WO2021036083A1 - 自动驾驶的驾驶员行为模型开发方法、设备和存储介质 - Google Patents

自动驾驶的驾驶员行为模型开发方法、设备和存储介质 Download PDF

Info

Publication number
WO2021036083A1
WO2021036083A1 PCT/CN2019/123508 CN2019123508W WO2021036083A1 WO 2021036083 A1 WO2021036083 A1 WO 2021036083A1 CN 2019123508 W CN2019123508 W CN 2019123508W WO 2021036083 A1 WO2021036083 A1 WO 2021036083A1
Authority
WO
WIPO (PCT)
Prior art keywords
driver behavior
change data
data
vehicle
behavior model
Prior art date
Application number
PCT/CN2019/123508
Other languages
English (en)
French (fr)
Inventor
杜光辉
袁雁城
张尧文
Original Assignee
格物汽车科技(苏州)有限公司
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 格物汽车科技(苏州)有限公司 filed Critical 格物汽车科技(苏州)有限公司
Publication of WO2021036083A1 publication Critical patent/WO2021036083A1/zh

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
    • 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
    • B60W40/08—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 drivers or passengers
    • B60W40/09—Driving style or behaviour

Definitions

  • the present invention relates to the technical field of automatic driving, in particular to a method, equipment and storage medium for developing a driver behavior model for automatic driving.
  • Autonomous vehicles also known as unmanned vehicles, are intelligent vehicles that realize unmanned driving through computer systems. They rely on artificial intelligence, visual computing, radar, monitoring devices, and global positioning systems to work together to enable the vehicle’s computer system to Automatically and safely maneuver motor vehicles without unmanned operation.
  • the embodiments of the present invention provide a driver behavior model development method, device and storage medium for automatic driving, so as to solve the problem that the driver behavior model developed in the existing automatic driving technology cannot effectively extract the end-to-end solution algorithm and solution problem.
  • the present invention provides a driver behavior model development method for autonomous driving, which includes the following steps:
  • the actual output data includes the target vehicle driver's decision data and Operational change data of the target vehicle;
  • step (3) where the correction of the basic model includes:
  • the excitation input includes operating change parameters of surrounding vehicles.
  • the incentive input further includes road traffic information parameters and environmental information parameters.
  • the environmental information parameters include one or any combination of illuminance, weather, temperature, humidity, wind direction, and wind speed;
  • the road traffic information parameters include traffic information parameters for main roads in urban areas, suburban areas One or any combination of road traffic information parameters, national road traffic information parameters, provincial road traffic information parameters, and high-speed traffic information parameters.
  • the incentive input further includes the driver's age parameter, gender parameter, physiological parameter, psychological parameter, and driving age parameter.
  • the target vehicle operation change data includes vehicle position change data, speed change data, acceleration change data, steering angle change data, yaw rate change data, lateral acceleration One or any combination of change data, accelerator opening change data, and brake pedal opening change data.
  • it further includes the operating change parameters of the surrounding vehicles including vehicle position change data, speed change data, acceleration change data, steering angle change data, yaw rate change data, lateral acceleration change data, One or any combination of accelerator opening change data and brake pedal opening change data.
  • the present invention also provides a driver behavior model development device, which includes a memory, a processor, and a program stored in the memory and capable of running on the processor.
  • a driver behavior model development device which includes a memory, a processor, and a program stored in the memory and capable of running on the processor.
  • the present invention also provides a computer-readable storage medium, the computer-readable storage medium stores a driver behavior model development program, which is implemented when the driver behavior model development program is executed by a processor.
  • the above-mentioned driver behavior model development method for autonomous driving is described in detail below.
  • the driver behavior model development method, equipment, and storage medium for automatic driving disclosed in the embodiments of the present application are completely different from the prior art method based on AI technology analysis and training to obtain a driver behavior model from massive amounts of data.
  • First create a basic model in the simulation environment based on the transfer relationship between the excitation input and the theoretical output under the excitation input.
  • Second use the excitation input to intervene in the target vehicle in the field test scenario to obtain the true value of the target vehicle in the field test scenario.
  • Output and finally, use the real output in the field test scenario to modify the basic model to obtain a driver behavior model that is close to the real driver behavior to the greatest extent, and effectively extract end-to-end algorithms and solutions.
  • Fig. 1 is a flowchart of a method for developing a driver behavior model in a first embodiment of the present invention
  • Figure 2 is the model diagram under the first field test scenario
  • Figure 3 is a model diagram under the second field test scenario
  • Figure 4 is a model diagram under the third field test scenario
  • Fig. 5 is a structural block diagram of a driver behavior model development device in the second embodiment of the present invention.
  • This embodiment discloses a driver behavior model development method for automatic driving. As shown in FIG. 1, the development method includes the following steps:
  • the theoretical output here is the driving behavior predicted by the creator of the basic model to have 4 to 10 years of driving experience, and to have good driving behavior within the driving age, and the driving behavior of an experienced driver in the driving environment of the incentive input.
  • (A) Operating variation parameters of vehicles located around the target vehicle in the driving environment including the front and rear directions of the same lane, the parallel position of the left and right adjacent lanes, and the front and rear directions of the left and right adjacent lanes.
  • the operating change parameters of the surrounding vehicles here include vehicle position change data, speed change data, acceleration change data, steering angle change data, yaw rate change data, lateral acceleration change data, accelerator opening change data, brake pedal opening change One or any combination of data.
  • the road traffic information parameters here include one or any combination of main road traffic information parameters in urban areas, suburban road traffic information parameters, national road traffic information parameters, provincial road traffic information parameters, and high-speed traffic information parameters;
  • the environmental information parameters here include One or any combination of illuminance, weather, temperature, humidity, wind direction, wind speed.
  • the creator of the basic model creates the basic model in the simulation environment according to the transfer relationship between the excitation input and the theoretical output under the excitation input.
  • the actual output data includes the target vehicle driver's decision data and the target Vehicle operation change data.
  • the target vehicle operation change data includes vehicle position change data, speed change data, acceleration change data, steering angle change data, yaw rate change data, lateral acceleration change data, accelerator opening change data, brake pedal opening change data One of them or any combination.
  • test scenarios design field test scenarios based on experience and typical scenes of Chinese roads collected throughout the year, including key elements such as road types, vehicle types, weather conditions, vehicle distribution conditions, and vehicle behaviors.
  • a test outline is prepared according to the needs of the driver's behavior model development.
  • the outline content includes the definition of collected data, the change mode of vehicle operation in a single scene, and the change mode of vehicle operation in combined scenes.
  • the person in charge of the test instructs the test vehicle (or "surrounding vehicle") to change its operation mode according to the requirements of the test program, as an incentive to collect the response mode of the driver of the tested vehicle (or "target vehicle”), including the driver The decision-making data and the operational change data of the tested vehicle.
  • the correction process here includes judging whether the actual output data of the target vehicle in the field test scenario is different from the theoretical output, if so, using the real output data to update the theoretical output data, and using the updated theoretical output data to modify the basic model.
  • the vehicle is controlled to accelerate or decelerate by sensing the speed of the preceding vehicle, the distance between the accelerometer, and other related information to ensure that the vehicle and the preceding vehicle maintain a safe and comfortable distance dx.
  • the own vehicle needs to obtain at least the following data: 1The speed of the preceding vehicle in the last time period; 2The acceleration of the preceding vehicle in the last time period; 3The distance between the own vehicle and the preceding vehicle in the last time period; 4The current vehicle in front Estimated parking distance at vehicle speed; 5Estimated parking distance at current speed of the vehicle. And output at least the following data: 1The distance between the vehicle and the preceding vehicle in the current time period; 2The acceleration of the vehicle in the current time period; 3The speed of the vehicle in the current time period.
  • the SC1 scene of the field test includes the correction of the difference between the acceleration and deceleration strategy, and the limitation of the experience value (or "threshold experience value") difference correction while maintaining the distance between the vehicle and the preceding vehicle.
  • the vehicle adopts the deceleration strategy, and the acceleration strategy is used when creating the basic model.
  • the deceleration strategy is used to update the acceleration strategy, and one of the incentive input in this scenario and the updated acceleration strategy is used.
  • the field test SC2 scenario includes the correction of the deceleration strategy difference and the deceleration experience value difference correction adopted by the vehicle after the emergency braking of the vehicle in front.
  • the deceleration of the vehicle is a1
  • the deceleration of the vehicle under the excitation input is a2 (a2 is not equal to a1)
  • the deceleration is updated with deceleration a2 in this scenario a1
  • the intention of changing lanes is predicted by sensing the trajectory of abnormal vehicles in adjacent lanes, and by actively shortening the distance between the vehicle and the preceding vehicle to avoid the full rights of hidden dangers caused by the arbitrary lane change of the adjacent vehicle , The vehicle and the preceding vehicle will eventually maintain a safe and compact distance dx.
  • the vehicle needs to obtain at least the following data: 1The speed change and acceleration change range of the N time period before the lane change vehicle; 2The distance to the vehicle ahead and the change range of the N time period before the lane change vehicle and the change range; 3Last time Cycle distance between the vehicle in front and the vehicle in front; 4Estimation of the parking distance of the vehicle in front at the current speed; 5The usable area of adjacent lanes
  • the field test SC3 scenario includes the correction of the empirical value difference of the distance between the vehicle and the preceding vehicle at different speeds of the vehicle in front, and the revision of the difference of the change rule function.
  • the field test SC3 scenario includes the correction of the lateral control strategy difference, the correction of the experience value of the yaw rate, the correction of the change rate, etc. after the vehicle in front of the vehicle has braked at different levels.
  • the vehicle In the field test SC5 scenario, the vehicle is controlled longitudinally and laterally by sensing the speed, acceleration, and distance of the preceding vehicle, the vehicle being overtaken, and the neighboring vehicle to ensure that the vehicle and the neighboring vehicle stay in place.
  • a safe and comfortable distance (-dx and dRR, etc.), even if the vehicle in front of the vehicle in front of the vehicle does a certain degree of emergency braking without any warning, the vehicle can safely change lanes to the expected adjacent lane.
  • the own vehicle needs to obtain at least the following data: 1The speed of the vehicle to be overtaken in the last time period; 2The acceleration of the vehicle to be overtaken in the last time period; 3The vehicle and the vehicle to be overtaken in the last time period The distance between the vehicle; 4The speed of the vehicle to be overtaken in the last time period; 5The acceleration of the vehicle to be overtaken in the last time period; 6The distance between the own vehicle and the vehicle to be overtaken in the last time period; 7The current vehicle in front Estimated parking distance at vehicle speed; 8 Estimated parking distance at current speed of the vehicle.
  • the field test SC3 scenario includes the correction of the difference between the horizontal and vertical control strategies adopted by the vehicle when the vehicle in front and the overtaken vehicle are in different relative positions and at different relative speeds, and the correction of the difference in related experience values.
  • This embodiment also discloses a driver behavior model development device.
  • the device includes a memory, a processor, and a program stored in the above-mentioned memory and running on the above-mentioned processor, and the program is processed by the above-mentioned processor.
  • the driver's behavior model development method for autonomous driving as shown in Figure 1 is implemented when the driver is executed.
  • This embodiment also discloses a computer-readable storage medium, the computer-readable storage medium stores a driver behavior model development program, and when the driver behavior model development program is executed by a processor, the program shown in FIG. 1 is implemented.
  • Driver behavior model development method for autonomous driving is also disclosed.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Mathematical Physics (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Traffic Control Systems (AREA)
  • Control Of Driving Devices And Active Controlling Of Vehicle (AREA)

Abstract

本发明公开了一种用于自动驾驶的驾驶员行为模型开发方法、设备和存储介质，该方法包括以下步骤，(1)根据激励输入和理论输出之间的传递关系在仿真环境中创建基础模型；(2)使用与创建基础模型相同的激励输入在实地测试场景中干预目标车辆，获取实地测试场景中该激励输入下目标车辆的真实输出数据，所述真实输出数据包括目标车辆驾驶员决策数据和目标车辆运行变化数据；(3)使用获取的实地测试场景下目标车辆的真实输出数据对所述基础模型进行修正。本发明与现有技术中基于AI技术分析，从海量庞大的数据中训练获取驾驶员行为模型的方法决然不同，获取最大程度上趋近于真实驾驶员行为的驾驶员行为模型，有效提取端到端的算法和方案。

Description

自动驾驶的驾驶员行为模型开发方法、设备和存储介质 技术领域
本发明涉及自动驾驶技术领域，具体涉及一种用于自动驾驶的驾驶员行为模型开发方法、设备和存储介质。
背景技术
自动驾驶车辆又称无人驾驶车辆，是一种通过电脑***实现无人驾驶的智能车辆，其依靠人工智能、视觉计算、雷达、监控装置和全球定位***协同合作，使车辆的电脑***可以在无人操作的情况下自动安全地操纵机动车辆。
目前，一些互联网企业和汽车厂商依赖人工智能或深度学习的方法来获取自动驾驶车辆的预测和决策模型算法，其实现理论是：通过车载传感器(比如，视频摄像头、雷达传感器和激光测距器等)获取行驶场景中的道路数据，从车辆行驶过程中获取驾驶员行为数据，由此形成涵盖场景和驾驶员行为的大数据，通过AI分析场景和驾驶员行为数据，并据此不断迭代算法终将得到一个从感知到执行的E2E解决方案。但，实际情况是，不论Waymo还是国内主机厂都已经收集到了大量数据，均没有提取到有效的端到端解决算法和方案，究其原因，主要有以下两点：其一，每个场景都是独一无二的，数量上无法穷举地球上每时每刻产生的所有场景；其二，AI分析不能根据传感器采集的数据评估周围车辆的行为(比如，是否安全、是否高效、是否合规等)，甚至连场景分类都很难做到。
发明内容
本发明实施例提供一种用于自动驾驶的驾驶员行为模型开发方法、设备和 存储介质，以解决现有自动驾驶技术中开发的驾驶员行为模型不能有效提取端到端的解决算法和方案问题。
为了解决上述技术问题，本发明提供了一种用于自动驾驶的驾驶员行为模型开发方法，其包括以下步骤，
(1)根据激励输入和理论输出之间的传递关系在仿真环境中创建基础模型；
(2)使用与创建基础模型相同的激励输入在实地测试场景中干预目标车辆，获取实地测试场景中该激励输入下目标车辆的真实输出数据，所述真实输出数据包括目标车辆驾驶员决策数据和目标车辆运行变化数据；
(3)使用获取的实地测试场景下目标车辆的真实输出数据对所述基础模型进行修正。
本发明一个较佳实施例中，进一步包括步骤(3)中，对所述基础模型进行修正包括，
判断所述实地测试场景下目标车辆的真实输出数据与所述理论输出是否差异，若有，使用真实输出数据更新理论输出数据，并使用更新后的理论输出数据对所述基础模型进行修正。
本发明一个较佳实施例中，进一步包括所述激励输入包括周围车辆的运行变化参数。
本发明一个较佳实施例中，进一步包括所述激励输入还包括道路交通信息参数和环境信息参数。
本发明一个较佳实施例中，进一步包括所述环境信息参数包括光照度、天气、温度、湿度、风向、风速其中之一或任意组合；所述道路交通信息参数包括城区主道路交通信息参数、郊区道路交通信息参数、国道交通信息参数、省 道交通信息参数、高速交通信息参数其中之一或任意组合。
本发明一个较佳实施例中，进一步包括所述激励输入还包括驾驶员的年龄参数、性别参数、生理参数、心理参数和驾龄参数。
本发明一个较佳实施例中，进一步包括步骤(2)中，目标车辆运行变化数据包括车辆位置变化数据、速度变化数据、加速度变化数据、转向角变化数据、横摆角速度变化数据、侧向加速度变化数据、油门开度变化数据、刹车踏板开度变化数据其中之一或任意组合。
本发明一个较佳实施例中，进一步包括所述周围车辆的运行变化参数包括车辆位置变化数据、速度变化数据、加速度变化数据、转向角变化数据、横摆角速度变化数据、侧向加速度变化数据、油门开度变化数据、刹车踏板开度变化数据其中之一或任意组合。
为了解决上述技术问题，本发明还提供了一种驾驶员行为模型开发设备，包括存储器、处理器及存储在所述存储器内并可在所述处理器上运行的程序，所述程序被所述处理器执行时实现以上所述的用于自动驾驶的驾驶员行为模型开发方法。
为了解决上述技术问题，本发明还提供了一种计算机可读存储介质，所述计算机可读存储介质上存储有驾驶员行为模型开发程序，所述驾驶员行为模型开发程序被处理器执行时实现以上所述的用于自动驾驶的驾驶员行为模型开发方法。
本申请实施例公开的用于自动驾驶的驾驶员行为模型开发方法、设备和存储介质，与现有技术中基于AI技术分析，从海量庞大的数据中训练获取驾驶员行为模型的方法决然不同。首先，根据激励输入与该激励输入下的理论输出之间的传递关系在仿真环境中创建基础模型，其次，在实地测试场景中以该激励输入干预目标车辆，获取实地测试场景下目标车辆的真实输出，最后，使用实 地测试场景下的真实输出对基础模型进行修正，获取最大程度上趋近于真实驾驶员行为的驾驶员行为模型，有效提取端到端的算法和方案。
附图说明
图1是本发明第一实施例中驾驶员行为模型开发方法的流程图；
图2是第一种实地测试场景下的模型图；
图3是第二种实地测试场景下的模型图；
图4是第三种实地测试场景下的模型图；
图5是本发明第二实施例中驾驶员行为模型开发设备的结构框图。
具体实施方式
下面结合附图和具体实施例对本发明作进一步说明，以使本领域的技术人员可以更好地理解本发明并能予以实施，但所举实施例不作为对本发明的限定。
本实施例公开一种用于自动驾驶的驾驶员行为模型开发方法，参照图1所示，该开发方法包括以下步骤，
(1)根据激励输入和理论输出之间的传递关系在仿真环境中创建基础模型。
此处的理论输出为基础模型创建者预判有4～10年驾龄、且在驾龄内驾驶行为良好、有经验的驾驶员在该激励输入的驾驶环境下做出的驾驶行为。
此处的激励输入包括以下其中之一或者任意组合：
(A)驾驶环境中位于目标车辆周围(包括同车道前后方向、左右相邻车道并行位置、以及左右相邻车道前后方向)的车辆的运行变化参数。此处周围车辆的运行变化参数包括车辆位置变化数据、速度变化数据、加速度变化数据、转向角变化数据、横摆角速度变化数据、侧向加速度变化数据、油门开度变化 数据、刹车踏板开度变化数据其中之一或任意组合。
(B)道路交通信息参数和环境信息参数。此处的道路交通信息参数包括城区主道路交通信息参数、郊区道路交通信息参数、国道交通信息参数、省道交通信息参数、高速交通信息参数其中之一或任意组合；此处的环境信息参数包括光照度、天气、温度、湿度、风向、风速其中之一或任意组合。
(C)驾驶员的年龄参数、性别参数、生理参数、心理参数和驾龄参数。
(D)车辆类型参数。
基础模型创建者根据激励输入与该激励输入下的理论输出之间的传递关系在仿真环境中创建基础模型。
(2)使用与创建基础模型相同的激励输入在实地测试场景中干预目标车辆，获取实地测试场景中该激励输入下目标车辆的真实输出数据，该真实输出数据包括目标车辆驾驶员决策数据和目标车辆运行变化数据。此处目标车辆运行变化数据包括车辆位置变化数据、速度变化数据、加速度变化数据、转向角变化数据、横摆角速度变化数据、侧向加速度变化数据、油门开度变化数据、刹车踏板开度变化数据其中之一或任意组合。
此处的关键在于实地测试场景的设定：根据经验和常年收集的中国道路的典型场景来设计实地测试场景，包括道路类型、车辆类型、天气状况、车辆分布状况、车辆行为等关键元素。测试开始前根据驾驶员行为模型开发的需求编制测试大纲，大纲内容包括采集数据定义、单一场景车辆运行变化方式、组合场景车辆运行变化方式等内容。测试时测试负责人指挥测试车辆(或称“周围车辆”)按照测试大纲的要求变化运行方式，以此作为激励采集被测车辆(或称“目标车辆”)驾驶员的应对方式，包括驾驶员的决策数据和被测车辆运行变化数据。
(3)使用获取的实地测试场景下目标车辆的真实输出数据对所述基础模型进行修正。此处修正过程包括，判断实地测试场景下目标车辆的真实输出数据与理论输出是否差异，若有，使用真实输出数据更新理论输出数据，并使用更新后的理论输出数据对基础模型进行修正。
参照图2所示为无威胁跟车场景模型：
实地测试SC1场景下，通过感知前车的速度、加速度计车距等相关信息来对本车进行加速或减速的控制，确保本车和前车保持在一个安全、舒适的车距dx。
实地测试SC2场景下，即使前车在没有任何前兆的情况下做一定程度的紧急制动，本车也能以一个可接受的减速度和前车保持一定的安全车距ds。
此处，本车至少需要获取数据有：①上个时间周期的前车车速；②上个时间周期的前车加速度；③上个时间周期的本车与前车的车距；④前车当前车速下停车距离估值；⑤本车当前车速下停车距离估值。并至少输出以下数据：①当前时间周期本车和前车保持的车距；②当前时间周期的本车加速度；③当前时间周期的本车车速。
实地测试SC1场景下包括，本车在保持和前车车距的情况下，加、减速策略差异修正、限制经验值(或称“阈值经验值”)差异修正等。比如，实地测试SC1场景下，本车采用减速策略，而创建基础模型时采用加速策略，则在该场景下用减速策略更新加速策略，并使用该场景下的激励输入与更新后的加速策略之间的传递关系更新基础模型。
实地测试SC2场景下包括，本车在前车紧急制动后采用的减速策略差异修正、减速度经验值差异修正等。比如，实地测试SC2场景下，本车减速度为a1，而创建基础模型时，该激励输入下本车减速度为a2(a2不等于a1)，则在该场景下用减速度a2更新减速度a1，并使用该场景下的激励输入与更新后的减速 度a2之间的传递关系更新基础模型。
参照图3所示为近距离CUT-IN威胁下的跟车场景模型：
实地测试SC3场景下，通过感知相邻车道内非正常车辆的行驶轨迹来预测其变道意图，并通过积极的缩短本车和前车的距离来避免该相邻车随意变道导致的全权隐患，本车和前车最终将维持在一个安全、紧凑的车距dx。
实地测试SC4场景下，即使前车在没有任何前兆的情况下做一定程度的紧急制动，本车也能通过变道来避让，并和新车道内的前、后车维持在一定的安全车距d FR，d RR。
此处，本车至少需要获取数据有：①变道车前N个时间周期的车速变化及加速度变化幅度；②变道车前N个时间周期的与其前车距离及变化幅度；③上个时间周期的本车与前车的车距；④前车当前车速下停车距离估值；⑤相邻车道的可行使区域。
并至少输出以下数据：①当前时间周期本车和前车保持的车距；②当前时间周期的本车加速度；③当前时间周期的本车车速；④当前时间周期的本车在车道内的横向位置。
实地测试SC3场景下包括，在前车不同车速下，本车和前车保持的车距经验值差异修正、变化规律函数差异修订。
实地测试SC3场景下包括，本车在前车不同等级的制动后采用的横向控制策略差异修正、横摆角速度经验值差异修正、变化率差异修正等。
参照图4所示为本车主动变道超车场景模型
实地测试SC5场景下，通过感知前车、被超后车及相邻前车的速度、加速度及车距等所有相关信息来对本车进行纵向及横向的控制，确保本车和相邻车保持在一个安全、舒适的车距(-dx及dRR等)，即使前车前车在没有任何前兆 的情况下做一定程度的紧急制动本车也能安全变道到预期的相邻车道。
此处，本车至少需要获取数据有：①上个时间周期的拟被超后车车速；②上个时间周期的拟被超后车加速度；③上个时间周期的本车与拟被超后车的车距；④上个时间周期的拟被超前车车速；⑤上个时间周期的拟被超前车加速度；⑥上个时间周期的本车与拟被超前车的车距；⑦前车当前车速下停车距离估值；⑧本车当前车速下停车距离估值。
并至少输出以下数据：①当前时间周期本车和前车的车距；②当前时间周期本车和被超后车的车距；③当前时间周期本车和相邻前车的车距；④当前时间周期的本车加速度；⑤当前时间周期的本车车速。
实地测试SC3场景下包括，在前车和被超后车处于不同相对位置及不同相对车速时本车采用的横、纵向控制策略差异修正、及相关经验值差异修正。
本实施例还公开一种驾驶员行为模型开发设备，参照图5所示，该设备包括存储器、处理器及存储在上述存储器内并可在上述处理器上运行的程序，该程序被所述处理器执行时实现如图1所示的用于自动驾驶的驾驶员行为模型开发方法。
本实施例还公开一种计算机可读存储介质，该计算机可读存储介质上存储有驾驶员行为模型开发程序，所述驾驶员行为模型开发程序被处理器执行时实现如图1所示的用于自动驾驶的驾驶员行为模型开发方法。
以上所述实施例仅是为充分说明本发明而所举的较佳的实施例，本发明的保护范围不限于此。本技术领域的技术人员在本发明基础上所作的等同替代或变换，均在本发明的保护范围之内。本发明的保护范围以权利要求书为准。

Claims (10)

  1. 一种用于自动驾驶的驾驶员行为模型开发方法，其特征在于：其包括以下步骤，
    (1)根据激励输入和理论输出之间的传递关系在仿真环境中创建基础模型；
    (2)使用与创建基础模型相同的激励输入在实地测试场景中干预目标车辆，获取实地测试场景中该激励输入下目标车辆的真实输出数据，所述真实输出数据包括目标车辆驾驶员决策数据和目标车辆运行变化数据；
    (3)使用获取的实地测试场景下目标车辆的真实输出数据对所述基础模型进行修正。
  2. 如权利要求1所述的用于自动驾驶的驾驶员行为模型开发方法，其特征在于：步骤(3)中，对所述基础模型进行修正包括，
    判断所述实地测试场景下目标车辆的真实输出数据与所述理论输出是否差异，若有，使用真实输出数据更新理论输出数据，并使用更新后的理论输出数据对所述基础模型进行修正。
  3. 如权利要求1所述的用于自动驾驶的驾驶员行为模型开发方法，其特征在于：所述激励输入包括周围车辆的运行变化参数。
  4. 如权利要求3所述的用于自动驾驶的驾驶员行为模型开发方法，其特征在于：所述激励输入还包括道路交通信息参数和环境信息参数。
  5. 如权利要求4所述的用于自动驾驶的驾驶员行为模型开发方法，其特征在于：所述环境信息参数包括光照度、天气、温度、湿度、风向、风速其中之一或任意组合；所述道路交通信息参数包括城区主道路交通信息参数、郊区道 路交通信息参数、国道交通信息参数、省道交通信息参数、高速交通信息参数其中之一或任意组合。
  6. 如权利要求3所述的用于自动驾驶的驾驶员行为模型开发方法，其特征在于：所述激励输入还包括驾驶员的年龄参数、性别参数、生理参数、心理参数和驾龄参数。
  7. 如权利要求1所述的用于自动驾驶的驾驶员行为模型开发方法，其特征在于：步骤(2)中，目标车辆运行变化数据包括车辆位置变化数据、速度变化数据、加速度变化数据、转向角变化数据、横摆角速度变化数据、侧向加速度变化数据、油门开度变化数据、刹车踏板开度变化数据其中之一或任意组合。
  8. 如权利要求3所述的用于自动驾驶的驾驶员行为模型开发方法，其特征在于：所述周围车辆的运行变化参数包括车辆位置变化数据、速度变化数据、加速度变化数据、转向角变化数据、横摆角速度变化数据、侧向加速度变化数据、油门开度变化数据、刹车踏板开度变化数据其中之一或任意组合。
  9. 一种驾驶员行为模型开发设备，其特征在于：包括存储器、处理器及存储在所述存储器内并可在所述处理器上运行的程序，所述程序被所述处理器执行时实现如权利要求1-8任一项所述的用于自动驾驶的驾驶员行为模型开发方法。
  10. 一种计算机可读存储介质，其特征在于：所述计算机可读存储介质上存储有驾驶员行为模型开发程序，所述驾驶员行为模型开发程序被处理器执行时实现如权利要求1-8任一项所述的用于自动驾驶的驾驶员行为模型开发方法。
PCT/CN2019/123508 2019-08-26 2019-12-06 自动驾驶的驾驶员行为模型开发方法、设备和存储介质 WO2021036083A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910791480.0A CN110497914B (zh) 2019-08-26 2019-08-26 自动驾驶的驾驶员行为模型开发方法、设备和存储介质
CN201910791480.0 2019-08-26

Publications (1)

Publication Number Publication Date
WO2021036083A1 true WO2021036083A1 (zh) 2021-03-04

Family

ID=68589647

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/123508 WO2021036083A1 (zh) 2019-08-26 2019-12-06 自动驾驶的驾驶员行为模型开发方法、设备和存储介质

Country Status (2)

Country Link
CN (1) CN110497914B (zh)
WO (1) WO2021036083A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113706911A (zh) * 2021-08-25 2021-11-26 上海尔纯数据科技有限公司 一种基于数字化交通场景的自动驾驶方法

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110497914B (zh) * 2019-08-26 2020-10-30 格物汽车科技(苏州)有限公司 自动驾驶的驾驶员行为模型开发方法、设备和存储介质
CN111505965B (zh) * 2020-06-17 2020-09-29 深圳裹动智驾科技有限公司 自动驾驶车辆仿真测试的方法、装置、计算机设备及存储介质
CN112180921B (zh) * 2020-09-22 2021-07-30 安徽江淮汽车集团股份有限公司 自动驾驶算法训练***及方法
CN113353087B (zh) * 2021-07-23 2022-08-30 上海汽车集团股份有限公司 一种驾驶辅助方法、装置及***
CN113859250B (zh) * 2021-10-14 2023-10-10 泰安北航科技园信息科技有限公司 一种基于驾驶行为异常识别的智能网联汽车信息安全威胁检测***
CN114132333A (zh) * 2021-12-14 2022-03-04 阿维塔科技(重庆)有限公司 一种智能驾驶***优化方法、装置及计算机可读存储介质

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5895435A (en) * 1996-03-01 1999-04-20 Toyota Jidosha Kabushiki Kaisha Vehicle drive mode estimating device, and vehicle control apparatus, transmission shift control apparatus and vehicle drive force control apparatus including drive mode estimating device
CN106314438A (zh) * 2016-08-15 2017-01-11 西北工业大学 一种司机驾驶轨迹中异常轨迹的检测方法和***
CN107153916A (zh) * 2017-04-30 2017-09-12 安徽中科美络信息技术有限公司 一种基于fcm聚类和bp神经网络的驾驶行为评价方法
CN107235044A (zh) * 2017-05-31 2017-10-10 北京航空航天大学 一种基于多传感数据实现对道路交通场景和司机驾驶行为的还原方法
EP3272611A1 (en) * 2015-04-21 2018-01-24 Panasonic Intellectual Property Management Co., Ltd. Information processing system, information processing method, and program
CN108819948A (zh) * 2018-06-25 2018-11-16 大连大学 基于逆向强化学习的驾驶员行为建模方法
US20190049980A1 (en) * 2017-08-08 2019-02-14 TuSimple Neural network based vehicle dynamics model
CN110497914A (zh) * 2019-08-26 2019-11-26 格物汽车科技(苏州)有限公司 自动驾驶的驾驶员行为模型开发方法、设备和存储介质

Family Cites Families (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2014057648A1 (ja) * 2012-10-12 2014-04-17 日産自動車株式会社 車両用走行支援装置
US9361409B2 (en) * 2013-01-10 2016-06-07 International Business Machines Corporation Automatic driver modeling for integration of human-controlled vehicles into an autonomous vehicle network
KR101592728B1 (ko) * 2014-07-08 2016-02-15 현대자동차주식회사 차량의 주행 시뮬레이션 장치 및 그 방법
US20160314224A1 (en) * 2015-04-24 2016-10-27 Northrop Grumman Systems Corporation Autonomous vehicle simulation system
CN107139929B (zh) * 2017-05-15 2019-04-02 北理慧动（常熟）车辆科技有限公司 一种重型自动变速车辆广义阻力系数的估计及修正方法
CN109032103B (zh) * 2017-06-09 2020-12-18 百度在线网络技术（北京）有限公司 无人驾驶车辆的测试方法、装置、设备及存储介质
CN109515444B (zh) * 2017-09-18 2021-02-26 百度在线网络技术（北京）有限公司 用于输出无人驾驶汽车的行驶性能指标的方法和装置
KR102015076B1 (ko) * 2017-11-13 2019-08-27 주식회사 소네트 일상 주행 데이터를 이용한 자율 주행 알고리즘 개발 장치 및 그 방법
CN108216233B (zh) * 2017-12-28 2019-10-15 北京经纬恒润科技有限公司 一种自适应巡航***控制参数的标定方法及装置
CN110015306B (zh) * 2018-01-10 2020-12-04 华为技术有限公司 驾驶轨迹获取方法及装置
KR20190097486A (ko) * 2018-02-12 2019-08-21 슈어소프트테크주식회사 운전 성향 추정이 가능한 자동차, 운전 성향 추정 방법 및 시스템
CN108803607B (zh) * 2018-06-08 2021-06-01 北京领骏科技有限公司 一种用于自动驾驶的多功能仿真***
CN109213126B (zh) * 2018-09-17 2020-05-19 安徽江淮汽车集团股份有限公司 自动驾驶汽车测试***和方法
CN109726447A (zh) * 2018-12-10 2019-05-07 北京百度网讯科技有限公司 自动驾驶车辆周围行人疏散方法、装置及存储介质
CN109884916B (zh) * 2019-02-26 2022-03-04 魔门塔(苏州)科技有限公司 一种自动驾驶仿真评估方法及装置
CN109993849A (zh) * 2019-03-22 2019-07-09 山东省科学院自动化研究所 一种自动驾驶测试场景再现模拟方法、装置及***
CN110155073B (zh) * 2019-05-24 2020-06-09 合肥工业大学 基于驾驶人偏好的驾驶行为模式识别方法与***

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5895435A (en) * 1996-03-01 1999-04-20 Toyota Jidosha Kabushiki Kaisha Vehicle drive mode estimating device, and vehicle control apparatus, transmission shift control apparatus and vehicle drive force control apparatus including drive mode estimating device
EP3272611A1 (en) * 2015-04-21 2018-01-24 Panasonic Intellectual Property Management Co., Ltd. Information processing system, information processing method, and program
CN106314438A (zh) * 2016-08-15 2017-01-11 西北工业大学 一种司机驾驶轨迹中异常轨迹的检测方法和***
CN107153916A (zh) * 2017-04-30 2017-09-12 安徽中科美络信息技术有限公司 一种基于fcm聚类和bp神经网络的驾驶行为评价方法
CN107235044A (zh) * 2017-05-31 2017-10-10 北京航空航天大学 一种基于多传感数据实现对道路交通场景和司机驾驶行为的还原方法
US20190049980A1 (en) * 2017-08-08 2019-02-14 TuSimple Neural network based vehicle dynamics model
CN108819948A (zh) * 2018-06-25 2018-11-16 大连大学 基于逆向强化学习的驾驶员行为建模方法
CN110497914A (zh) * 2019-08-26 2019-11-26 格物汽车科技(苏州)有限公司 自动驾驶的驾驶员行为模型开发方法、设备和存储介质

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113706911A (zh) * 2021-08-25 2021-11-26 上海尔纯数据科技有限公司 一种基于数字化交通场景的自动驾驶方法

Also Published As

Publication number Publication date
CN110497914A (zh) 2019-11-26
CN110497914B (zh) 2020-10-30

Similar Documents

Publication Publication Date Title
WO2021036083A1 (zh) 自动驾驶的驾驶员行为模型开发方法、设备和存储介质
CN111506058B (zh) 通过信息融合来计划自动驾驶的短期路径的方法及装置
CN112133089B (zh) 一种基于周围环境与行为意图的车辆轨迹预测方法、***及装置
CN111127931B (zh) 一种智能网联汽车的车路云协同方法、装置及***
CN111653113B (zh) 车辆的局部路径确定方法、装置、终端和存储介质
Nouveliere Experimental vehicle longitudinal control using a second order sliding mode technique
DE102020127043A1 (de) Sicherheitssystem für ein fahrzeug
CN112997060A (zh) 用于修改自主车辆的控制单元的方法和***
CN109501799A (zh) 一种车联网条件下的动态路径规划方法
CN113291308A (zh) 一种考虑驾驶行为特性的车辆自学习换道决策***及方法
US11645360B2 (en) Neural network image processing
CN111301419A (zh) 用于sae 4级自动化车道变更的基于强化学习的方法
CN113085873A (zh) 驾驶策略的获取方法、装置、计算机设备和存储介质
CN114077541A (zh) 验证用于自动驾驶车辆的自动控制软件的方法和***
CN113511215B (zh) 一种混合自动驾驶决策方法、设备及计算机存储介质
CN113071515B (zh) 可移动载体控制方法、装置、可移动载体及存储介质
CN115136081A (zh) 用于训练用于机动车的控制器的至少一个算法的方法、用于优化区域中的交通流的方法、计算机程序产品以及机动车
US11657635B2 (en) Measuring confidence in deep neural networks
US11429843B2 (en) Vehicle operation labeling
CN116901963A (zh) 自动驾驶车辆的制动控制方法、装置、车辆和介质
CN111830949B (zh) 自动驾驶车辆控制方法、装置、计算机设备和存储介质
US11782451B1 (en) Training machine learning model for controlling autonomous vehicle
US10977783B1 (en) Quantifying photorealism in simulated data with GANs
Fan et al. Virtual Platform Development for New Control Logic Concept Test and Validation
Gonzalez et al. Longitudinal collision avoidance based on model predictive controllers and fuzzy inference systems

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19943774

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19943774

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 19943774

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 21/09/2022)

122 Ep: pct application non-entry in european phase

Ref document number: 19943774

Country of ref document: EP

Kind code of ref document: A1