CN106864458B - An automatic obstacle avoidance system and method, and a smart car - Google Patents

An automatic obstacle avoidance system and method, and a smart car Download PDF

Info

Publication number
CN106864458B
CN106864458B CN201710183810.9A CN201710183810A CN106864458B CN 106864458 B CN106864458 B CN 106864458B CN 201710183810 A CN201710183810 A CN 201710183810A CN 106864458 B CN106864458 B CN 106864458B
Authority
CN
China
Prior art keywords
lane
barrier
intelligent automobile
obstacle
smart car
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.)
Active
Application number
CN201710183810.9A
Other languages
Chinese (zh)
Other versions
CN106864458A (en
Inventor
方啸
江涛
邓书朝
张茂胜
徐达学
段山保
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Chery Automobile Co Ltd
Original Assignee
Chery Automobile Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Chery Automobile Co Ltd filed Critical Chery Automobile Co Ltd
Priority to CN201710183810.9A priority Critical patent/CN106864458B/en
Publication of CN106864458A publication Critical patent/CN106864458A/en
Application granted granted Critical
Publication of CN106864458B publication Critical patent/CN106864458B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • B60W30/10—Path keeping
    • B60W30/12—Lane keeping
    • 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
    • B60W40/02—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 ambient conditions
    • B60W40/06—Road conditions

Landscapes

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

Abstract

本发明公开了一种自动绕障系统及方法、智能汽车，属于汽车领域。所述自动绕障系统包括障碍物信息采集模块和自动驾驶控制模块，本发明通过在智能汽车前部设置障碍物信息采集模块，以获取智能汽车所在车道内且位于智能汽车前方预设范围内的障碍物信息，通过自动驾驶控制模块根据障碍物信息判断智能汽车是否能由障碍物的旁边通过，并在判断智能汽车不能够从障碍物的旁边通过时，控制智能汽车由障碍物上方通过，并使智能汽车由障碍物上方通过时，智能汽车的两个前轮和两个后轮均位于障碍物外侧，从而避免智能汽车在行驶过程中因遇到障碍物而发生颠簸，保证乘员的舒适感。

The invention discloses an automatic obstacle avoidance system and method, and an intelligent automobile, belonging to the field of automobiles. The automatic obstacle avoidance system includes an obstacle information collection module and an automatic driving control module. In the present invention, an obstacle information collection module is arranged at the front of the smart car to obtain the information in the lane where the smart car is located and within the preset range in front of the smart car. Obstacle information, through the automatic driving control module to judge whether the smart car can pass by the side of the obstacle according to the obstacle information, and when it is judged that the smart car cannot pass by the obstacle, control the smart car to pass above the obstacle, and When the smart car passes over the obstacle, the two front wheels and the two rear wheels of the smart car are located outside the obstacle, so as to avoid the bumping of the smart car when it encounters obstacles during driving, and ensure the comfort of the occupants .

Description

一种自动绕障系统及方法、智能汽车An automatic obstacle avoidance system and method, and a smart car

技术领域technical field

本发明涉及汽车领域，特别涉及一种自动绕障系统及方法、智能汽车。The invention relates to the field of automobiles, in particular to an automatic obstacle avoidance system and method, and an intelligent automobile.

背景技术Background technique

随着科学技术的发展和人民生活水平的提高，汽车已成为人类出行必不可少的交通工具，同时，人们对汽车行驶过程中的舒适性的要求也越来越高。With the development of science and technology and the improvement of people's living standards, automobiles have become an indispensable means of transportation for human travel. At the same time, people have higher and higher requirements for the comfort of automobiles.

目前的智能汽车在行驶过程中注重车道保持，在行车过程中遇到井盖等障碍物时容易发生颠簸，乘员舒适感较差。The current smart car pays attention to lane keeping during driving, and it is prone to bumps when encountering obstacles such as manhole covers during driving, and the occupants have poor comfort.

发明内容Contents of the invention

为了解决现有技术中的智能汽车在行驶过程中注重车道保持，在行车过程中遇到井盖等障碍物时容易发生颠簸，乘员舒适感较差的问题，本发明实施例提供了一种自动绕障系统及方法、智能汽车。所述技术方案如下：In order to solve the problem that the smart car in the prior art pays attention to lane keeping during driving, bumps easily when it encounters obstacles such as manhole covers, and the occupants have poor comfort. Barrier system and method, smart car. Described technical scheme is as follows:

第一方面，提供了一种自动绕障系统，所述系统包括：In a first aspect, an automatic obstacle avoidance system is provided, the system comprising:

障碍物信息采集模块，设置在智能汽车前部，用于获取智能汽车所在车道内且位于智能汽车前方预设范围内的障碍物信息，所述障碍物包括在垂直或近似垂直于所述智能汽车所在车道的车道线方向上的宽度小于所述智能汽车的两个前轮之间的距离的井盖、凹坑、土堆或沙堆，所述障碍物信息包括所述障碍物的位置和几何形状；The obstacle information acquisition module is arranged at the front of the smart car, and is used to acquire information on obstacles in the lane where the smart car is located and within a preset range in front of the smart car. Manhole covers, pits, mounds or sand piles whose width in the direction of the lane line of the lane is less than the distance between the two front wheels of the smart car, the obstacle information includes the position and geometric shape of the obstacle ;

自动驾驶控制模块，与所述障碍物信息采集模块连接，用于根据所述障碍物信息，判断所述智能汽车是否能在所述车道内由所述障碍物的旁边通过；The automatic driving control module is connected with the obstacle information collection module, and is used to judge whether the smart car can pass by the obstacle in the lane according to the obstacle information;

若判断所述智能汽车能够在所述车道内从所述障碍物的旁边通过，则控制所述智能汽车向所述车道内能够通过所述障碍物的一侧行驶；If it is judged that the smart car can pass by the obstacle in the lane, then control the smart car to drive to the side of the lane that can pass the obstacle;

若判断所述智能汽车不能够在所述车道内从所述障碍物的旁边通过，则控制所述智能汽车由所述障碍物上方通过，并使所述智能汽车由所述障碍物上方通过时，所述智能汽车的两个前轮和两个后轮均位于所述障碍物外侧。If it is judged that the smart car cannot pass by the obstacle in the lane, then control the smart car to pass above the obstacle, and make the smart car pass by above the obstacle , the two front wheels and the two rear wheels of the smart car are located outside the obstacle.

进一步地，所述系统还包括：Further, the system also includes:

车道线信息采集模块，与所述自动驾驶控制模块连接，用于获取所述智能汽车所在车道的两条车道线的位置信息。The lane line information collection module is connected with the automatic driving control module and is used to acquire the position information of the two lane lines of the lane where the smart car is located.

具体地，所述车道线信息采集模块包括：Specifically, the lane line information collection module includes:

第一摄像头，设置在所述智能汽车的前部，用于拍摄包含所述智能汽车所在车道的两条车道线的图像；The first camera is arranged at the front of the smart car, and is used to take images of two lane lines including the lane where the smart car is located;

第一图像处理单元，与所述第一摄像头连接，用于对包含所述两条车道线的图像进行处理，获取所述智能汽车与所述车道线的相对位置信息。The first image processing unit is connected with the first camera, and is used to process the image containing the two lane lines, and obtain relative position information between the smart car and the lane lines.

具体地，所述障碍物信息采集模块包括：Specifically, the obstacle information collection module includes:

第二摄像头，设置在所述智能汽车前部，用于拍摄包含所述障碍物的图像；The second camera is arranged at the front of the smart car and is used to take images containing the obstacles;

第二图像处理单元，分别与所述第二摄像头和所述第一图像处理单元连接，用于对所述障碍物的图像进行处理，并结合所述智能汽车与所述车道线的相对位置信息，获取所述障碍物的几何形状信息和所述障碍物与所述智能汽车及所述车道线的相对位置信息。The second image processing unit is connected to the second camera and the first image processing unit respectively, and is used to process the image of the obstacle and combine the relative position information of the smart car and the lane line , acquiring geometric shape information of the obstacle and relative position information of the obstacle, the smart car and the lane line.

具体地，所述第一摄像头和所述第二摄像头均设置在所述智能汽车的前挡风玻璃上。Specifically, both the first camera and the second camera are arranged on the front windshield of the smart car.

第二方面，本发明实施例提供了一种自动绕障方法，应用于所述自动绕障系统，其特征在于，所述方法包括：In the second aspect, an embodiment of the present invention provides an automatic obstacle avoidance method, which is applied to the automatic obstacle avoidance system, wherein the method includes:

获取智能汽车所在车道内且位于智能汽车前方预设范围内的障碍物信息，所述障碍物包括在垂直或近似垂直于所述智能汽车所在车道的车道线方向上的宽度小于所述智能汽车的两个前轮之间的距离的井盖、凹坑、土堆或沙堆，所述障碍物信息包括所述障碍物的位置和几何形状；Acquiring information on obstacles in the lane where the smart car is located and within a preset range in front of the smart car, the obstacles include obstacles whose width is smaller than that of the smart car in the direction perpendicular to or approximately perpendicular to the lane line of the lane where the smart car is located Manhole covers, pits, mounds or sand piles of the distance between the two front wheels, the obstacle information includes the location and geometry of the obstacle;

根据所述障碍物信息，判断所述智能汽车是否能在所述车道内由所述障碍物的旁边通过；According to the obstacle information, it is judged whether the smart car can pass by the obstacle in the lane;

若判断所述智能汽车能够在所述车道内从所述障碍物的旁边通过，则控制所述智能汽车向所述车道内能够通过所述障碍物的一侧行驶；If it is judged that the smart car can pass by the obstacle in the lane, then control the smart car to drive to the side of the lane that can pass the obstacle;

若判断所述智能汽车不能够在所述车道内从所述障碍物的旁边通过，则控制所述智能汽车由所述障碍物上方通过，并使所述智能汽车由所述障碍物上方通过时，所述智能汽车的两个前轮和两个后轮均位于所述障碍物外侧。If it is judged that the smart car cannot pass by the obstacle in the lane, then control the smart car to pass above the obstacle, and make the smart car pass by above the obstacle , the two front wheels and the two rear wheels of the smart car are located outside the obstacle.

具体地，所述根据所述障碍物信息，判断所述智能汽车是否能在所述车道内由所述障碍物的旁边通过，包括：Specifically, according to the obstacle information, judging whether the smart car can pass by the obstacle in the lane includes:

获取所述障碍物与所述车道线的相对位置信息；Obtain relative position information of the obstacle and the lane line;

根据所述障碍物与所述车道线的相对位置信息，并结合所述障碍物的几何形状信息，比较所述障碍物的边缘到所述车道的两条车道线之间的距离与所述智能汽车的两个前轮之间的距离的大小，若所述障碍物的边缘到所述车道的至少一条车道线之间的距离大于所述智能汽车的两个前轮之间的距离，则判断所述智能汽车能够在所述车道内从所述障碍物的旁边通过，若所述障碍物的边缘到所述车道的两条车道线之间的距离均小于所述智能汽车的两个前轮之间的距离，则判断所述智能汽车不能够在所述车道内从所述障碍物的旁边通过。According to the relative position information of the obstacle and the lane line, combined with the geometric shape information of the obstacle, compare the distance between the edge of the obstacle and the two lane lines of the lane with the intelligent The size of the distance between the two front wheels of the car, if the distance between the edge of the obstacle and at least one lane line of the lane is greater than the distance between the two front wheels of the smart car, then judge The smart car can pass by the obstacle in the lane, if the distance between the edge of the obstacle and the two lane lines of the lane is smaller than the two front wheels of the smart car If the distance between them is determined, it is judged that the smart car cannot pass by the obstacle in the lane.

进一步地，所述方法还包括：Further, the method also includes:

针对不同驾驶场景设定不同的增强信号算法，根据所述智能汽车驾驶过程中的实际参数计算增强信号，并计算每个增强信号与目标增强信号的差值的绝对值，按照增强信号与目标增强信号的差值的绝对值减小的方向优化驾驶策略Set different enhanced signal algorithms for different driving scenarios, calculate the enhanced signal according to the actual parameters in the driving process of the smart car, and calculate the absolute value of the difference between each enhanced signal and the target enhanced signal, according to the enhanced signal and target enhanced Direction-optimized driving strategy with reduced absolute value of signal difference

第三方面，提供了一种智能汽车，所述智能汽车包括所述自动绕障系统。In a third aspect, a smart car is provided, and the smart car includes the automatic obstacle avoidance system.

本发明实施例提供的技术方案带来的有益效果是：The beneficial effects brought by the technical solution provided by the embodiments of the present invention are:

本发明通过在智能汽车前部设置障碍物信息采集模块，以获取智能汽车所在车道内且位置智能汽车前方预设范围内的障碍物信息，通过自动驾驶控制模块根据障碍物信息判断智能汽车是否能由障碍物的旁边通过，并在判断智能汽车不能够从障碍物的旁边通过时，控制智能汽车由障碍物上方通过，并使智能汽车由障碍物上方通过时，智能汽车的两个前轮和两个后轮均位于障碍物外侧，从而避免智能汽车在行驶过程中因遇到障碍物而发生颠簸，保证乘员的舒适感。In the present invention, an obstacle information collection module is set at the front of the smart car to obtain information about obstacles in the lane where the smart car is located and within a preset range in front of the smart car, and the automatic driving control module judges whether the smart car can Pass by the side of the obstacle, and when it is judged that the smart car cannot pass by the side of the obstacle, control the smart car to pass by the obstacle, and when the smart car passes by the obstacle, the two front wheels of the smart car and The two rear wheels are located on the outside of the obstacle, so as to prevent the smart car from bumping when it encounters obstacles during driving, and ensure the comfort of the occupants.

附图说明Description of drawings

为了更清楚地说明本发明实施例中的技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings that need to be used in the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those skilled in the art, other drawings can also be obtained based on these drawings without creative effort.

图1是本发明一实施例提供的自动绕障系统的结构框图；Fig. 1 is a structural block diagram of an automatic obstacle avoidance system provided by an embodiment of the present invention;

图2是本发明又一实施例提供的智能汽车遇障时的状态示意图；Fig. 2 is a schematic diagram of the state of a smart car when an obstacle is encountered according to another embodiment of the present invention;

图3是本发明又一实施例提供的智能汽车绕障时的状态示意图；Fig. 3 is a schematic diagram of the state of the smart car when it is circumventing obstacles provided by another embodiment of the present invention;

图4是本发明又一实施例提供的自动绕障方法的流程图。Fig. 4 is a flow chart of an automatic obstacle avoidance method provided by another embodiment of the present invention.

其中：in:

1障碍物信息采集模块，11第二摄像头，12第二图像处理单元；1 Obstacle information acquisition module, 11 second camera, 12 second image processing unit;

2自动驾驶控制模块；2. Automatic driving control module;

3车道线信息采集模块，31第一摄像头，32第一图像处理单元；3 lane line information acquisition module, 31 first camera, 32 first image processing unit;

10智能汽车，10 smart cars,

20障碍物，20 obstacles,

30车道线，30 lane lines,

40车道中心线。40 lane centerline.

具体实施方式Detailed ways

为使本发明的目的、技术方案和优点更加清楚，下面将结合附图对本发明实施方式作进一步地详细描述。In order to make the object, technical solution and advantages of the present invention clearer, the implementation manner of the present invention will be further described in detail below in conjunction with the accompanying drawings.

实施例一Embodiment one

如图1所示，本发明实施例提供了一种自动绕障系统，所述系统包括：As shown in Figure 1, an embodiment of the present invention provides an automatic obstacle avoidance system, which includes:

障碍物信息采集模块1，设置在智能汽车10前部，用于获取智能汽车10所在车道内且位于智能汽车10前方预设范围内的障碍物20信息，所述障碍物20包括在垂直于所述智能汽车10所在车道的车道线30方向上的宽度小于所述智能汽车10的两个前轮之间的距离的井盖、凹坑、土堆或沙堆，所述障碍物20信息包括所述障碍物20的位置和几何形状；Obstacle information collection module 1 is arranged at the front of the smart car 10, and is used to obtain information on obstacles 20 within the lane where the smart car 10 is located and within a preset range in front of the smart car 10, the obstacles 20 are included in the Manhole covers, pits, mounds or sand piles whose width in the direction of the lane line 30 of the lane where the smart car 10 is located is smaller than the distance between the two front wheels of the smart car 10, the information on the obstacle 20 includes the The location and geometry of the obstacle 20;

自动驾驶控制模块2，与所述障碍物信息采集模块1连接，用于根据所述障碍物20信息，判断所述智能汽车10是否能在所述车道内由所述障碍物20的旁边通过；The automatic driving control module 2 is connected with the obstacle information collection module 1, and is used to judge whether the smart car 10 can pass by the obstacle 20 in the lane according to the obstacle 20 information;

若判断所述智能汽车10能够在所述车道内从所述障碍物20的旁边通过，则控制所述智能汽车10向所述车道内能够通过所述障碍物20的一侧行驶；If it is judged that the smart car 10 can pass by the obstacle 20 in the lane, then control the smart car 10 to travel to the side that can pass the obstacle 20 in the lane;

若判断所述智能汽车10不能够在所述车道内从所述障碍物20的旁边通过，则控制所述智能汽车10由所述障碍物20上方通过，并使所述智能汽车10由所述障碍物20上方通过时，所述智能汽车10的两个前轮和两个后轮均位于所述障碍物20外侧。If it is judged that the smart car 10 cannot pass by the obstacle 20 in the lane, the smart car 10 is controlled to pass above the obstacle 20, and the smart car 10 is passed by the obstacle 20. When passing above the obstacle 20 , the two front wheels and the two rear wheels of the smart car 10 are located outside the obstacle 20 .

在本发明实施例中，在障碍物信息采集模块1未检测到智能汽车10所在车道上预设范围内存在井盖、凹坑、土堆或沙堆等障碍物20时，自动驾驶控制模块2控制智能汽车10沿车道中心线40行驶，当障碍物信息采集模块1检测到智能汽车10所在车道上的预设范围内存在障碍物20时，自动驾驶控制模块2根据障碍物20信息判断智能汽车10是否能从障碍物20旁边通过，而后根据具体判断结果决定绕过障碍物20的驾驶策略。如图2所示，当自动驾驶控制模块2判断智能汽车10能够从障碍物20旁边通过时，则控制智能汽车10向车道中能够通过智能汽车10的一侧行驶，如图3所示，当自动驾驶控制模块2判断智能汽车10不能够从障碍物20旁边通过时，则控制智能汽车10由障碍物20上方通过，且使得智能汽车10通过障碍物20上方时，其两个前轮和两个后轮均位于障碍物20之外。In the embodiment of the present invention, when the obstacle information collection module 1 does not detect that there are obstacles 20 such as manhole covers, pits, mounds or sand piles in the preset range on the lane where the smart car 10 is located, the automatic driving control module 2 controls The smart car 10 runs along the lane centerline 40. When the obstacle information collection module 1 detects that there is an obstacle 20 within the preset range on the lane where the smart car 10 is located, the automatic driving control module 2 judges the smart car 10 according to the information of the obstacle 20. Whether it is possible to pass by the obstacle 20, and then determine the driving strategy for bypassing the obstacle 20 according to the specific judgment result. As shown in Figure 2, when the automatic driving control module 2 judges that the smart car 10 can pass by the obstacle 20, it controls the smart car 10 to drive to the side where the smart car 10 can pass in the lane, as shown in Figure 3, when When the automatic driving control module 2 judges that the smart car 10 cannot pass by the obstacle 20, it controls the smart car 10 to pass above the obstacle 20, and when the smart car 10 passes above the obstacle 20, its two front wheels and two Each rear wheel is located outside the obstacle 20.

其中，本领域技术人员可以理解，当障碍物20为土堆或沙堆时，土堆或沙堆的最高高度低于智能汽车10底盘的高度。Wherein, those skilled in the art can understand that when the obstacle 20 is an earth mound or a sand mound, the highest height of the earth mound or sand mound is lower than the height of the chassis of the smart car 10 .

本发明通过在智能汽车10前部设置障碍物信息采集模块1，以获取智能汽车10所在车道内且位置智能汽车10前方预设范围内的障碍物20信息，通过自动驾驶控制模块2根据障碍物20信息判断智能汽车10是否能由障碍物20的旁边通过，并在判断智能汽车10不能够从障碍物20的旁边通过时，控制智能汽车10由障碍物20上方通过，并使智能汽车10由障碍物20上方通过时，智能汽车10的两个前轮和两个后轮均位于障碍物20外侧，从而避免智能汽车10在行驶过程中因遇到障碍物20而发生颠簸，保证乘员的舒适感。In the present invention, an obstacle information collection module 1 is set at the front of the smart car 10 to obtain information on obstacles 20 within the lane where the smart car 10 is located and within a preset range in front of the smart car 10, and the automatic driving control module 2 can detect the obstacles according to the obstacle information. 20 information to determine whether the smart car 10 can pass by the side of the obstacle 20, and when judging that the smart car 10 cannot pass by the side of the obstacle 20, control the smart car 10 to pass above the obstacle 20, and make the smart car 10 pass by the obstacle 20 When passing above the obstacle 20, the two front wheels and the two rear wheels of the smart car 10 are located outside the obstacle 20, thereby avoiding the bumping of the smart car 10 due to encountering the obstacle 20 during driving, and ensuring the comfort of the occupants sense.

如图1所示，在本发明实施例中，该自动绕障系统还包括：As shown in Figure 1, in the embodiment of the present invention, the automatic obstacle avoidance system also includes:

车道线信息采集模块3，与所述自动驾驶控制模块2连接，用于获取所述智能汽车10所在车道的两条车道线30的位置信息。The lane line information collection module 3 is connected with the automatic driving control module 2 and used to acquire the position information of the two lane lines 30 of the lane where the smart car 10 is located.

在本发明实施例中，通过车道线30采集模块获取智能汽车10所在车道的两条车道线30的位置信息，当障碍物信息采集模块1检测到智能汽车10所在车道内且位于智能汽车10前方预设范围内存在障碍物20时，自动驾驶控制模块2根据两条车道线30的位置信息与智能汽车10信息判断智能汽车10是否能在其所在车道内由障碍物20旁边通过，且当障碍物信息采集模块1未检测到智能汽车10所在车道内且位于智能汽车10前方的预设范围内存在障碍物20时，自动驾驶控制模块2控制智能汽车10行驶过程中以智能汽车10的中轴线与两条车道线30等距为原则。从而在车道保持的基础上进行绕障，保证乘员的舒适感。In the embodiment of the present invention, the position information of the two lane lines 30 of the lane where the smart car 10 is located is acquired by the lane line 30 acquisition module, when the obstacle information acquisition module 1 detects that the smart car 10 is in the lane and is located in front of the smart car 10 When there is an obstacle 20 in the preset range, the automatic driving control module 2 judges whether the smart car 10 can pass by the obstacle 20 in its lane according to the position information of the two lane lines 30 and the information of the smart car 10 , and when the obstacle When the object information collection module 1 does not detect that there is an obstacle 20 in the lane where the smart car 10 is located and within the preset range in front of the smart car 10, the automatic driving control module 2 controls the smart car 10 to move around the central axis of the smart car 10 while the smart car 10 is running. Equidistant from the two lane lines 30 is the principle. In this way, obstacles can be circumvented on the basis of lane keeping to ensure the comfort of the occupants.

如图1所示，在本发明实施例中，所述车道线信息采集模块3包括：As shown in Figure 1, in the embodiment of the present invention, the lane line information collection module 3 includes:

第一摄像头31，设置在所述智能汽车10的前部，用于拍摄包含所述智能汽车10所在车道的两条车道线30的图像；The first camera 31 is arranged on the front portion of the smart car 10, and is used to take images of two lane lines 30 including the lane where the smart car 10 is located;

第一图像处理单元32，与所述第一摄像头31连接，用于对包含所述两条车道线30的图像进行处理，获取所述智能汽车10与所述车道线30的相对位置信息。The first image processing unit 32 is connected with the first camera 31 and is used for processing the image including the two lane lines 30 to obtain the relative position information of the smart car 10 and the lane lines 30 .

在本发明实施例中，第一摄像头31设置在智能汽车10的前部，对智能汽车10前方的区域进行拍摄，第一图像处理单元32根据第一摄像头31拍摄到的画面，利用图像增强技术增强车道边缘，并采用自适应二值化算法提取车道线30，然后根据车道线30特征提取车道线30内侧边缘，再通过HOUGH变换拟合出直到线，最后采用车道线30跟踪技术得到稳定的车道线30，根据摄像头在智能汽车10上的安装位置及摄像头的摄像参数，计算出智能汽车10与车道的两条车道线30的距离，得出智能汽车10与车道线30的相对位置信息。In the embodiment of the present invention, the first camera 31 is arranged at the front of the smart car 10, and the area in front of the smart car 10 is photographed, and the first image processing unit 32 utilizes image enhancement technology according to the picture captured by the first camera 31. Enhance the edge of the lane, and use the adaptive binarization algorithm to extract the lane line 30, then extract the inner edge of the lane line 30 according to the characteristics of the lane line 30, and then use the HOUGH transform to fit the straight line, and finally use the lane line 30 tracking technology to obtain a stable The lane lines 30 calculate the distance between the smart car 10 and the two lane lines 30 of the lane according to the installation position of the camera on the smart car 10 and the shooting parameters of the camera, and obtain the relative position information of the smart car 10 and the lane lines 30 .

如图1所示，在本发明实施例中，所述障碍物信息采集模块1包括：As shown in Figure 1, in the embodiment of the present invention, the obstacle information collection module 1 includes:

第二摄像头11，设置在所述智能汽车10前部，用于拍摄包含所述障碍物20的图像；The second camera 11 is arranged on the front part of the smart car 10, and is used to take an image containing the obstacle 20;

第二图像处理单元12，分别与所述第二摄像头11和所述第一图像处理单元32连接，用于对包含所述障碍物20的图像进行处理，并结合所述智能汽车10与所述车道线30的相对位置信息，获取所述障碍物20的几何形状信息和所述障碍物20与所述智能汽车10及所述车道线30的相对位置信息。The second image processing unit 12 is connected with the second camera 11 and the first image processing unit 32 respectively, and is used to process the image containing the obstacle 20, and combine the smart car 10 with the The relative position information of the lane line 30 is to obtain the geometric shape information of the obstacle 20 and the relative position information of the obstacle 20 , the smart car 10 and the lane line 30 .

在本发明实施例中，第二摄像头11设置在智能汽车10的前部，用于实时拍摄智能汽车10前方预设范围内的画面，第二图像处理单元12根据第二摄像头11拍摄到的画面，对画面进行处理，识别出画面内的障碍物20，并根据摄像头在智能汽车10上的设置位置及摄像头的摄像参数计算出障碍物20的几何形状，且结合智能汽车10与车道线30的相对位置，得出障碍物20与智能汽车10及车道线30三者的相对位置，以便于自动驾驶控制模块2进行分析判断。In the embodiment of the present invention, the second camera 11 is arranged on the front portion of the smart car 10 for real-time shooting of pictures within the preset range in front of the smart car 10, and the second image processing unit 12 captures the picture according to the second camera 11 , process the screen, identify the obstacle 20 in the screen, and calculate the geometric shape of the obstacle 20 according to the installation position of the camera on the smart car 10 and the shooting parameters of the camera, and combine the smart car 10 and the lane line 30 The relative position obtains the relative position of the obstacle 20, the smart car 10 and the lane line 30, so that the automatic driving control module 2 can analyze and judge.

其中，第二图像处理单元12识别障碍物20的方法可以为：预先采集大量障碍物20的图片，形成样本数据库，对样本数据库中的样本进行分析整合，得到可以描述各类障碍物20的数学模型。当第二摄像头11拍摄的画面中有符合某一数学模型的画面存在时，即可通过第二图像处理单元12获知该障碍物20的信息。Wherein, the method for the second image processing unit 12 to identify the obstacle 20 may be: collect a large number of images of the obstacle 20 in advance, form a sample database, analyze and integrate the samples in the sample database, and obtain a mathematical model that can describe various obstacles 20 Model. When there is a picture conforming to a certain mathematical model among the pictures taken by the second camera 11 , the information of the obstacle 20 can be obtained through the second image processing unit 12 .

如图2所示，也可参见图3，在本发明实施例中，第一摄像头31和第二摄像头11分别设置在智能汽车10的前挡风玻璃上，拍摄范围较广。As shown in FIG. 2 , also refer to FIG. 3 , in the embodiment of the present invention, the first camera 31 and the second camera 11 are respectively arranged on the front windshield of the smart car 10 , and the shooting range is relatively wide.

实施例二Embodiment two

如图3所示，本发明实施例提供了一种自动绕障方法，该方法包括：As shown in Figure 3, an embodiment of the present invention provides an automatic obstacle avoidance method, which includes:

在步骤201中，获取智能汽车所在车道内且位于智能汽车前方预设范围内的障碍物信息，所述障碍物包括在垂直或近似垂直于所述智能汽车所在车道的车道线方向上的宽度小于所述智能汽车的两个前轮之间的距离的井盖、凹坑、土堆或沙堆，所述障碍物信息包括所述障碍物的位置和几何形状。In step 201, the obstacle information in the lane where the smart car is located and within the preset range in front of the smart car is obtained, and the obstacle includes a width less than The distance between the two front wheels of the smart car is the manhole cover, pit, mound or sand pile, and the obstacle information includes the position and geometric shape of the obstacle.

在本发明实施例中，障碍物信息通过设置在智能汽车前部的障碍物信息采集模块采集，在智能汽车行驶至离障碍物100米左右时，即可通过障碍物信息采集模块采集障碍物信息。In the embodiment of the present invention, the obstacle information is collected by the obstacle information collection module arranged at the front of the smart car, and when the smart car is about 100 meters away from the obstacle, the obstacle information can be collected by the obstacle information collection module .

在步骤202中，根据所述障碍物信息，判断所述智能汽车是否能在所述车道内由所述障碍物的旁边通过；In step 202, according to the obstacle information, it is judged whether the smart car can pass by the obstacle in the lane;

若判断所述智能汽车能够在所述车道内从所述障碍物的旁边通过，则进入步骤203，若判断所述智能汽车不能够在所述车道内从所述障碍物的旁边通过，则进入步骤204。If it is judged that the smart car can pass by the obstacle in the lane, enter step 203; if it is judged that the smart car cannot pass by the obstacle in the lane, enter Step 204.

在步骤203中，控制所述智能汽车向所述车道内能够通过所述障碍物的一侧行驶。In step 203, the smart car is controlled to drive to the side of the lane where the obstacle can pass.

在本发明实施例中，当智能汽车的自动驾驶控制模块判断智能汽车能够在所述车道内从障碍物的旁边通过时，自动驾驶控制模块控制智能汽车偏离车道中心线，可以智能汽车能够在车道内通过障碍物的一侧的车道线及障碍物的边缘设置虚拟车道，该虚拟车道的中心线平行于车道中心线，自动驾驶控制模块控制智能汽车沿该虚拟车道的中心线行驶。In the embodiment of the present invention, when the automatic driving control module of the smart car judges that the smart car can pass by the obstacle in the lane, the automatic driving control module controls the smart car to deviate from the center line of the lane, so that the smart car can pass in the lane. A virtual lane is set through the lane line on one side of the obstacle and the edge of the obstacle. The centerline of the virtual lane is parallel to the centerline of the lane. The automatic driving control module controls the smart car to drive along the centerline of the virtual lane.

在步骤204中，控制所述智能汽车由所述障碍物上方通过，并使所述智能汽车由所述障碍物上方通过时，所述智能汽车的两个前轮和两个后轮均位于所述障碍物外侧。In step 204, the smart car is controlled to pass above the obstacle, and when the smart car passes above the obstacle, the two front wheels and the two rear wheels of the smart car are located at the outside the obstacle.

在本发明实施例中，由于本发明实施例中所说的障碍物在垂直或近似垂直于车道线方向上的宽度小于智能汽车的两个前轮之间的距离，则当智能汽车的自动驾驶控制模块判断智能汽车不能在所述车道内由障碍物旁边通过时，智能汽车的自动驾驶控制模块控制智能汽车由障碍物上方通过，此时，可以障碍物沿车道中心线方向的中心线设置虚拟车道，智能汽车的自动驾驶控制模块控制智能汽车沿该虚拟车道的中心线行驶，使得智能汽车在通过障碍物上方时，智能汽车的两个前轮和两个后轮均位于障碍物外侧，也即使智能汽车由障碍物上方架空驶过。In the embodiment of the present invention, since the width of the obstacle in the embodiment of the present invention in the direction vertical or approximately perpendicular to the lane line is smaller than the distance between the two front wheels of the smart car, when the automatic driving of the smart car When the control module judges that the smart car cannot pass by the obstacle in the lane, the automatic driving control module of the smart car controls the smart car to pass above the obstacle. Lane, the automatic driving control module of the smart car controls the smart car to drive along the centerline of the virtual lane, so that when the smart car passes over the obstacle, the two front wheels and the two rear wheels of the smart car are located outside the obstacle, and Even if the smart car drives overhead above the obstacle.

其中，所述根据所述障碍物信息，判断所述智能汽车是否能在所述车道内由所述障碍物的旁边通过，包括：Wherein, the judging whether the smart car can pass by the obstacle in the lane according to the obstacle information includes:

获取所述障碍物与所述车道线的相对位置信息；Obtain relative position information of the obstacle and the lane line;

根据所述障碍物与所述车道线的相对位置信息，并结合所述障碍物的几何形状信息，比较所述障碍物的边缘到所述车道的两条车道线之间的距离与所述智能汽车的两个前轮之间的距离的大小，若所述障碍物的边缘到所述车道的至少一条车道线之间的距离大于所述智能汽车的两个前轮之间的距离，则判断所述智能汽车能够在所述车道内从所述障碍物的旁边通过，若所述障碍物的边缘到所述车道的两条车道线之间的距离均小于所述智能汽车的两个前轮之间的距离，则判断所述智能汽车不能够在所述车道内从所述障碍物的旁边通过。According to the relative position information of the obstacle and the lane line, combined with the geometric shape information of the obstacle, compare the distance between the edge of the obstacle and the two lane lines of the lane with the intelligent The size of the distance between the two front wheels of the car, if the distance between the edge of the obstacle and at least one lane line of the lane is greater than the distance between the two front wheels of the smart car, then judge The smart car can pass by the obstacle in the lane, if the distance between the edge of the obstacle and the two lane lines of the lane is smaller than the two front wheels of the smart car If the distance between them is determined, it is judged that the smart car cannot pass by the obstacle in the lane.

在本发明实施例中，为了保持智能汽车始终在一个车道内行驶，故需通过障碍物与车道线的相对位置信息来判断智能汽车是否能在车道内由障碍物旁边通过，当障碍物的一侧边缘到车道线的距离大于智能汽车的两个前轮或两个后轮之间的距离时，则可判断智能汽车可由障碍物的旁边通过，当障碍物的任一侧边缘到车道线的距离均小于智能汽车的两个前轮或两个后轮之间的距离时，则可判断智能汽车不能有障碍物的旁边通过。In the embodiment of the present invention, in order to keep the smart car always driving in a lane, it is necessary to judge whether the smart car can pass by the obstacle in the lane through the relative position information of the obstacle and the lane line. When the distance from the side edge to the lane line is greater than the distance between the two front wheels or the two rear wheels of the smart car, it can be judged that the smart car can pass by the side of the obstacle. When the distances are smaller than the distance between the two front wheels or the two rear wheels of the smart car, it can be judged that the smart car cannot pass by the obstacle.

本发明通过在智能汽车前部设置障碍物信息采集模块，以获取智能汽车所在车道内且位置智能汽车前方预设范围内的障碍物信息，通过自动驾驶控制模块根据障碍物信息判断智能汽车是否能在所述车道内由障碍物的旁边通过，并在判断智能汽车不能够在所述车道内从障碍物的旁边通过时，控制智能汽车由障碍物上方通过，并使智能汽车由障碍物上方通过时，智能汽车的两个前轮和两个后轮均位于障碍物外侧，从而避免智能汽车在行驶过程中因遇到障碍物而发生颠簸，保证乘员的舒适感。In the present invention, an obstacle information collection module is set at the front of the smart car to obtain information about obstacles in the lane where the smart car is located and within a preset range in front of the smart car, and the automatic driving control module judges whether the smart car can Pass by the side of the obstacle in the lane, and when it is judged that the smart car cannot pass by the side of the obstacle in the lane, control the smart car to pass above the obstacle, and make the smart car pass by above the obstacle At this time, the two front wheels and the two rear wheels of the smart car are located on the outside of the obstacle, so as to avoid the bumping of the smart car when it encounters obstacles during driving, and ensure the comfort of the occupants.

在本发明实施例中，为使智能汽车能够安全行驶，所述方法还包括：In the embodiment of the present invention, in order to enable the smart car to drive safely, the method also includes:

针对不同驾驶场景设定不同的增强信号算法，根据所述智能汽车驾驶过程中的实际参数计算增强信号，并计算每个增强信号与目标增强信号的差值的绝对值，按照增强信号与目标增强信号的差值的绝对值减小的方向优化驾驶策略如：Set different enhanced signal algorithms for different driving scenarios, calculate the enhanced signal according to the actual parameters in the driving process of the smart car, and calculate the absolute value of the difference between each enhanced signal and the target enhanced signal, according to the enhanced signal and target enhanced The absolute value of the signal difference reduces the direction of the optimal driving strategy such as:

参见图1，当智能汽车的障碍物信息采集模块未采集到智能汽车所在车道的前方预设范围内存在障碍物时，增强信号可按照如下公式(1)进行计算：Referring to Fig. 1, when the obstacle information acquisition module of the smart car does not collect obstacles in the preset range ahead of the lane where the smart car is located, the enhanced signal can be calculated according to the following formula (1):

其中，r为增强信号，d1为智能汽车与一条车道线的距离，d2为智能汽车与另一条车道线的距离。Among them, r is the enhanced signal, d 1 is the distance between the smart car and one lane line, and d 2 is the distance between the smart car and another lane line.

其中，目标增强信号的数值为0，r的数值越趋近于0，表明智能汽车行驶过程中的中轴线越靠近车道中心线，系统记录驾驶过程中r最接近于0时的驾驶策略，在之后无需绕障的驾驶场景中对该驾驶策略进行进一步优化，以得到最优化的驾驶策略；Among them, the value of the target enhancement signal is 0, and the value of r is closer to 0, indicating that the central axis of the smart car is closer to the center line of the lane during driving. The system records the driving strategy when r is closest to 0 during driving. Afterwards, the driving strategy is further optimized in the driving scene without obstacle avoidance to obtain the optimal driving strategy;

参见图3，以障碍物为井盖进行说明，当判断智能汽车不能从井盖旁边通过，控制智能汽车由井盖的上方通过时，增强信号可按照如下公式(2)进行计算：Referring to Figure 3, the obstacle is used as the manhole cover for illustration. When it is judged that the smart car cannot pass by the manhole cover and the smart car is controlled to pass above the manhole cover, the enhanced signal can be calculated according to the following formula (2):

其中，r为增强信号，d1为智能汽车与一条车道线的距离，d2为智能汽车与另一条车道线的距离，θ为智能汽车前进方向与井盖方位的夹角。Among them, r is the enhanced signal, d 1 is the distance between the smart car and a lane line, d 2 is the distance between the smart car and another lane line, θ is the angle between the smart car’s forward direction and the orientation of the manhole cover.

在公式(2)中，对智能汽车行驶过程中的车道保持和绕障分别赋予了不同的权重，在智能汽车行驶过程中遇到障碍物时，为保持智能汽车行驶过程中的平稳性，绕障的比重大于车道保持的比重。其中，目标增强信号的数值为0，由公式(2)可知，θ值越小且智能汽车偏离车道中心线的位移越小，目标增强信号的数值越接近于0，系统记录驾驶过程中r最接近于0时的驾驶策略，在之后绕障的驾驶场景中对该驾驶策略进行进一步优化，以得到最优化的驾驶策略。In formula (2), different weights are assigned to the lane keeping and obstacle avoidance during the driving process of the smart car. The proportion of obstacles is greater than the proportion of lane keeping. Among them, the value of the target enhancement signal is 0. From the formula (2), it can be seen that the smaller the value of θ and the smaller the displacement of the smart car from the center line of the lane, the closer the value of the target enhancement signal is to 0. When the driving strategy is close to 0, the driving strategy is further optimized in the subsequent driving scene of obstacle avoidance to obtain the optimal driving strategy.

实施例三Embodiment three

参见图2和图3，本发明实施例提供了一种智能汽车，该智能汽车应用实施例一中所述的自动绕障系统。Referring to FIG. 2 and FIG. 3 , an embodiment of the present invention provides a smart car, which applies the automatic obstacle avoidance system described in Embodiment 1.

本发明通过在智能汽车前部设置障碍物信息采集模块，以获取智能汽车所在车道内且位置智能汽车前方预设范围内的障碍物信息，通过自动驾驶控制模块根据障碍物信息判断智能汽车是否能由障碍物的旁边通过，并在判断智能汽车不能够从障碍物的旁边通过时，控制智能汽车由障碍物上方通过，并使智能汽车由障碍物上方通过时，智能汽车的两个前轮和两个后轮均位于障碍物外侧，从而避免智能汽车在行驶过程中因遇到障碍物而发生颠簸，保证乘员的舒适感。In the present invention, an obstacle information collection module is set at the front of the smart car to obtain information about obstacles in the lane where the smart car is located and within a preset range in front of the smart car, and the automatic driving control module judges whether the smart car can Pass by the side of the obstacle, and when it is judged that the smart car cannot pass by the side of the obstacle, control the smart car to pass by the obstacle, and when the smart car passes by the obstacle, the two front wheels of the smart car and The two rear wheels are located on the outside of the obstacle, so as to prevent the smart car from bumping when it encounters obstacles during driving, and ensure the comfort of the occupants.

上述本发明实施例序号仅仅为了描述，不代表实施例的优劣。The serial numbers of the above embodiments of the present invention are for description only, and do not represent the advantages and disadvantages of the embodiments.

以上所述仅为本发明的较佳实施例，并不用以限制本发明，凡在本发明的精神和原则之内，所作的任何修改、等同替换、改进等，均应包含在本发明的保护范围之内。The above descriptions are only preferred embodiments of the present invention, and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included in the protection of the present invention. within range.

Claims (8)

1. a kind of automatically around barrier system, which is characterized in that the system comprises:
Obstacle information acquisition module, setting is in intelligent automobile front, in lane where obtaining intelligent automobile and positioned at intelligence Obstacle information in energy vehicle front preset range, the barrier are included in vertically or approximately perpendicular to the intelligent automobile Width on the lane line direction in place lane be less than the well lid of the distance between two front-wheels of the intelligent automobile, pit, Mound or sand drift, the maximum height of the barrier are lower than the height on intelligent automobile chassis, and the obstacle information includes described The position of barrier and geometry；
Automatic Pilot control module is connect with the obstacle information acquisition module, for according to the obstacle information, judgement Whether the intelligent automobile can be in the lane by passing through beside the barrier；
If judging, the intelligent automobile can pass through beside the barrier in the lane, control the intelligent vapour Vehicle can be travelled into the lane by the side of the barrier；
If judging, the intelligent automobile can not pass through beside the barrier in the lane, control the intelligence Automobile above the barrier by passing through, and when making the intelligent automobile by passing through above the barrier, the intelligent automobile Two front-wheels and two rear-wheels be respectively positioned on the outside of the barrier；
Different enhancing signal algorithms is set for different Driving Scenes, according to the practical ginseng in the intelligent automobile driving procedure Number calculates enhancing signal, and calculates the absolute value of the difference of each the enhancing signal and targets improvement signal, according to described absolute It is worth reduced direction and optimizes driving strategy,
Wherein, before the obstacle information acquisition module does not collect lane where the intelligent automobile and is located at intelligent automobile There are when the barrier in square preset range, the enhancing signal is obtained by following first formula:
Wherein, r is the enhancing signal, d1It is the intelligent automobile at a distance from a lane line, d2For the intelligent automobile with The distance of another lane line,
Wherein, the numerical value of the targets improvement signal is that the numerical value of 0, r more levels off to 0, shows the intelligent vehicle running process In central axes closer to lane center, driving strategy when recording r in driving procedure closest to 0, later without around The driving strategy is advanced optimized in the Driving Scene of barrier, with the driving strategy optimized.
2. system according to claim 1, which is characterized in that the system also includes:
Lane line information acquisition module is connect with the automatic Pilot control module, for vehicle where obtaining the intelligent automobile The location information of two lane lines in road.
3. system according to claim 2, which is characterized in that the lane line information acquisition module includes:
The front of the intelligent automobile is arranged in first camera, includes two of lane where the intelligent automobile for shooting The image of lane line；
First image processing unit is connect with first camera, for carrying out to the image comprising two lane lines Processing, obtains the relative position information of the intelligent automobile Yu the lane line.
4. system according to claim 3, which is characterized in that the obstacle information acquisition module includes:
Second camera is arranged in the intelligent automobile front, for shooting the image comprising the barrier；
Second image processing unit is connect with the second camera and the first image processing unit respectively, for packet Image containing the barrier is handled, and in conjunction with the relative position information of the intelligent automobile and the lane line, is obtained The relative position information of the geometry information of the barrier and the barrier and the intelligent automobile and the lane line.
5. system according to claim 4, which is characterized in that first camera and the second camera are respectively provided with On the front windshield of the intelligent automobile.
6. a kind of automatically around barrier method, applied to automatic around hindering system as described in any one of claim 1-5 claim, It is characterized in that, which comprises
Obstacle information where obtaining intelligent automobile in lane and within the scope of intelligent automobile front preset, the barrier It is less than the intelligent vapour including the width on vertical or lane line direction approximately perpendicular to lane where the intelligent automobile Well lid, pit, mound or the sand drift of the distance between two front-wheels of vehicle, the obstacle information include the position of the barrier It sets and geometry；
According to the obstacle information, judge whether the intelligent automobile can be led in the lane by the side of the barrier It crosses；
If judging, the intelligent automobile can pass through beside the barrier in the lane, control the intelligent vapour Vehicle can be travelled into the lane by the side of the barrier；
If judging, the intelligent automobile can not pass through beside the barrier in the lane, control the intelligence Automobile above the barrier by passing through, and when making the intelligent automobile by passing through above the barrier, the intelligent automobile Two front-wheels and two rear-wheels be respectively positioned on the outside of the barrier；
Different enhancing signal algorithms is set for different Driving Scenes, according to the practical ginseng in the intelligent automobile driving procedure Number calculates enhancing signal, and calculates the absolute value of the difference of each enhancing signal and targets improvement signal, according to enhancing signal and mesh The direction that the absolute value of the difference of mark enhancing signal reduces optimizes driving strategy,
Wherein, when the obstacle information acquisition module does not collect the intelligent automobile place lane and is located at the intelligent vapour There are when the barrier in the preset range of front side, the enhancing signal is obtained by following first formula:
Wherein, r is the enhancing signal, d1It is the intelligent automobile at a distance from a lane line, d2For the intelligent automobile with The distance of another lane line,
Wherein, the numerical value of the targets improvement signal is that the numerical value of 0, r more levels off to 0, shows the intelligent vehicle running process In central axes closer to lane center, driving strategy when recording r in driving procedure closest to 0, later without around The driving strategy is advanced optimized in the Driving Scene of barrier, with the driving strategy optimized.
7. according to the method described in claim 6, judging the intelligence it is characterized in that, described according to the obstacle information Whether automobile can be in the lane by passing through beside the barrier, comprising:
Obtain the relative position information of the barrier Yu the lane line；
According to the relative position information of the barrier and the lane line, and in conjunction with the geometry information of the barrier, Compare two front-wheels of the edge of the barrier to the distance between two lane lines in the lane with the intelligent automobile The distance between size, if the edge of the barrier is greater than institute to the distance between at least one lane line in the lane The distance between two front-wheels for stating intelligent automobile then judge that the intelligent automobile can be in the lane from the barrier Side pass through, if the edge of the barrier is respectively less than the intelligent vapour to the distance between two lane lines in the lane The distance between two front-wheels of vehicle then judge that the intelligent automobile can not be in the lane from the side of the barrier Pass through.
8. a kind of intelligent automobile, which is characterized in that the intelligent automobile includes as described in any one of claim 1-5 claim It is automatic around barrier system.
CN201710183810.9A 2017-03-24 2017-03-24 An automatic obstacle avoidance system and method, and a smart car Active CN106864458B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710183810.9A CN106864458B (en) 2017-03-24 2017-03-24 An automatic obstacle avoidance system and method, and a smart car

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710183810.9A CN106864458B (en) 2017-03-24 2017-03-24 An automatic obstacle avoidance system and method, and a smart car

Publications (2)

Publication Number Publication Date
CN106864458A CN106864458A (en) 2017-06-20
CN106864458B true CN106864458B (en) 2019-12-03

Family

ID=59172961

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710183810.9A Active CN106864458B (en) 2017-03-24 2017-03-24 An automatic obstacle avoidance system and method, and a smart car

Country Status (1)

Country Link
CN (1) CN106864458B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US12272153B2 (en) 2019-12-20 2025-04-08 Zoox, Inc. In-path obstacle detection and avoidance system

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109829351B (en) * 2017-11-23 2021-06-01 华为技术有限公司 Lane information detection method, device and computer readable storage medium
CN108627135A (en) * 2018-04-28 2018-10-09 惠州市德赛西威汽车电子股份有限公司 A kind of method and system for the road conditions that are recessed by front
CN109533154B (en) * 2018-12-07 2020-10-16 纳恩博（北京）科技有限公司 Scooter
CN110550029B (en) 2019-08-12 2021-02-09 华为技术有限公司 Obstacle avoidance method and device
CN110887488A (en) * 2019-11-18 2020-03-17 天津大学 Unmanned rolling machine positioning method
CN111409630A (en) * 2020-04-13 2020-07-14 新石器慧通（北京）科技有限公司 Vehicle obstacle avoidance method, system and device
CN111554093A (en) * 2020-05-15 2020-08-18 无锡北斗星通信息科技有限公司 Real-time analysis system and method for traffic reference data
CN111806433B (en) * 2020-06-09 2022-07-12 宁波吉利汽车研究开发有限公司 Obstacle avoidance method, device and equipment for automatically driven vehicle

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101398783B1 (en) * 2013-01-11 2014-05-27 한국과학기술원 Obstacle avoidance detection system and method using driver attention and direction of front car for semi-active safety
CN104276174A (en) * 2013-07-03 2015-01-14 沃尔沃汽车公司 A vehicle system, a vehicle and a method for autonomous road irregularity avoidance
CN105223952A (en) * 2015-09-28 2016-01-06 小米科技有限责任公司 The control method of balance car and device
CN105620474A (en) * 2016-01-26 2016-06-01 吉林大学 Active obstacle avoiding method for four-wheel hub drive electric automobile with multiple modes
CN106394555A (en) * 2016-08-29 2017-02-15 无锡卓信信息科技股份有限公司 Unmanned automobile obstacle avoidance system and method based on 3D camera
CN106515728A (en) * 2016-12-22 2017-03-22 深圳市招科智控科技有限公司 System and method for avoiding collision and obstacle for a driverless bus

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101398783B1 (en) * 2013-01-11 2014-05-27 한국과학기술원 Obstacle avoidance detection system and method using driver attention and direction of front car for semi-active safety
CN104276174A (en) * 2013-07-03 2015-01-14 沃尔沃汽车公司 A vehicle system, a vehicle and a method for autonomous road irregularity avoidance
CN105223952A (en) * 2015-09-28 2016-01-06 小米科技有限责任公司 The control method of balance car and device
CN105620474A (en) * 2016-01-26 2016-06-01 吉林大学 Active obstacle avoiding method for four-wheel hub drive electric automobile with multiple modes
CN106394555A (en) * 2016-08-29 2017-02-15 无锡卓信信息科技股份有限公司 Unmanned automobile obstacle avoidance system and method based on 3D camera
CN106515728A (en) * 2016-12-22 2017-03-22 深圳市招科智控科技有限公司 System and method for avoiding collision and obstacle for a driverless bus

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US12272153B2 (en) 2019-12-20 2025-04-08 Zoox, Inc. In-path obstacle detection and avoidance system

Also Published As

Publication number Publication date
CN106864458A (en) 2017-06-20

Similar Documents

Publication Publication Date Title
CN106864458B (en) An automatic obstacle avoidance system and method, and a smart car
US11373532B2 (en) Pothole detection system
CN106485233B (en) Driving area detection method, device and electronic device
CN108647638B (en) Vehicle position detection method and device
US9235767B2 (en) Detection region modification for driving assistance apparatus and driving assistance method
CN105678787A (en) Heavy-duty lorry driving barrier detection and tracking method based on binocular fisheye camera
JP3925488B2 (en) Image processing apparatus for vehicle
US20250200985A1 (en) Methods and apparatus for acquisition and tracking, object classification and terrain inference
CN109987082B (en) Vehicle control device, vehicle control method, and storage medium
CN101135558A (en) A method and device for vehicle collision avoidance warning based on machine vision
CN101131321A (en) A method and device for real-time measurement of safe vehicle distance for vehicle collision avoidance warning
US10108866B2 (en) Method and system for robust curb and bump detection from front or rear monocular cameras
JP2020201746A (en) Distance estimation device, distance estimation method, and distance estimation computer program
CN110045736A (en) A kind of curve barrier preventing collision method and its system based on unmanned plane
CN105205805A (en) Vision-based intelligent vehicle transverse control method
US11386568B2 (en) Method and device for determining a quality of a surface in the surroundings of a transportation vehicle
CN107220632B (en) A road image segmentation method based on normal feature
CN113353071B (en) Narrow area intersection vehicle safety auxiliary method and system based on deep learning
US20200193184A1 (en) Image processing device and image processing method
CN113978456B (en) Reversing image display method with target display
CN114815835A (en) An artificial intelligence-based AGV adaptive turning obstacle avoidance device
CN118565526B (en) Range finding compensation method and device under jolt working condition, storage medium and electronic equipment
JP2024035512A (en) Compartment line recognition device
CN118584464B (en) Vehicle distance measurement method and device, storage medium and electronic equipment
US20250258294A1 (en) Object detection apparatus

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
TR01 Transfer of patent right

Effective date of registration: 20220221

Address after: 241006 Anshan South Road, Wuhu Economic and Technological Development Zone, Anhui Province

Patentee after: Wuhu Sambalion auto technology Co.,Ltd.

Address before: 241006 Changchun Road, Wuhu economic and Technological Development Zone, Wuhu, Anhui, 8

Patentee before: CHERY AUTOMOBILE Co.,Ltd.

TR01 Transfer of patent right
TR01 Transfer of patent right

Effective date of registration: 20251204

Address after: 241006 Wuhu economic and Technological Development Zone, Anhui, No. 8 Changchun Road

Patentee after: CHERY AUTOMOBILE Co.,Ltd.

Country or region after: China

Address before: 241006 Anshan South Road, Wuhu Economic and Technological Development Zone, Anhui Province

Patentee before: Wuhu Sambalion auto technology Co.,Ltd.

Country or region before: China

TR01 Transfer of patent right