model-based weak traffic participant track prediction method
Han et al. A novel end-to-end model for steering behavior prediction of autonomous ego-vehicles using spatial and temporal attention mechanism
Zhang et al. Multi-modal virtual-real fusion based transformer for collaborative perception
CN116501820A (en) Vehicle track prediction method, device, equipment and storage medium
CN116541295A (en) Road dynamic scene simulation method and system
CN111160089A (en) Trajectory prediction system and method based on different vehicle types
CN114926823B (en) WGCN-based vehicle driving behavior prediction method
CN115817477A (en) Game theory-based automatic port wharf face driving lane changing decision method
CN115440041A (en) Method for predicting driving behavior of key vehicle under road side view angle
CN113536973B (en) Traffic sign detection method based on saliency
CN114822048A (en) Cloud planning service system and method for Internet vehicles

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