CN108549366A - Intelligent automobile road driving mapping experiment method parallel with virtual test - Google Patents
Intelligent automobile road driving mapping experiment method parallel with virtual test Download PDFInfo
- Publication number
- CN108549366A CN108549366A CN201810417326.2A CN201810417326A CN108549366A CN 108549366 A CN108549366 A CN 108549366A CN 201810417326 A CN201810417326 A CN 201810417326A CN 108549366 A CN108549366 A CN 108549366A
- Authority
- CN
- China
- Prior art keywords
- trajectory
- smart car
- planned
- safety
- scene
- 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 19
- 238000002474 experimental method Methods 0.000 title claims abstract description 16
- 238000013507 mapping Methods 0.000 title claims abstract description 14
- 230000008447 perception Effects 0.000 claims abstract description 27
- 238000004088 simulation Methods 0.000 claims abstract description 9
- 230000007613 environmental effect Effects 0.000 claims description 8
- 238000010835 comparative analysis Methods 0.000 claims description 7
- 230000003993 interaction Effects 0.000 claims description 2
- 238000012360 testing method Methods 0.000 abstract description 42
- 238000011156 evaluation Methods 0.000 description 5
- 238000011161 development Methods 0.000 description 3
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000011990 functional testing Methods 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0243—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults model based detection method, e.g. first-principles knowledge model
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M17/00—Testing of vehicles
- G01M17/007—Wheeled or endless-tracked vehicles
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/24—Pc safety
- G05B2219/24065—Real time diagnostics
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Traffic Control Systems (AREA)
Abstract
本发明涉及一种智能汽车道路行驶与虚拟测试平行映射实验方法，旨在提高智能汽车测试的效率及安全性。首先采集驾驶员驾驶车辆的轨迹数据、自动驾驶系统的感知数据与规划轨迹数据（注意此时智能汽车并没有执行该规划轨迹）；然后对实际轨迹和规划轨迹进行对比，搜索两轨迹存在显著差异的场景；之后通过智能汽车的感知信息，对这些场景进行重构，并进行场景回放与仿真预测，分别计算两轨迹的安全性，并对其进行评估。本方法无需使用自动驾驶系统控制车辆，只要智能车在道路行驶（即人类驾驶员在操控汽车），就可进行测试和实验。本方法既可提高测试效率，又可保证测试的安全性。
The invention relates to a parallel mapping experiment method for road driving and virtual testing of smart cars, aiming at improving the efficiency and safety of smart car testing. First collect the trajectory data of the driver’s vehicle, the perception data of the automatic driving system and the planned trajectory data (note that the smart car does not execute the planned trajectory at this time); then compare the actual trajectory with the planned trajectory, and search for significant differences between the two trajectories After that, through the perception information of the smart car, these scenes are reconstructed, and the scene playback and simulation prediction are performed, and the safety of the two trajectories is calculated and evaluated. This method does not need to use the automatic driving system to control the vehicle, as long as the smart car is driving on the road (that is, the human driver is controlling the car), it can be tested and experimented with. The method can not only improve the test efficiency, but also ensure the safety of the test.
Description
技术领域technical field
本发明属于智能汽车测试技术领域，更具体的说，本发明涉及一种在驾驶员驾驶智能汽车在实际道路行自主，驶的过程中，搜索智能汽车规划路径与驾驶员驾驶路径存在差异的场景，并在虚拟环境中构建相同的场景，进行场景回放和仿真测试，实现对智能汽车的行驶安全进行测试和评估的系统。The invention belongs to the technical field of smart car testing, and more specifically, the invention relates to a process of searching for a scene where there is a difference between the planned route of the smart car and the driving route of the driver when the driver drives the smart car autonomously on an actual road , and build the same scene in the virtual environment, and carry out scene playback and simulation test, so as to realize the system of testing and evaluating the driving safety of smart cars.
背景技术Background technique
随着科学技术的发展，基于自动驾驶技术的智能汽车在交通安全的提升和交通拥堵的防治等方面展现出巨大的发展潜力，是汽车行业和交通运行发展的方向。With the development of science and technology, smart cars based on autonomous driving technology have shown great development potential in improving traffic safety and preventing traffic congestion, which is the direction of the development of the automotive industry and traffic operations.
智能汽车的自动驾驶系统由环境感知、规划决策和车辆控制三大模块组成。环境感知模块通过设置在智能车上的传感器，感知车辆周边交通参与者的交通参数，同时识别标志标线、信号控制、天气条件等交通环境信息。规划决策模块通过环境感知模块得到的信息，对车辆的行驶路径进行规划，同时对车辆的加减速等行为进行决策。车辆控制模块根据规划决策模块的路径规划和行为决策，对车辆的行驶方向和速度进行控制。三大模块互相联系，层层递进，最终实现自动驾驶。本发明关注的是对智能汽车规划决策模块的测试。The automatic driving system of a smart car consists of three modules: environment perception, planning decision-making and vehicle control. The environmental perception module perceives the traffic parameters of the traffic participants around the vehicle through the sensors installed on the smart car, and at the same time recognizes traffic environment information such as signs and markings, signal control, and weather conditions. The planning and decision-making module plans the driving path of the vehicle through the information obtained by the environment perception module, and at the same time makes decisions on the acceleration and deceleration of the vehicle. The vehicle control module controls the driving direction and speed of the vehicle according to the path planning and behavior decision of the planning decision-making module. The three modules are interconnected and progress layer by layer, finally realizing automatic driving. The present invention focuses on the testing of the smart car planning and decision-making module.
智能汽车在一般道路上行驶时，需要应对各种复杂的交通环境和天气状况，如混合交通流环境、大雪及雾霾天气等。因此，智能车上路之前必须经过全面严格的测试，否则将有安全风险。当前，对智能汽车驾驶水平的测试主要通过公开道路测试、试验场地测试和虚拟测试进行。公开道路测试具有最真实的测试环境，但是测试场景不可控，需要极长的测试周期且存在安全隐患。兰德公司的报告表明，因为智能车要面对的场景是无限的，而且交通事故是极小概率事件，如果要证明智能汽车的安全性在统计上显著高于人类驾驶，约需要100辆车，一天24小时，以25英里每小时的速度全年无休测试225年。除此之外，公开道路测试具有较高的交通安全风险，受制于法律政策等因素，难以大规模开展。试验场地测试往往是在固定场景下针对单车进行简单交通场景下的功能测试，对智能汽车实际上路可能遇到的复杂环境难以全面真实再现。虚拟测试可以提高测试的效率，同时能够保证测试的安全性，但无法保证测试场景的真实性。When smart cars drive on ordinary roads, they need to deal with various complex traffic environments and weather conditions, such as mixed traffic flow environments, heavy snow and foggy weather, etc. Therefore, smart cars must undergo comprehensive and rigorous testing before they are put on the road, otherwise there will be safety risks. At present, the test of the driving level of smart cars is mainly carried out through public road tests, proving ground tests and virtual tests. The public road test has the most realistic test environment, but the test scene is uncontrollable, requires a very long test cycle and has potential safety hazards. According to the report of the Rand Corporation, because the scenarios that smart cars have to face are infinite, and traffic accidents are extremely low-probability events, if it is to prove that the safety of smart cars is statistically significantly higher than that of human drivers, about 100 vehicles are needed , 24 hours a day, 225 years at 25 mph, year round. In addition, public road testing has high traffic safety risks and is difficult to carry out on a large scale due to factors such as laws and policies. The proving ground test is often a functional test of a single vehicle under a simple traffic scene in a fixed scene, and it is difficult to fully and truly reproduce the complex environment that a smart car may encounter on the road. Virtual testing can improve the efficiency of testing and ensure the safety of testing, but it cannot guarantee the authenticity of testing scenarios.
针对现有测试方法存在的问题，本发明提出了一种智能汽车在有人驾驶的状态下公开道路行驶过程中，与虚拟测试平行映射进行实验评测的新方法，本方法将公开道路测试和虚拟测试两种测试方式整合在一起，通过平行映射实验对智能车的自动驾驶系统进行测试和评估。本发明提出的方法解决了公开道路测试存在的安全隐患和测试效率低的问题，只要配备了环境感知和规划决策系统的智能汽车在道路上行驶，本方法就可以通过平行实验对智能车进行测试。Aiming at the problems existing in the existing testing methods, the present invention proposes a new method for performing experimental evaluation through parallel mapping with virtual testing when smart cars are driving on public roads in the state of manned driving. This method will open road testing and virtual testing The two test methods are integrated to test and evaluate the automatic driving system of the smart car through parallel mapping experiments. The method proposed by the present invention solves the problems of potential safety hazards and low test efficiency in public road testing. As long as the smart car equipped with the environmental perception and planning decision-making system runs on the road, the method can test the smart car through parallel experiments .
发明内容Contents of the invention
本发明要解决的技术问题是通过智能车在公开道路的实际轨迹输出和特定场景下根据其规划决策计算的虚拟轨迹进行对比，识别智能车行驶中的关键场景，并通过关键场景对智能车的自动驾驶系统进行评估。该方法首先采集驾驶员驾驶车辆的轨迹数据、自动驾驶系统的感知数据与规划轨迹数据；然后对比实际轨迹和规划轨迹，搜索两轨迹存在显著差异的场景；最后通过对这些场景进行回放与仿真预测，完成对智能车的安全性评估。The technical problem to be solved in the present invention is to compare the actual track output of the smart car on the public road with the virtual track calculated according to its planning decision in a specific scene, to identify the key scenes in the driving of the smart car, and to analyze the smart car's trajectory through the key scenes. Evaluation of autonomous driving systems. This method first collects the trajectory data of the driver's vehicle, the perception data of the automatic driving system, and the planned trajectory data; then compares the actual trajectory with the planned trajectory, and searches for scenes with significant differences between the two trajectories; finally, through playback and simulation prediction of these scenarios , to complete the safety assessment of the smart car.
智能汽车的自动驾驶系统一般包括环境感知、决策规划和控制执行三个模块。本方法的基本思想是，智能汽车在公开道路上由人驾驶时，环境感知和规划决策模块仍然工作，但控制执行模块不工作，这样就可以得到规划决策的短期规划轨迹，由于没有交由执行器执行，智能汽车不需要按照这个轨迹行驶，因此不会对真实世界的交通产生影响，保证了测试安全。同时，将环境感知、规划决策和控制执行三个模块映射到虚拟世界中，在虚拟世界中执行规划轨迹，并对虚拟世界的动态产生影响，在虚拟世界中形成闭环运行，对智能汽车进行测试。因此本方法称之为道路行驶与虚拟测试平行映射实验方法，其核心思想如附图3所示。The automatic driving system of a smart car generally includes three modules: environment perception, decision planning and control execution. The basic idea of this method is that when the smart car is driven by a human on the open road, the environmental perception and planning decision-making modules still work, but the control execution module does not work, so that the short-term planning trajectory of the planning decision can be obtained, because it is not handed over to the execution The smart car does not need to follow this trajectory, so it will not affect the traffic in the real world, ensuring the safety of the test. At the same time, the three modules of environment perception, planning decision-making and control execution are mapped to the virtual world, and the planned trajectory is executed in the virtual world, and the dynamics of the virtual world are affected, forming a closed-loop operation in the virtual world, and testing the smart car . Therefore, this method is called road driving and virtual test parallel mapping experiment method, and its core idea is shown in Figure 3.
本发明提出的一种智能汽车道路行驶与虚拟测试平行映射实验方法，具体步骤如下：A kind of smart car road running and virtual test parallel mapping experimental method proposed by the present invention, the specific steps are as follows:
（1）采集智能汽车的自动驾驶系统给出的行驶轨迹、感知信息及规划行驶轨迹：(1) Collect the driving trajectory, perception information and planned driving trajectory given by the automatic driving system of the smart car:
采集驾驶员在公开道路上驾驶配备了自动驾驶系统给出的行驶轨迹，所述自动驾驶系统给出的行驶轨迹包括具有时间戳的车辆位置坐标、速度和转向角等信息；采集智能汽车的感知信息，所述感知信息包括周围车流信息和环境信息等；采集智能汽车通过感知模块和规划决策模块给出的规划行驶轨迹，所述规划行驶轨迹包括短期规划的车辆位置坐标、速度和转向角等信息；Collect the driving trajectory given by the driver on the open road equipped with an automatic driving system, the driving trajectory given by the automatic driving system includes information such as vehicle position coordinates, speed, and steering angle with time stamps; collect the perception of smart cars Information, the perception information includes surrounding traffic flow information and environmental information, etc.; collect the planned driving trajectory given by the smart car through the perception module and planning decision-making module, and the planned driving trajectory includes short-term planned vehicle position coordinates, speed and steering angle, etc. information;
（2）对比智能汽车的自动驾驶系统给出的行驶轨迹和规划行驶轨迹，搜索两条轨迹存在显著差异的场景：(2) Compare the driving trajectory given by the automatic driving system of the smart car with the planned driving trajectory, and search for scenarios where there are significant differences between the two trajectories:
基于采集的智能汽车的规划行驶轨迹信息和自动驾驶系统给出的行驶轨迹进行对比分析，筛选出两条轨迹存在明显差异的场景；在某时刻t存在以下任意一种情况时，认为两条轨迹存在显著差异：Based on the comparative analysis of the collected planned driving trajectory information of the smart car and the driving trajectory given by the automatic driving system, the scenes with obvious differences between the two trajectories are screened out; when any of the following situations exists at a certain time t , the two trajectories are considered There are notable differences:
a)两轨迹车辆的纵向距离d大于阈值，即 ;a) The longitudinal distance d between two track vehicles is greater than the threshold ,Right now ;
b)两轨迹车辆的横向距离s大于阈值，即 ;b) The lateral distance s between the two track vehicles is greater than the threshold ,Right now ;
c)两轨迹车辆的速度差大于阈值，即 ;c) The speed difference between the two track vehicles greater than the threshold ,Right now ;
（3）场景回放和仿真预测：(3) Scene playback and simulation prediction:
对于步骤（2）中智能汽车的规划行驶轨迹信息和自动驾驶系统给出的行驶轨迹存在显著差异的场景，进行场景重构；即由于智能汽车的环境感知模块有一定的感知范围，同时也可能存在感知盲区，为尽可能保证重构场景与现实场景保持一致，对在t时刻存在显著差异的场景，通过车辆的感知模块在一个时间段到内的感知到的环境信息，对车辆周围的场景进行重构；For scenarios where there is a significant difference between the planned driving trajectory information of the smart car and the driving trajectory given by the automatic driving system in step (2), scene reconstruction is performed; There is a perception blind spot. In order to ensure that the reconstructed scene is consistent with the real scene as much as possible, for the scene with significant difference at time t , the perception module of the vehicle is used in a period of time. arrive Reconstruct the scene around the vehicle based on the perceived environmental information in the vehicle;
场景重构完成后，对时刻到t时刻的时间段内，智能汽车的实际行驶轨迹和规划轨迹进行回放，检验两条轨迹是否出现与障碍物的碰撞事件，并计算智能汽车行驶的安全指标，同时，通过交通仿真软件，对t到时段内，智能汽车及其他交通参与者的行为进行仿真；基于交通仿真软件生成的交通环境信息，通过智能汽车的自动驾驶系统生成规划行驶轨迹，并形成自动驾驶系统规划的轨迹与交通仿真软件中交通流的实时闭环交互；然后，计算t到时段内，智能汽车实际行驶轨迹与规划行驶轨迹的安全指标。其中，，；After the scene reconstruction is completed, the During the time period from time to time t , the actual driving trajectory and the planned trajectory of the smart car are played back to check whether the two trajectories collide with obstacles, and calculate the safety indicators of the smart car. At the same time, through the traffic simulation software, to t to During the time period, the behavior of smart cars and other traffic participants is simulated; based on the traffic environment information generated by the traffic simulation software, the planned driving trajectory is generated through the automatic driving system of the smart car, and the trajectory planned by the automatic driving system is formed. Real-time closed-loop interaction of traffic flow; then, calculate t to During the time period, the safety indicators of the actual driving trajectory and the planned driving trajectory of the smart car. in, , ;
（4）智能汽车自动驾驶系统安全评估：(4) Safety assessment of smart car automatic driving system:
基于智能汽车实际行驶轨迹与规划轨迹存在显著差异的场景，对于智能汽车自动驾驶系统的安全评估分两个部分：一是对回放轨迹的对比分析，即到t时段内的安全性分析；二是对差异出现后，继续行驶一段时间的轨迹对比分析，即t到时段内的安全性分析。安全性分析不仅分析本车的安全性，还要分析对后面车队的影响。Based on the scenario where there is a significant difference between the actual driving trajectory and the planned trajectory of the smart car, the safety assessment of the smart car automatic driving system is divided into two parts: one is the comparative analysis of the playback trajectory, namely The safety analysis within the time period from t to t ; the second is the comparative analysis of the trajectory of continuing to drive for a period of time after the difference occurs, that is, t to t Security analysis over time. Safety analysis not only analyzes the safety of the vehicle, but also analyzes the impact on the following team.
本发明中，所述智能汽车行驶的安全指标为TCC。In the present invention, the safety index of the smart car running is TCC.
本发明中，所述交通仿真软件为VISSIM或TESS NG中任一种。In the present invention, the traffic simulation software is any one of VISSIM or TESS NG.
与现有技术相比，本发明的技术方案具有以下有益效果：Compared with the prior art, the technical solution of the present invention has the following beneficial effects:
1.本发明提出的智能汽车道路行驶与虚拟测试平行映射实验方法，将公开道路测试和虚拟测试两种测试方式整合在一起，既提高了测试效率，又保障了测试的安全。在本实验方法中，智能汽车在实际道路行驶时，并非由自动驾驶系统控制，而是由驾驶员控制，保障了测试的安全性，也不存在违反法律法规的问题。同时，只要配备了自动驾驶系统的智能汽车在实际道路行驶，就能为本实验源源不断地提供数据，与受时间地点和法律法规限制的公开道路测试相比，极大地提高了测试效率。1. The parallel mapping experiment method of intelligent vehicle road driving and virtual test proposed by the present invention integrates the two test modes of public road test and virtual test, which not only improves the test efficiency, but also ensures the safety of the test. In this experimental method, when the smart car is driving on the actual road, it is not controlled by the automatic driving system, but by the driver, which ensures the safety of the test and does not violate laws and regulations. At the same time, as long as the smart car equipped with the automatic driving system is driving on the actual road, it can continuously provide data for this experiment, which greatly improves the test efficiency compared with the public road test limited by time, place and laws and regulations.
2.本发明提出的智能汽车道路行驶与虚拟测试平行映射实验方法，对于实际轨迹与规划轨迹具有显著差异的关键场景，不仅通过智能汽车感知数据对场景进行回放，对比实际路径和智能汽车规划路径的安全性，而且通过仿真软件，推演差异轨迹出现后一段时间内智能汽车和周围交通流的演变，分析实际轨迹与规划轨迹未来一定时段的安全性演化态势，建立基于场景回放和未来状态推演的安全评价方法，使得对智能汽车自动驾驶系统安全性的评价更加全面可靠。2. The parallel mapping experimental method of smart car road driving and virtual test proposed by the present invention, for the key scene with significant difference between the actual trajectory and the planned trajectory, not only replays the scene through the smart car perception data, but also compares the actual path with the smart car planning path And through simulation software, deduce the evolution of smart cars and surrounding traffic flow for a period of time after the emergence of different trajectories, analyze the security evolution situation of actual trajectories and planned trajectories for a certain period of time in the future, and establish a model based on scene playback and future state deduction The safety evaluation method makes the evaluation of the safety of the intelligent vehicle automatic driving system more comprehensive and reliable.
附图说明Description of drawings
图1 本发明提出的智能汽车道路行驶与虚拟测试平行映射实验方法流程图；Fig. 1 is the flow chart of the intelligent vehicle road running and virtual test parallel mapping experimental method proposed by the present invention;
图2 本发明步骤2中各判断指标示意图；Fig. 2 schematic diagram of each judgment index in step 2 of the present invention;
图3 平行映射实验方法的基本思路图；Figure 3 The basic idea of the parallel mapping experiment method;
图4 实施例1中，使用VISSIM对场景进行仿真预测的界面；Fig. 4 In embodiment 1, the interface of using VISSIM to simulate and predict the scene;
图5 实施例1中的典型场景示例。Figure 5 is an example of a typical scenario in Embodiment 1.
具体实施方式Detailed ways
下面结合附图和实施例，对本发明的技术方案作详细说明。本实施例在以本发明技术方案为前提下进行实施，但本发明的保护范围不限于下述的实施例。The technical solutions of the present invention will be described in detail below in conjunction with the accompanying drawings and embodiments. This embodiment is implemented on the premise of the technical solution of the present invention, but the protection scope of the present invention is not limited to the following embodiments.
实施例1Example 1
本实施例的实施地点为上海市，通过多位驾驶员驾驶装有自动驾驶的智能汽车在上海市实际道路行驶获得的数据，对比实际轨迹并与规划轨迹，搜索出轨迹具有显著差异的场景，进行平行映射实验评估智能车安全性，包括以下详细步骤：The implementation location of this embodiment is Shanghai. Through the data obtained by multiple drivers driving smart cars equipped with automatic driving on the actual roads in Shanghai, the actual trajectory is compared with the planned trajectory, and the scene with a significant difference in trajectory is found. A parallel mapping experiment was conducted to evaluate the safety of the smart car, including the following detailed steps:
（1）采集车辆的行驶轨迹、感知信息及规划行驶轨迹：(1) Collect the vehicle's driving trajectory, perception information and planning driving trajectory:
采集驾驶员在上海市实际道路驾驶智能汽车的行驶轨迹，包括具有时间戳的车辆位置坐标、速度、转向角等信息。采集智能汽车感知信息，包括周围障碍物位置信息、车道信息等。采集智能汽车通过感知模块和规划决策模块给出的规划行驶轨迹，包括规划的车辆位置坐标、速度、转向角等信息。Collect the driving trajectory of the driver driving the smart car on the actual road in Shanghai, including the vehicle position coordinates, speed, steering angle and other information with time stamps. Collect smart car perception information, including location information of surrounding obstacles, lane information, etc. Collect the planned driving trajectory given by the smart car through the perception module and planning decision-making module, including the planned vehicle position coordinates, speed, steering angle and other information.
（2）对比车辆行驶轨迹和规划轨迹，搜索两个轨迹存在显著差异的场景：(2) Compare the vehicle trajectory with the planned trajectory, and search for scenarios where there are significant differences between the two trajectories:
基于采集的车辆行驶轨迹信息和自动驾驶系统给出的规划行驶轨迹进行对比分析，筛选出两轨迹存在明显差异的场景。在某时刻t存在以下任意一种情况时，认为两轨迹存在显著差异：Based on the comparative analysis of the collected vehicle trajectory information and the planned trajectory given by the automatic driving system, the scenes with obvious differences between the two trajectories are screened out. When any of the following conditions exists at a certain time t , it is considered that there is a significant difference between the two trajectories:
a)两轨迹车辆的纵向距离d大于阈值，即 ;a) The longitudinal distance d between two track vehicles is greater than the threshold ,Right now ;
b)两轨迹车辆的横向距离s大于阈值，即 ;b) The lateral distance s between the two track vehicles is greater than the threshold ,Right now ;
c)两轨迹车辆的速度差大于阈值，即 ;c) The speed difference between the two track vehicles greater than the threshold ,Right now ;
（3）场景回放和仿真预测：(3) Scene playback and simulation prediction:
对于所有搜索出的实际轨迹与规划轨迹存在显著差异的场景，进行场景重构。对在t时刻存在显著差异的场景，通过车辆的感知模块在一个时间段到内的感知到的环境信息，对车辆周围的场景进行重构，得到每一时刻该场景中每个车辆的位置和速度信息及固定障碍物的位置信息。For all the scenes where there is a significant difference between the searched actual trajectory and the planned trajectory, scene reconstruction is performed. For scenes with significant differences at time t , through the perception module of the vehicle in a period of time arrive Based on the perceived environmental information in the vehicle, the scene around the vehicle is reconstructed, and the position and speed information of each vehicle in the scene at each moment and the position information of fixed obstacles are obtained.
场景重构完成后，进行场景回放。对时刻到t时刻的时间段内，车辆的实际行驶轨迹和规划轨迹进行回放。在回放中，首先检验两条轨迹是否出现了与其他车辆或障碍物的碰撞事件；然后并计算两轨迹的智能车行驶过程中，每个时刻的TTC指标，得出回放阶段的最小TTC指标。若出现碰撞事件，。After the scene reconstruction is completed, perform scene playback. right During the time period from time t to time t , the actual driving trajectory and the planned trajectory of the vehicle are played back. In the playback, first check whether there is a collision event with other vehicles or obstacles in the two trajectories; then calculate the TTC index at each moment during the driving process of the smart car on the two trajectories, and obtain the minimum TTC index in the playback stage . In the event of a collision, .
然后，通过交通仿真软件对场景的演变进行预测。使用交通仿真软件VISSIM，以两轨迹出现显著差异的时刻t时刻场景的状态作为初始状态，对t到时段内，智能汽车及其他交通参与者的行为进行仿真预测。计算t到时段内，车辆实际行驶轨迹与规划行驶轨迹每个时刻的TTC指标，得出预测阶段的最小TTC指标。若出现碰撞事件，。此外，还要计算差异行为对整个交通流的影响，因此，还要计算整个车队中每辆车每个时刻的TTC，取最小值最为车队最小TTC指标。Then, the evolution of the scene is predicted by traffic simulation software. Using the traffic simulation software VISSIM, the state of the scene at time t when there is a significant difference between the two trajectories is taken as the initial state . During the time period, the behavior of smart cars and other traffic participants is simulated and predicted. Calculate t to In the time period, the TTC index of the actual driving trajectory and the planned driving trajectory of the vehicle at each moment can be obtained to obtain the minimum TTC index in the prediction stage . In the event of a collision, . In addition, it is also necessary to calculate the impact of differential behavior on the entire traffic flow. Therefore, it is also necessary to calculate the TTC of each vehicle in the entire fleet at each moment, and take the minimum value as the minimum TTC index of the fleet .
（4）智能汽车自动驾驶系统安全评估：(4) Safety assessment of smart car automatic driving system:
通过场景回放和仿真预测得到的安全指标，从回放、预测两个层面，评估智能汽车的自动驾驶系统的安全性能：Through the safety indicators obtained by scene playback and simulation prediction, the safety performance of the automatic driving system of smart cars is evaluated from two levels of playback and prediction:
a)若回放阶段实际轨迹的最小TTC大于规划轨迹的最小TTC，即，说明此场景中自动驾驶系统的安全性低于人类驾驶；反之，若，说明此场景中自动驾驶系统的安全性高于人类驾驶；a) If the minimum TTC of the actual trajectory in the playback phase is greater than the minimum TTC of the planned trajectory, that is , indicating that the safety of the automatic driving system in this scenario is lower than that of human driving; on the contrary, if , indicating that the safety of the automatic driving system in this scenario is higher than that of human driving;
b)若回放场景中两轨迹安全性差别不大，且仿真预测阶段实际轨迹的最小TTC大于规划轨迹的最小TTC，即，说明此场景中自动驾驶系统的安全性低于人类驾驶；反之，若，说明此场景中自动驾驶系统的安全性高于人类驾驶；b) If there is little difference in security between the two trajectories in the playback scene, and the minimum TTC of the actual trajectory in the simulation prediction stage is greater than the minimum TTC of the planned trajectory, that is , indicating that the safety of the automatic driving system in this scenario is lower than that of human driving; on the contrary, if , indicating that the safety of the automatic driving system in this scenario is higher than that of human driving;
c)若对于单个车辆两轨迹安全性差别不大，且仿真预测阶段实际轨迹的车队最小TTC大于规划轨迹的车队最小TTC，即，说明此场景中自动驾驶系统的安全性低于人类驾驶；反之，若，说明此场景中自动驾驶系统的安全性高于人类驾驶。c) If there is little difference in safety between the two trajectories for a single vehicle, and the minimum TTC of the fleet of the actual trajectory in the simulation prediction stage is greater than the minimum TTC of the fleet of the planned trajectory, that is , indicating that the safety of the automatic driving system in this scenario is lower than that of human driving; on the contrary, if , indicating that the safety of the automatic driving system in this scenario is higher than that of human driving.
（5）典型场景示例：(5) Examples of typical scenarios:
如附图5中所示场景，测试车辆的实际轨迹与规划轨迹在t时刻出现显著差异，因此首先对该场景进行重构，然后进行回放和预测评估。As shown in Figure 5, there is a significant difference between the actual trajectory of the test vehicle and the planned trajectory at time t , so the scene is reconstructed first, and then playback and prediction evaluation are performed.
通过回看轨迹可以看出，测试车辆右前方的车辆换道插入测试车辆前方，由于测试车驾驶员根据右前方车辆的行为预判到了即将发生的换道行为，因此进行了换道操作，而自动驾驶系统没有预判到插入行为，因此做出的规划是继续在本车道行驶。通过回看可以计算实际轨迹和规划轨迹的TTC指标，此阶段，说明此阶段自动驾驶的安全性低于人类驾驶。Looking back at the trajectory, it can be seen that the vehicle in front of the test vehicle changed lanes and inserted in front of the test vehicle. Because the driver of the test vehicle predicted the upcoming lane change behavior based on the behavior of the vehicle in front of the right, he performed the lane change operation. The automatic driving system did not predict the cut-in behavior, so the plan made was to continue driving in this lane. By looking back at the TTC indicators that can calculate the actual trajectory and the planned trajectory, at this stage , indicating that the safety of autonomous driving at this stage is lower than that of human driving.
通过预测轨迹可以看出，在两条轨迹出现显著差异之后，实际轨迹保持安全行驶，而预测轨迹中，测试车辆首先由于前车插入，进行急刹操作，并差点追尾前方车辆，TTC小于安全阈值；随后测试车辆由于急刹操作，被测试车后方车辆追尾，发生事故。此阶段且，说明自动驾驶的安全性低于人类驾驶。It can be seen from the predicted trajectory that after the significant difference between the two trajectories, the actual trajectory remains safe to drive, while in the predicted trajectory, the test vehicle first performs a sudden brake operation due to the insertion of the vehicle in front, and almost rear-ends the vehicle in front, and the TTC is less than the safety threshold ; Subsequently, the test vehicle was rear-ended by the vehicle behind the test vehicle due to the sudden brake operation, and an accident occurred. this stage and , indicating that autonomous driving is less safe than human driving.
Claims (3)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810417326.2A CN108549366B (en) | 2018-05-04 | 2018-05-04 | Parallel mapping experimental method for intelligent vehicle road driving and virtual test |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810417326.2A CN108549366B (en) | 2018-05-04 | 2018-05-04 | Parallel mapping experimental method for intelligent vehicle road driving and virtual test |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108549366A true CN108549366A (en) | 2018-09-18 |
| CN108549366B CN108549366B (en) | 2020-11-10 |
Family
ID=63513206
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810417326.2A Active CN108549366B (en) | 2018-05-04 | 2018-05-04 | Parallel mapping experimental method for intelligent vehicle road driving and virtual test |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108549366B (en) |
Cited By (43)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109255341A (en) * | 2018-10-30 | 2019-01-22 | 百度在线网络技术（北京）有限公司 | Extracting method, device, equipment and the medium of barrier perception wrong data |
| CN109358526A (en) * | 2018-10-15 | 2019-02-19 | 清华大学苏州汽车研究院（吴江） | Software-in-the-loop testing method for automatic driving tracking algorithm based on simulation |
| CN109375630A (en) * | 2018-12-06 | 2019-02-22 | 上海智梯信息科技有限公司 | A kind of intelligent driving test track seeking system and method |
| CN109520744A (en) * | 2018-11-12 | 2019-03-26 | 百度在线网络技术（北京）有限公司 | The driving performance test method and device of automatic driving vehicle |
| CN109557904A (en) * | 2018-12-06 | 2019-04-02 | 百度在线网络技术（北京）有限公司 | A kind of test method, device, equipment and medium |
| CN109598066A (en) * | 2018-12-05 | 2019-04-09 | 百度在线网络技术（北京）有限公司 | Effect evaluation method, device, equipment and the storage medium of prediction module |
| CN109765803A (en) * | 2019-01-24 | 2019-05-17 | 同济大学 | A hardware simulation test system and method for self-driving car multi-ICU co-space-time |
| CN109886474A (en) * | 2019-01-24 | 2019-06-14 | 同济大学 | A kind of closed test field planing method towards automatic driving vehicle test |
| CN109885929A (en) * | 2019-02-19 | 2019-06-14 | 百度在线网络技术（北京）有限公司 | Automatic Pilot decision rule data reproducing method and device |
| CN109933856A (en) * | 2019-02-19 | 2019-06-25 | 百度在线网络技术（北京）有限公司 | Automatic Pilot decision rule data reproducing method and device |
| CN110288160A (en) * | 2019-06-27 | 2019-09-27 | 北京华如科技股份有限公司 | A kind of situation dynamic prediction method based on parallel simulation |
| CN110595798A (en) * | 2019-09-19 | 2019-12-20 | 北京百度网讯科技有限公司 | Test method and device |
| CN110758403A (en) * | 2019-10-30 | 2020-02-07 | 北京百度网讯科技有限公司 | Control method, device, equipment and storage medium for automatic driving vehicle |
| CN110781578A (en) * | 2019-09-23 | 2020-02-11 | 同济大学 | A test and evaluation method of intelligent networked vehicle algorithm based on accident scene |
| CN110782125A (en) * | 2019-09-23 | 2020-02-11 | 同济大学 | Road safety risk degree evaluation method for automatically driving automobile |
| CN111090915A (en) * | 2018-10-19 | 2020-05-01 | 百度在线网络技术（北京）有限公司 | Automatic driving simulation method, device and storage medium |
| CN111123731A (en) * | 2018-10-31 | 2020-05-08 | 百度在线网络技术（北京）有限公司 | Method, device, storage medium and terminal equipment for simulating automatic driving vehicle |
| CN111179585A (en) * | 2018-11-09 | 2020-05-19 | 上海汽车集团股份有限公司 | Site testing method and device for automatic driving vehicle |
| CN111367283A (en) * | 2020-03-11 | 2020-07-03 | 郴州职业技术学院 | Unmanned vehicle obstacle avoidance method and system based on obstacle configuration reconstruction |
| CN111462475A (en) * | 2019-01-18 | 2020-07-28 | 上汽通用汽车有限公司 | Real-time interactive dynamic traffic flow test system |
| CN111551382A (en) * | 2020-05-12 | 2020-08-18 | 中国科学院心理研究所 | A system and method for testing driver's vehicle distance control ability |
| CN111767651A (en) * | 2020-06-28 | 2020-10-13 | 北京百度网讯科技有限公司 | Index prediction model construction method, index prediction method and device |
| CN111879319A (en) * | 2020-06-29 | 2020-11-03 | 中国科学院合肥物质科学研究院 | Indoor testing method and system for ground unmanned platform and computer equipment |
| CN111914412A (en) * | 2020-07-21 | 2020-11-10 | 同济大学 | A fault injector-based automatic driving performance limitation testing system and method |
| CN112286206A (en) * | 2020-11-17 | 2021-01-29 | 苏州智加科技有限公司 | Automatic driving simulation method, system, equipment, readable storage medium and platform |
| CN112527633A (en) * | 2020-11-20 | 2021-03-19 | 北京赛目科技有限公司 | Automatic driving simulation test method and device for scene library |
| CN112581633A (en) * | 2020-12-24 | 2021-03-30 | 北京亮道智能汽车技术有限公司 | In-loop virtual simulation test method and system for vehicle with automatic driving function |
| CN112816954A (en) * | 2021-02-09 | 2021-05-18 | 中国信息通信研究院 | Road side perception system evaluation method and system based on truth value |
| CN112926135A (en) * | 2021-03-02 | 2021-06-08 | 北京百度网讯科技有限公司 | Scene information determination method, apparatus, device, storage medium, and program product |
| CN113065685A (en) * | 2021-03-01 | 2021-07-02 | 沃行科技(南京)有限公司 | High-precision map traffic rule model based on automatic driving application scene and implementation method thereof |
| CN113112643A (en) * | 2020-01-13 | 2021-07-13 | 北京地平线机器人技术研发有限公司 | Evaluation method and device for predicted trajectory, electronic device and storage medium |
| CN113610166A (en) * | 2021-08-10 | 2021-11-05 | 吉林大学 | Method for establishing test scene library for intelligent vehicle |
| CN113779864A (en) * | 2021-08-06 | 2021-12-10 | 同济大学 | Method and device for constructing operational design area for autonomous vehicles |
| CN113935638A (en) * | 2021-10-20 | 2022-01-14 | 北京轻舟智航科技有限公司 | Trajectory decision evaluation method based on plane topology analysis |
| CN113949996A (en) * | 2021-10-11 | 2022-01-18 | 重庆大学 | Data processing method and system for collection and playback of vehicle-road collaborative test scene |
| CN113962110A (en) * | 2021-11-30 | 2022-01-21 | 广州文远知行科技有限公司 | Automatic driving track evaluation method, device, equipment and storage medium |
| WO2022027304A1 (en) * | 2020-08-05 | 2022-02-10 | 华为技术有限公司 | Testing method and apparatus for autonomous vehicle |
| WO2022105395A1 (en) * | 2020-11-17 | 2022-05-27 | Suzhou Zhijia Science & Technologies Co., Ltd. | Data processing method, apparatus, and system, computer device, and non-transitory storage medium |
| CN114563196A (en) * | 2022-02-22 | 2022-05-31 | 上清童子(北京)投资顾问有限公司 | Method for checking usability and reliability of automatic driving automobile |
| CN114627640A (en) * | 2022-01-21 | 2022-06-14 | 中国科学院深圳先进技术研究院 | Dynamic evolution method of intelligent networked automobile driving strategy |
| CN114822042A (en) * | 2022-06-28 | 2022-07-29 | 深圳市华耀商品检验有限公司 | Information security test management system and method for vehicle-mounted terminal detection |
| CN114838948A (en) * | 2022-03-04 | 2022-08-02 | 湖北国际物流机场有限公司 | Automatic lane merging test method and system for airport automatic driving guide vehicle |
| CN114930425A (en) * | 2020-02-28 | 2022-08-19 | 国际商业机器公司 | Autonomous driving assessment using data analysis |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8199656B1 (en) * | 2004-03-03 | 2012-06-12 | At&T Intellectual Property Ii, Lp | System and method for testing automated provisioning and maintenance of operations support systems |
| CN102610092A (en) * | 2012-03-23 | 2012-07-25 | 天津大学 | Urban road speed predication method based on RBF (radial basis function) neural network |
| CN105788400A (en) * | 2016-03-07 | 2016-07-20 | 兵器工业卫生研究所 | Human-machine-environment comprehensive simulating test system for special vehicle |
| CN106053091A (en) * | 2016-02-02 | 2016-10-26 | 北京理工大学 | Power cabin comprehensive testing device and testing method based on virtual scene |
| CN106991811A (en) * | 2017-05-03 | 2017-07-28 | 同济大学 | Expressway exit ring road upstream trackside road information Optimization Design based on drive simulation experiment porch |
| CN107315407A (en) * | 2017-08-31 | 2017-11-03 | 中国第汽车股份有限公司 | A kind of automotive motor controller emulation test system |
| CN107403038A (en) * | 2017-07-05 | 2017-11-28 | 同济大学 | A kind of virtual method for rapidly testing of intelligent automobile |
| CN107506830A (en) * | 2017-06-20 | 2017-12-22 | 同济大学 | Towards the artificial intelligence training platform of intelligent automobile programmed decision-making module |
-
2018
- 2018-05-04 CN CN201810417326.2A patent/CN108549366B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8199656B1 (en) * | 2004-03-03 | 2012-06-12 | At&T Intellectual Property Ii, Lp | System and method for testing automated provisioning and maintenance of operations support systems |
| CN102610092A (en) * | 2012-03-23 | 2012-07-25 | 天津大学 | Urban road speed predication method based on RBF (radial basis function) neural network |
| CN106053091A (en) * | 2016-02-02 | 2016-10-26 | 北京理工大学 | Power cabin comprehensive testing device and testing method based on virtual scene |
| CN105788400A (en) * | 2016-03-07 | 2016-07-20 | 兵器工业卫生研究所 | Human-machine-environment comprehensive simulating test system for special vehicle |
| CN106991811A (en) * | 2017-05-03 | 2017-07-28 | 同济大学 | Expressway exit ring road upstream trackside road information Optimization Design based on drive simulation experiment porch |
| CN107506830A (en) * | 2017-06-20 | 2017-12-22 | 同济大学 | Towards the artificial intelligence training platform of intelligent automobile programmed decision-making module |
| CN107403038A (en) * | 2017-07-05 | 2017-11-28 | 同济大学 | A kind of virtual method for rapidly testing of intelligent automobile |
| CN107315407A (en) * | 2017-08-31 | 2017-11-03 | 中国第汽车股份有限公司 | A kind of automotive motor controller emulation test system |
Cited By (72)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109358526A (en) * | 2018-10-15 | 2019-02-19 | 清华大学苏州汽车研究院（吴江） | Software-in-the-loop testing method for automatic driving tracking algorithm based on simulation |
| CN109358526B (en) * | 2018-10-15 | 2021-10-08 | 清华大学苏州汽车研究院（吴江） | Software-in-the-loop testing method for automatic driving tracking algorithm based on simulation |
| CN111090915A (en) * | 2018-10-19 | 2020-05-01 | 百度在线网络技术（北京）有限公司 | Automatic driving simulation method, device and storage medium |
| CN111090915B (en) * | 2018-10-19 | 2023-12-15 | 百度在线网络技术（北京）有限公司 | Automatic driving simulation method, device and storage medium |
| CN109255341A (en) * | 2018-10-30 | 2019-01-22 | 百度在线网络技术（北京）有限公司 | Extracting method, device, equipment and the medium of barrier perception wrong data |
| CN109255341B (en) * | 2018-10-30 | 2021-08-10 | 百度在线网络技术（北京）有限公司 | Method, device, equipment and medium for extracting obstacle perception error data |
| CN111123731B (en) * | 2018-10-31 | 2022-12-02 | 阿波罗智能技术(北京)有限公司 | Method, device, storage medium and terminal equipment for simulating automatic driving vehicle |
| CN111123731A (en) * | 2018-10-31 | 2020-05-08 | 百度在线网络技术（北京）有限公司 | Method, device, storage medium and terminal equipment for simulating automatic driving vehicle |
| CN111179585A (en) * | 2018-11-09 | 2020-05-19 | 上海汽车集团股份有限公司 | Site testing method and device for automatic driving vehicle |
| CN109520744A (en) * | 2018-11-12 | 2019-03-26 | 百度在线网络技术（北京）有限公司 | The driving performance test method and device of automatic driving vehicle |
| CN109520744B (en) * | 2018-11-12 | 2020-04-21 | 百度在线网络技术（北京）有限公司 | Driving performance testing method and device for automatic driving vehicle |
| CN109598066A (en) * | 2018-12-05 | 2019-04-09 | 百度在线网络技术（北京）有限公司 | Effect evaluation method, device, equipment and the storage medium of prediction module |
| CN109598066B (en) * | 2018-12-05 | 2023-08-08 | 百度在线网络技术（北京）有限公司 | Effect evaluation method, apparatus, device and storage medium for prediction module |
| CN109557904A (en) * | 2018-12-06 | 2019-04-02 | 百度在线网络技术（北京）有限公司 | A kind of test method, device, equipment and medium |
| CN109557904B (en) * | 2018-12-06 | 2020-07-10 | 百度在线网络技术（北京）有限公司 | Test method, device, equipment and medium |
| CN109375630A (en) * | 2018-12-06 | 2019-02-22 | 上海智梯信息科技有限公司 | A kind of intelligent driving test track seeking system and method |
| CN111462475B (en) * | 2019-01-18 | 2021-12-10 | 上汽通用汽车有限公司 | Real-time interactive dynamic traffic flow test system |
| CN111462475A (en) * | 2019-01-18 | 2020-07-28 | 上汽通用汽车有限公司 | Real-time interactive dynamic traffic flow test system |
| CN109886474B (en) * | 2019-01-24 | 2023-02-10 | 同济大学 | Closed test field planning method for automatic driving vehicle test |
| CN109765803A (en) * | 2019-01-24 | 2019-05-17 | 同济大学 | A hardware simulation test system and method for self-driving car multi-ICU co-space-time |
| CN109886474A (en) * | 2019-01-24 | 2019-06-14 | 同济大学 | A kind of closed test field planing method towards automatic driving vehicle test |
| CN109885929A (en) * | 2019-02-19 | 2019-06-14 | 百度在线网络技术（北京）有限公司 | Automatic Pilot decision rule data reproducing method and device |
| CN109885929B (en) * | 2019-02-19 | 2023-07-07 | 百度在线网络技术（北京）有限公司 | Automatic driving decision planning data reproduction method and device |
| CN109933856B (en) * | 2019-02-19 | 2023-07-07 | 百度在线网络技术（北京）有限公司 | Automatic driving decision planning data reproduction method and device |
| CN109933856A (en) * | 2019-02-19 | 2019-06-25 | 百度在线网络技术（北京）有限公司 | Automatic Pilot decision rule data reproducing method and device |
| CN110288160A (en) * | 2019-06-27 | 2019-09-27 | 北京华如科技股份有限公司 | A kind of situation dynamic prediction method based on parallel simulation |
| CN110595798B (en) * | 2019-09-19 | 2022-04-05 | 北京百度网讯科技有限公司 | Test method and device |
| CN110595798A (en) * | 2019-09-19 | 2019-12-20 | 北京百度网讯科技有限公司 | Test method and device |
| CN110781578B (en) * | 2019-09-23 | 2024-03-29 | 同济大学 | Intelligent network coupling algorithm testing and evaluating method based on accident scene |
| CN110782125A (en) * | 2019-09-23 | 2020-02-11 | 同济大学 | Road safety risk degree evaluation method for automatically driving automobile |
| CN110782125B (en) * | 2019-09-23 | 2023-05-02 | 同济大学 | Road safety risk assessment method for automatic driving automobile |
| CN110781578A (en) * | 2019-09-23 | 2020-02-11 | 同济大学 | A test and evaluation method of intelligent networked vehicle algorithm based on accident scene |
| CN110758403B (en) * | 2019-10-30 | 2022-03-01 | 北京百度网讯科技有限公司 | Control method, device, equipment and storage medium for automatic driving vehicle |
| CN110758403A (en) * | 2019-10-30 | 2020-02-07 | 北京百度网讯科技有限公司 | Control method, device, equipment and storage medium for automatic driving vehicle |
| CN113112643A (en) * | 2020-01-13 | 2021-07-13 | 北京地平线机器人技术研发有限公司 | Evaluation method and device for predicted trajectory, electronic device and storage medium |
| CN114930425A (en) * | 2020-02-28 | 2022-08-19 | 国际商业机器公司 | Autonomous driving assessment using data analysis |
| US11814080B2 (en) | 2020-02-28 | 2023-11-14 | International Business Machines Corporation | Autonomous driving evaluation using data analysis |
| CN111367283A (en) * | 2020-03-11 | 2020-07-03 | 郴州职业技术学院 | Unmanned vehicle obstacle avoidance method and system based on obstacle configuration reconstruction |
| CN111551382A (en) * | 2020-05-12 | 2020-08-18 | 中国科学院心理研究所 | A system and method for testing driver's vehicle distance control ability |
| CN111767651B (en) * | 2020-06-28 | 2023-07-25 | 北京百度网讯科技有限公司 | Index prediction model construction method, index prediction method and device |
| CN111767651A (en) * | 2020-06-28 | 2020-10-13 | 北京百度网讯科技有限公司 | Index prediction model construction method, index prediction method and device |
| CN111879319B (en) * | 2020-06-29 | 2023-10-20 | 中国科学院合肥物质科学研究院 | Indoor test method and system for ground unmanned platform and computer equipment |
| CN111879319A (en) * | 2020-06-29 | 2020-11-03 | 中国科学院合肥物质科学研究院 | Indoor testing method and system for ground unmanned platform and computer equipment |
| CN111914412B (en) * | 2020-07-21 | 2023-07-04 | 同济大学 | A fault injector-based automatic driving performance limitation testing system and method |
| CN111914412A (en) * | 2020-07-21 | 2020-11-10 | 同济大学 | A fault injector-based automatic driving performance limitation testing system and method |
| WO2022027304A1 (en) * | 2020-08-05 | 2022-02-10 | 华为技术有限公司 | Testing method and apparatus for autonomous vehicle |
| CN112286206A (en) * | 2020-11-17 | 2021-01-29 | 苏州智加科技有限公司 | Automatic driving simulation method, system, equipment, readable storage medium and platform |
| CN112286206B (en) * | 2020-11-17 | 2024-01-23 | 苏州智加科技有限公司 | Automatic driving simulation method, system, equipment, readable storage medium and platform |
| WO2022105395A1 (en) * | 2020-11-17 | 2022-05-27 | Suzhou Zhijia Science & Technologies Co., Ltd. | Data processing method, apparatus, and system, computer device, and non-transitory storage medium |
| CN112527633B (en) * | 2020-11-20 | 2021-10-01 | 北京赛目科技有限公司 | Automatic driving simulation test method and device for scene library |
| CN112527633A (en) * | 2020-11-20 | 2021-03-19 | 北京赛目科技有限公司 | Automatic driving simulation test method and device for scene library |
| CN112581633A (en) * | 2020-12-24 | 2021-03-30 | 北京亮道智能汽车技术有限公司 | In-loop virtual simulation test method and system for vehicle with automatic driving function |
| CN112816954B (en) * | 2021-02-09 | 2024-03-26 | 中国信息通信研究院 | Road side perception system evaluation method and system based on true value |
| CN112816954A (en) * | 2021-02-09 | 2021-05-18 | 中国信息通信研究院 | Road side perception system evaluation method and system based on truth value |
| CN113065685A (en) * | 2021-03-01 | 2021-07-02 | 沃行科技(南京)有限公司 | High-precision map traffic rule model based on automatic driving application scene and implementation method thereof |
| CN113065685B (en) * | 2021-03-01 | 2023-10-17 | 沃行科技(南京)有限公司 | High-precision map traffic rule model based on automatic driving application scene and implementation method thereof |
| CN112926135B (en) * | 2021-03-02 | 2024-01-23 | 北京百度网讯科技有限公司 | Scene information determination method, apparatus, device, storage medium, and program product |
| CN112926135A (en) * | 2021-03-02 | 2021-06-08 | 北京百度网讯科技有限公司 | Scene information determination method, apparatus, device, storage medium, and program product |
| CN113779864B (en) * | 2021-08-06 | 2024-04-26 | 同济大学 | Method and device for constructing running design area for automatic driving automobile |
| CN113779864A (en) * | 2021-08-06 | 2021-12-10 | 同济大学 | Method and device for constructing operational design area for autonomous vehicles |
| CN113610166B (en) * | 2021-08-10 | 2023-12-26 | 吉林大学 | Method for establishing test scene library for intelligent vehicle |
| CN113610166A (en) * | 2021-08-10 | 2021-11-05 | 吉林大学 | Method for establishing test scene library for intelligent vehicle |
| CN113949996B (en) * | 2021-10-11 | 2022-10-28 | 重庆大学 | Data processing method and system for acquisition and playback of vehicle-road cooperative test scene |
| CN113949996A (en) * | 2021-10-11 | 2022-01-18 | 重庆大学 | Data processing method and system for collection and playback of vehicle-road collaborative test scene |
| CN113935638A (en) * | 2021-10-20 | 2022-01-14 | 北京轻舟智航科技有限公司 | Trajectory decision evaluation method based on plane topology analysis |
| CN113962110A (en) * | 2021-11-30 | 2022-01-21 | 广州文远知行科技有限公司 | Automatic driving track evaluation method, device, equipment and storage medium |
| CN114627640A (en) * | 2022-01-21 | 2022-06-14 | 中国科学院深圳先进技术研究院 | Dynamic evolution method of intelligent networked automobile driving strategy |
| CN114563196A (en) * | 2022-02-22 | 2022-05-31 | 上清童子(北京)投资顾问有限公司 | Method for checking usability and reliability of automatic driving automobile |
| CN114838948A (en) * | 2022-03-04 | 2022-08-02 | 湖北国际物流机场有限公司 | Automatic lane merging test method and system for airport automatic driving guide vehicle |
| CN114838948B (en) * | 2022-03-04 | 2024-05-17 | 湖北国际物流机场有限公司 | Automatic merging test method and system for airport automatic driving guided vehicle |
| CN114822042B (en) * | 2022-06-28 | 2022-09-02 | 深圳市华耀商品检验有限公司 | Information security test management system and method for vehicle-mounted terminal detection |
| CN114822042A (en) * | 2022-06-28 | 2022-07-29 | 深圳市华耀商品检验有限公司 | Information security test management system and method for vehicle-mounted terminal detection |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108549366B (en) | 2020-11-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108549366A (en) | Intelligent automobile road driving mapping experiment method parallel with virtual test | |
| WO2022121248A1 (en) | Test evaluation information determining method, apparatus and device, and computer storage medium | |
| CN112740188B (en) | Log-based simulation using bias | |
| CN109242251B (en) | Driving behavior safety detection method, device, equipment and storage medium | |
| Murphey et al. | Driver's style classification using jerk analysis | |
| JP6916552B2 (en) | A method and device for detecting a driving scenario that occurs during driving and providing information for evaluating a driver's driving habits. | |
| CN112258841B (en) | Intelligent vehicle risk assessment method based on vehicle track prediction | |
| CN114077541A (en) | Method and system for validating automatic control software for self-driving vehicles | |
| CN113378305B (en) | Driverless trolley-based vehicle-road cooperative testing method and device | |
| WO2012096063A1 (en) | Traffic-flow simulation apparatus, traffic-flow simulation program, and traffic-flow simulation method | |
| CN110751847B (en) | A method and system for autonomous vehicle behavior decision-making | |
| CN111123735A (en) | Automatic driving simulation operation method and device | |
| JP2020121714A (en) | A learning method and a learning device for performing a trajectory-based behavior analysis on a recent travel route to determine whether to change a vehicle mode from a manual travel mode to an autonomous travel mode | |
| CN108959813A (en) | A kind of emulation modelling method of intelligent vehicle road guide environmental model | |
| CN110781578B (en) | Intelligent network coupling algorithm testing and evaluating method based on accident scene | |
| CN104835339B (en) | A kind of reminding method and system based on geographical position to special traffic violation | |
| CN110599025A (en) | Method for evaluating reliability index of driving behavior of automatic driving automobile | |
| CN109900494A (en) | A kind of generation method of test case | |
| Ma et al. | Testing and evaluating driverless vehicles' intelligence: the Tsinghua lion case study | |
| Karunakaran et al. | Automatic lane change scenario extraction and generation of scenarios in OpenX format from real-world data | |
| CN116842688A (en) | Online compliance verification system oriented to automatic driving decision algorithm | |
| CN116430750A (en) | Automatic driving system detection method, device and system based on simulation | |
| CN118228612B (en) | Natural automatic driving scene generation method and device based on reinforcement learning | |
| Che et al. | A test method for self-driving vehicle based on mixed reality | |
| Tamilarasan et al. | Drive scenario generation based on metrics for evaluating an autonomous vehicle controller |
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 |