CN112721929A - Decision-making method for lane changing behavior of automatic driving vehicle based on search technology - Google Patents
Decision-making method for lane changing behavior of automatic driving vehicle based on search technology Download PDFInfo
- Publication number
- CN112721929A CN112721929A CN202110030986.7A CN202110030986A CN112721929A CN 112721929 A CN112721929 A CN 112721929A CN 202110030986 A CN202110030986 A CN 202110030986A CN 112721929 A CN112721929 A CN 112721929A
- Authority
- CN
- China
- Prior art keywords
- behavior
- lane change
- search
- decision
- tree
- 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 23
- 230000008859 change Effects 0.000 claims abstract description 46
- 230000006399 behavior Effects 0.000 claims description 92
- 230000001133 acceleration Effects 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000003780 insertion Methods 0.000 claims description 2
- 238000004422 calculation algorithm Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 6
- 238000013138 pruning Methods 0.000 description 6
- 238000010845 search algorithm Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 230000001413 cellular effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000005284 excitation Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/18—Propelling the vehicle
- B60W30/18009—Propelling the vehicle related to particular drive situations
- B60W30/18163—Lane change; Overtaking manoeuvres
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a decision-making method for lane change behavior of an automatic driving vehicle based on a search technology, which comprises the following steps: (S1) after predicting the future trajectory of the surrounding vehicle, the autonomous vehicle decides its own driving behavior; (S2) in the behavior decision, making a decision on a lane change behavior of the autonomous vehicle through the behavior search module and the behavior processing module, respectively. Through the scheme, the automatic driving system achieves the purpose of efficient automatic driving, and has high practical value and popularization value.
Description
Technical Field
The invention belongs to the technical field of automatic driving, and particularly relates to a method for deciding lane changing behavior of an automatic driving vehicle based on a search technology.
Background
Many studies have proposed many medium model predictions for autonomous driving, which are divided as follows:
predicting lane change based on the scene model: a new highway lane change assist and automatic driving control algorithm based on the scene model predictive control (scmpcc) has been proposed. The basic idea is to interpret the uncertainty in the traffic environment by a small number of future scenarios to perform a safe lane change.
Incentive-based decentralized coordinated lane change for autonomous vehicles: an excitation-based decision framework for decentralized and collaborative lane change of an automatic driving vehicle determines corresponding decisions by respectively adopting an excitation-based model and a collision avoidance coordination algorithm.
Predicting lane change based on a cellular automaton model: a classical cellular automaton model (STNS) has been proposed that uses a set of rules to determine future lane-change behavior.
Predicting lane change based on a kinematic model: a kinematic model of lane change is proposed, which can plan the motion trajectory of the lane according to the characteristics of a polynomial. In addition, an infinite dynamic circle is applied to detect collisions during the lane change.
Predicting lane change based on a selection model: a highway lane selection model (FLS) has been proposed that will enable traffic professionals to more accurately simulate lane-change behavior on a highway. Thus, the traffic simulation software integrates the FLS algorithm into a commercial version of its software. The FLS algorithm includes target lane selection and gap acceptance decisions, with the goal of outputting the most accurate lane change decision.
The lane change planning algorithm mainly focuses on the safety, comfort and accuracy of lane change, but ignores the potential influence of lane change on other vehicles, so that the automatic driving vehicle cannot process the road environment more intelligently, and the efficient automatic driving cannot be achieved. Therefore, how to solve the problems existing in the prior art is a problem which needs to be solved urgently by the technical personnel in the field.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides a decision-making method for lane changing behavior of an automatic driving vehicle based on a search technology, so that the automatic driving vehicle is more intelligent, and efficient automatic driving is achieved.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
a decision-making method for lane change behavior of an automatic driving vehicle based on a search technology comprises the following steps:
(S1) after predicting the future trajectory of the surrounding vehicle, the autonomous vehicle decides its own driving behavior;
(S2) in the behavior decision, making a decision on a lane change behavior of the autonomous vehicle through the behavior search module and the behavior processing module, respectively.
Further, the future trajectory prediction result of the surrounding vehicle in the step (S1) includes nine nodes, which are: (a) left lane change acceleration, (b) left lane change deceleration, (c) left lane change holding speed, (d) lane change-free acceleration, (e) lane change-free deceleration, (f) lane change-free holding speed, (g) right lane change acceleration, (h) right lane change deceleration, and (i) right lane change holding speed.
Further, the behavior search module in the step (S2) functions to search the system for the optimal behavior of the discrete autonomous vehicle.
Further, the role of the behavior processing module in the step (S2) is that the system directly converts discrete behaviors into continuous accurate values as output results.
Specifically, the specific steps of the action decision in the step (S2) are as follows:
(S21) the behavior search module acquires a result of predicting a trajectory of a surrounding vehicle;
(S22) constructing a search tree by the acquired trajectory prediction results of the surrounding vehicles;
(S23) performing a behavior search on the constructed search tree;
(S24) converting discrete ones of the execution behaviors into continuous precise values by the behavior processing module;
(S25) the behavior processing module outputs the continuous accurate value as a result.
Further, the searching for the tree in the step (S22) is based on a data structure of the tree, the depth of the tree is Z, each non-leaf node has nine child nodes, wherein the root node represents the current state, the other child nodes represent corresponding behaviors at a future time, and each node represents one behavior except the root node.
Specifically, each edge of the search tree in the step (S22) has two weights, i.e., an influence factor FimAnd velocity VAWherein the influence factor FimThe calculation method of (2) is as follows:
formula (1) represents the summation result of the influence factors of all surrounding ordinary vehicles, wherein,
the values 1, 2 and 3 represent the queuing situation, the queue-insertion situation and the crossing situation respectively.
Compared with the prior art, the invention has the following beneficial effects:
(1) the method comprises the steps of firstly obtaining a prediction result of a future track of a surrounding vehicle, constructing a search tree for the prediction result through a behavior search module, and then converting the prediction result into a continuous accurate value through a behavior processing module for outputting. The motion behavior of the vehicle is a continuous value, so that the time is consumed for directly searching the vehicle, and the behavior decision comprises a behavior searching module and a behavior processing module, so that the searched information is dispersed, the data processing time is shortened, the searching process is accelerated, and the behavior decision processing efficiency is improved. And by constructing a search algorithm and a pruning strategy of the search tree, an optimal decision sequence is effectively found, so that the automatic driving vehicle is more intelligent, and efficient automatic driving is achieved.
Drawings
FIG. 1 is a schematic view of the dynamic pruning of the present invention.
FIG. 2 is a schematic diagram of three influencing factors of the present invention.
FIG. 3 is a diagram illustrating the longest overlay path according to the present invention.
Detailed Description
The present invention is further illustrated by the following figures and examples, which include, but are not limited to, the following examples.
Examples
As shown in fig. 1 to 3, a decision method for lane change behavior of an autonomous vehicle based on search technology includes the following steps:
(S1) the autonomous vehicle decides its own driving behavior after predicting the future trajectory of the surrounding vehicle, (S2) in the behavior decision, the lane change behavior of the autonomous vehicle is decided by the behavior search module and the behavior processing module, respectively.
The future trajectory prediction result of the surrounding vehicle comprises nine nodes which are respectively: (a) left lane change acceleration, (b) left lane change deceleration, (c) left lane change holding speed, (d) lane change-free acceleration, (e) lane change-free deceleration, (f) lane change-free holding speed, (g) right lane change acceleration, (h) right lane change deceleration, and (i) right lane change holding speed.
In the step, the search tree is a data structure based on the tree, the depth of the tree is Z, each non-leaf node has nine child nodes (i.e. 3 × 3 discrete autonomous vehicle behaviors), wherein the root node represents the current state, the other child nodes represent corresponding behaviors at a future time, and each node represents one behavior except the root node, and the structure of the search tree is as shown in fig. 1.
Each edge of the search tree has two weights, the influencing factor FimAnd velocity VAWherein the speed calculation method is the longitudinal travel distance/unit time in m/s, and the influence factor FimThe calculation method of (2) is as follows:
formula (1) represents the summation result of the influence factors of all surrounding ordinary vehicles, wherein,
values of 1, 2 and 3 represent queuing conditions respectivelyThe queue-in situation and the crossover situation, three lane-change situations are shown in fig. 2.
In the behavior Search part, a Beam Search algorithm is used for searching, wherein the Beam Search algorithm is a heuristic Search algorithm and uses breadth-first Search to construct a Search tree, so that the memory requirement can be reduced, but the global optimal solution is not necessarily obtained. The Beam Search system establishes a Search tree using a breadth first strategy, sorts nodes according to heuristic cost at each layer of the tree, and then only leaves nodes with a predetermined number (Beam Width-bundling Width), and only the nodes continue to expand at the next layer, and other nodes are cut off.
The method and the device have the advantage that the optimal lane change behavior is quickly found, and the whole search space is represented by using a decision tree structure. Using a dynamic pruning strategy, the manipulation tree can be kept within a manageable size so that searches can be performed efficiently.
The search process has two goals: the first is to maximize the average speed of the autonomous vehicle, which is calculated as the longitudinal travel distance divided by the duration. The second is to minimize the influence on the surrounding ordinary vehicles, and the influence factor can simulate the influence degree of the ordinary vehicles on the automatic driving vehicle. And finally, outputting by a behavior decision function to obtain the optimal behavior of the automatic driving vehicle.
The behavior decision function consists of two submodules of behavior search and behavior processing. In the behavior searching stage, the system searches to obtain an optimal behavior sequence of a discretization version. Specifically, the discretization behavior is discretization of the transverse lane change behavior and the longitudinal motion behavior, and the following three lane change behaviors are considered: left lane changing, right lane changing and no lane changing; and three longitudinal behaviors: accelerate, decelerate, and maintain speed. In the behavior processing stage, the discrete behavior obtained in the first stage is converted and an accurate value is generated, and finally, the transverse and longitudinal behaviors of the complete automatic driving vehicle are obtained.
Based on the behavior search tree, a search algorithm and a pruning strategy are used to effectively make the behavior decision of the optimal lane change. Once the trajectory prediction function section outputs the result of the trajectory prediction of the ordinary vehicle, the system may start searching for the optimum behavior of the autonomous vehicle and decide how to implement the behavior. Since the longitudinal movement distance of the vehicle is a continuous value, the system needs to discretize the longitudinal movement distance first to enable the search process and then convert the longitudinal movement distance into a continuous value in the subsequent behavior processing process.
The flow of the algorithm is as follows:
1) inserting the initial node into the list;
2) the target node (the node satisfying the target) is piled up, if the node is a leaf node, the algorithm is ended;
3) otherwise, expanding the node and stacking the nodes with the bundling width. Then continuing to circulate in the second step;
4) the condition for the algorithm to end is to find the optimal behavior.
The target nodes are those that satisfy the maximization of the average speed of the autonomous vehicle while minimizing other common vehicle impact factors, and the search process is to search in the behavior tree and find those nodes (behaviors) that satisfy the target. For the searched target, the mathematical formula is as follows:
where M represents the optimal discrete behavior of the autonomous vehicle for the behavior search output, this equation (2) aims to find the discrete behavior that maximizes the speed while minimizing the influence factor. The Beam Search algorithm used by the method can cut off some paths (pruning) with low reliability under proper conditions, and find out the optimal solution after pruning.
And finally, in the behavior processing part, the evaluation is directly carried out according to the environmental information acquired by the sensor, the discrete behavior value output by the behavior searching part is serialized and is finely adjusted according to the real-time condition of the external environment, so that the safe driving of the automatic driving vehicle is met.
The above embodiments are only preferred embodiments of the present invention, and are not intended to limit the scope of the present invention, but all changes that can be made by applying the principles of the present invention and performing non-inventive work on the basis of the principles shall fall within the scope of the present invention.
Claims (7)
1. A decision-making method for lane change behavior of an automatic driving vehicle based on a search technology is characterized by comprising the following steps:
(S1) after predicting the future trajectory of the surrounding vehicle, the autonomous vehicle decides its own driving behavior;
(S2) in the behavior decision, making a decision on a lane change behavior of the autonomous vehicle through the behavior search module and the behavior processing module, respectively.
2. The decision-making method for lane-changing behavior of automatic driven vehicle based on search technology as claimed in claim 1, wherein the predicted future trajectory of the surrounding vehicle in said step (S1) includes nine nodes, which are respectively: (a) left lane change acceleration, (b) left lane change deceleration, (c) left lane change holding speed, (d) lane change-free acceleration, (e) lane change-free deceleration, (f) lane change-free holding speed, (g) right lane change acceleration, (h) right lane change deceleration, and (i) right lane change holding speed.
3. A search-technology-based decision-making method for lane-changing behavior of an autonomous vehicle according to claim 2, characterized in that the behavior search module in step (S2) is used to search the system for the optimal behavior of a discrete autonomous vehicle.
4. The decision method for determining lane change behavior of automatic driven vehicle based on search technology as claimed in claim 3, wherein the behavior processing module in step (S2) is used for directly converting discrete behaviors into continuous precise values as output results.
5. The decision-making method for lane-changing behavior of automatic driven vehicle based on search technology as claimed in claim 4, wherein the specific steps of the behavior decision in the step (S2) are as follows:
(S21) the behavior search module acquires a result of predicting a trajectory of a surrounding vehicle;
(S22) constructing a search tree by the acquired trajectory prediction results of the surrounding vehicles;
(S23) performing a behavior search on the constructed search tree;
(S24) converting discrete ones of the execution behaviors into continuous precise values by the behavior processing module;
(S25) the behavior processing module outputs the continuous accurate value as a result.
6. The method of claim 5, wherein the search tree in step (S22) is a tree-based data structure, the tree has a depth of Z, each non-leaf node has nine sub-nodes, wherein the root node represents the current state, the other sub-nodes represent corresponding behaviors at a future time, and each node represents a behavior except the root node.
7. The method for decision making on lane change behavior of autonomous vehicle based on search technology as claimed in claim 6, wherein each side of the search tree in said step (S22) has two weights, i.e. the influence factor FimAnd velocity VAWherein the influence factor FimThe calculation method of (2) is as follows:
formula (1) represents the summation result of the influence factors of all surrounding ordinary vehicles, wherein,
the values 1, 2 and 3 represent the queuing situation, the queue-insertion situation and the crossing situation respectively.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110030986.7A CN112721929B (en) | 2021-01-11 | 2021-01-11 | Decision-making method for lane changing behavior of automatic driving vehicle based on search technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110030986.7A CN112721929B (en) | 2021-01-11 | 2021-01-11 | Decision-making method for lane changing behavior of automatic driving vehicle based on search technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112721929A true CN112721929A (en) | 2021-04-30 |
| CN112721929B CN112721929B (en) | 2022-11-22 |
Family
ID=75590227
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110030986.7A Active CN112721929B (en) | 2021-01-11 | 2021-01-11 | Decision-making method for lane changing behavior of automatic driving vehicle based on search technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112721929B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114019981A (en) * | 2021-11-16 | 2022-02-08 | 北京三快在线科技有限公司 | Trajectory planning method and planning device for unmanned equipment |
Citations (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000039331A (en) * | 1999-07-30 | 2000-02-08 | Mitsubishi Electric Corp | Path-guiding device for vehicle and traffic congestion estimation method used therefor |
| WO2004045891A1 (en) * | 2002-11-21 | 2004-06-03 | Lucas Automotive Gmbh | System for influencing the speed of a motor vehicle |
| CN101089917A (en) * | 2007-06-01 | 2007-12-19 | 清华大学 | Quick identification method for object vehicle lane changing |
| US20100191411A1 (en) * | 2009-01-26 | 2010-07-29 | Bryon Cook | Driver Risk Assessment System and Method Employing Selectively Automatic Event Scoring |
| DE102011005844A1 (en) * | 2011-03-21 | 2012-09-27 | Bayerische Motoren Werke Aktiengesellschaft | Method for automatic controlling of vehicle, involves processing transverse movement of vehicle by decision tree and processing longitudinal movement of vehicle by another decision tree |
| CN105117395A (en) * | 2015-05-11 | 2015-12-02 | 电子科技大学 | Adjacent vehicle query algorithm based on position clue balance binary tree |
| CN105956625A (en) * | 2016-05-11 | 2016-09-21 | 清华大学深圳研究生院 | Method and system for recognizing automobile motion state based on given physical model |
| US9701307B1 (en) * | 2016-04-11 | 2017-07-11 | David E. Newman | Systems and methods for hazard mitigation |
| CN107139921A (en) * | 2017-04-05 | 2017-09-08 | 吉利汽车研究院（宁波）有限公司 | A kind of steering collision-proof method and system for vehicle |
| JP2018100896A (en) * | 2016-12-20 | 2018-06-28 | ヤフー株式会社 | Selection device, selection method, and selection program |
| US20180267557A1 (en) * | 2017-03-17 | 2018-09-20 | Denso International America, Inc. | Vehicle system and vehicle controller for controlling vehicle |
| CN109739246A (en) * | 2019-02-19 | 2019-05-10 | 百度在线网络技术（北京）有限公司 | Decision-making technique, device, equipment and storage medium during a kind of changing Lane |
| CN109791409A (en) * | 2016-09-23 | 2019-05-21 | 苹果公司 | The motion control decision of autonomous vehicle |
| CN109979200A (en) * | 2019-03-29 | 2019-07-05 | 武汉理工大学 | A kind of full-time shared public transportation lane public vehicles lane-change guidance system and method |
| US20190220015A1 (en) * | 2018-01-15 | 2019-07-18 | Uber Technologies, Inc. | Discrete Decision Architecture for Motion Planning System of an Autonomous Vehicle |
| CN110298131A (en) * | 2019-07-05 | 2019-10-01 | 西南交通大学 | Automatic Pilot lane-change decision model method for building up under a kind of mixing driving environment |
| CN110363295A (en) * | 2019-06-28 | 2019-10-22 | 电子科技大学 | A kind of intelligent vehicle multilane lane-change method based on DQN |
| CN110569783A (en) * | 2019-09-05 | 2019-12-13 | 吉林大学 | Method and system for identifying lane changing intention of driver |
| CN110597245A (en) * | 2019-08-12 | 2019-12-20 | 北京交通大学 | Automatic driving track-changing planning method based on quadratic planning and neural network |
| WO2020000192A1 (en) * | 2018-06-26 | 2020-01-02 | Psa Automobiles Sa | Method for providing vehicle trajectory prediction |
| CN110908375A (en) * | 2019-11-14 | 2020-03-24 | 北京三快在线科技有限公司 | Method and device for acquiring lane change decision information, storage medium and vehicle |
| US20200189597A1 (en) * | 2018-12-12 | 2020-06-18 | Visteon Global Technologies, Inc. | Reinforcement learning based approach for sae level-4 automated lane change |
-
2021
- 2021-01-11 CN CN202110030986.7A patent/CN112721929B/en active Active
Patent Citations (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000039331A (en) * | 1999-07-30 | 2000-02-08 | Mitsubishi Electric Corp | Path-guiding device for vehicle and traffic congestion estimation method used therefor |
| WO2004045891A1 (en) * | 2002-11-21 | 2004-06-03 | Lucas Automotive Gmbh | System for influencing the speed of a motor vehicle |
| CN101089917A (en) * | 2007-06-01 | 2007-12-19 | 清华大学 | Quick identification method for object vehicle lane changing |
| US20100191411A1 (en) * | 2009-01-26 | 2010-07-29 | Bryon Cook | Driver Risk Assessment System and Method Employing Selectively Automatic Event Scoring |
| DE102011005844A1 (en) * | 2011-03-21 | 2012-09-27 | Bayerische Motoren Werke Aktiengesellschaft | Method for automatic controlling of vehicle, involves processing transverse movement of vehicle by decision tree and processing longitudinal movement of vehicle by another decision tree |
| CN105117395A (en) * | 2015-05-11 | 2015-12-02 | 电子科技大学 | Adjacent vehicle query algorithm based on position clue balance binary tree |
| US9701307B1 (en) * | 2016-04-11 | 2017-07-11 | David E. Newman | Systems and methods for hazard mitigation |
| CN105956625A (en) * | 2016-05-11 | 2016-09-21 | 清华大学深圳研究生院 | Method and system for recognizing automobile motion state based on given physical model |
| CN109791409A (en) * | 2016-09-23 | 2019-05-21 | 苹果公司 | The motion control decision of autonomous vehicle |
| JP2018100896A (en) * | 2016-12-20 | 2018-06-28 | ヤフー株式会社 | Selection device, selection method, and selection program |
| US20180267557A1 (en) * | 2017-03-17 | 2018-09-20 | Denso International America, Inc. | Vehicle system and vehicle controller for controlling vehicle |
| CN107139921A (en) * | 2017-04-05 | 2017-09-08 | 吉利汽车研究院（宁波）有限公司 | A kind of steering collision-proof method and system for vehicle |
| US20190220015A1 (en) * | 2018-01-15 | 2019-07-18 | Uber Technologies, Inc. | Discrete Decision Architecture for Motion Planning System of an Autonomous Vehicle |
| WO2020000192A1 (en) * | 2018-06-26 | 2020-01-02 | Psa Automobiles Sa | Method for providing vehicle trajectory prediction |
| US20200189597A1 (en) * | 2018-12-12 | 2020-06-18 | Visteon Global Technologies, Inc. | Reinforcement learning based approach for sae level-4 automated lane change |
| CN109739246A (en) * | 2019-02-19 | 2019-05-10 | 百度在线网络技术（北京）有限公司 | Decision-making technique, device, equipment and storage medium during a kind of changing Lane |
| CN109979200A (en) * | 2019-03-29 | 2019-07-05 | 武汉理工大学 | A kind of full-time shared public transportation lane public vehicles lane-change guidance system and method |
| CN110363295A (en) * | 2019-06-28 | 2019-10-22 | 电子科技大学 | A kind of intelligent vehicle multilane lane-change method based on DQN |
| CN110298131A (en) * | 2019-07-05 | 2019-10-01 | 西南交通大学 | Automatic Pilot lane-change decision model method for building up under a kind of mixing driving environment |
| CN110597245A (en) * | 2019-08-12 | 2019-12-20 | 北京交通大学 | Automatic driving track-changing planning method based on quadratic planning and neural network |
| CN110569783A (en) * | 2019-09-05 | 2019-12-13 | 吉林大学 | Method and system for identifying lane changing intention of driver |
| CN110908375A (en) * | 2019-11-14 | 2020-03-24 | 北京三快在线科技有限公司 | Method and device for acquiring lane change decision information, storage medium and vehicle |
Non-Patent Citations (5)
| Title |
|---|
| 余卓平等: "城市工况下基于改进RRT的无人车运动规划算法", 《汽车技术》 * |
| 刘志强等: "基于车联网信息的自动换道方法研究", 《重庆理工大学学报(自然科学)》 * |
| 张金旺等: "基于概率统计的车辆运动轨迹预测方法", 《军事交通学院学报》 * |
| 徐兵等: "采用梯度提升决策树的车辆换道融合决策模型", 《浙江大学学报(工学版)》 * |
| 邓建华等: "基于换道决策机理的多车道元胞自动机模型", 《交通运输***工程与信息》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114019981A (en) * | 2021-11-16 | 2022-02-08 | 北京三快在线科技有限公司 | Trajectory planning method and planning device for unmanned equipment |
| CN114019981B (en) * | 2021-11-16 | 2023-12-22 | 北京三快在线科技有限公司 | Track planning method and device for unmanned equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112721929B (en) | 2022-11-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | Developing a Distributed Consensus‐Based Cooperative Adaptive Cruise Control System for Heterogeneous Vehicles with Predecessor Following Topology | |
| Hou et al. | Modeling mandatory lane changing using Bayes classifier and decision trees | |
| Wei et al. | Autonomous vehicle social behavior for highway entrance ramp management | |
| CN112242059B (en) | Intelligent decision-making method for unmanned vehicle based on motivation and risk assessment | |
| CN105573323A (en) | automatic driving track generation method and apparatus | |
| Barmpounakis et al. | Identifying predictable patterns in the unconventional overtaking decisions of PTW for cooperative ITS | |
| Dasgupta et al. | Merging and splitting maneuver of platoons by means of a novel PID controller | |
| Huang et al. | Design and performance evaluation of mixed manual and automated control traffic | |
| Pierson et al. | Learning risk level set parameters from data sets for safer driving | |
| Wu et al. | Differential variable speed limits control for freeway recurrent bottlenecks via deep reinforcement learning | |
| KR20210118995A (en) | Method and apparatus for generating u-turn path of autonomous vehicle based on deep learning | |
| CN112721929B (en) | Decision-making method for lane changing behavior of automatic driving vehicle based on search technology | |
| Ma et al. | A novel multimode hybrid control method for cooperative driving of an automated vehicle platoon | |
| Wheeler et al. | A probabilistic framework for microscopic traffic propagation | |
| Patil | A Review of Connected and Automated Vehicle Traffic Flow Models for Next-Generation Intelligent Transportation Systems | |
| CN112721948A (en) | Method for realizing lane change scheduling of automatic driving automobile based on prediction and search framework | |
| CN116448134B (en) | Vehicle path planning method and device based on risk field and uncertain analysis | |
| CN115826586A (en) | Path planning method and system fusing global algorithm and local algorithm | |
| CN114117944B (en) | Model updating method, device, equipment and readable storage medium | |
| CN114200917B (en) | Vehicle lane change control method and device | |
| Tang et al. | Consensus-based platoon control for non-lane-discipline connected autonomous vehicles considering time delays | |
| Saraoglu et al. | A Minimax-Based Decision-Making Approach for Safe Maneuver Planning in Automated Driving | |
| Pauca et al. | Communication topologies evaluation for a vehicle merging into a platoon on highway | |
| Zambelli et al. | Two-step asynchronous iterative formation control for heterogeneous vehicles in highway scenarios | |
| Zhao et al. | Behavior Planning of Trains with Trajectory Predictioin |
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 |