Unlock instant, AI-driven research and patent intelligence for your innovation.

Obstacle detection method, device and vehicle

An obstacle detection and obstacle detection technology is applied in the fields of devices, vehicles, and obstacle detection methods, which can solve the problems of vehicles hitting the edge of parking spaces, inability to adapt to automatic driving scenarios, and insufficient accuracy of obstacle detection methods.

Active Publication Date: 2020-10-20
GUANGZHOU XIAOPENG MOTORS TECH CO LTD
View PDF17 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, if figure 1 As shown, when the vehicle follows the Picture 1-1 When driving in the direction shown, the vehicle is likely to hit the edge of the parking space; Figure 1-2 When driving in the direction shown, the vehicle may not hit the edge of the parking space due to the steering operation. In fact, it is not necessary to control the vehicle to change the original driving route at this time, and the operation of re-kneading the parking space is unnecessary.
[0004] It can be seen that the existing obstacle detection methods are not accurate enough to adapt to more complex autonomous driving scenarios

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Obstacle detection method, device and vehicle
  • Obstacle detection method, device and vehicle
  • Obstacle detection method, device and vehicle

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0086] see figure 2 , figure 2 It is a schematic flowchart of an obstacle detection method disclosed in an embodiment of the present invention. The detection device applicable to the obstacle detection method may be a vehicle-mounted detection device, specifically, electronic equipment such as a vehicle-mounted industrial computer, a vehicle-mounted computer, or a bottom controller of a vehicle such as an electronic control unit (Electronic Control Unit, ECU). The embodiments of the present invention are not limited. Such as figure 2 As shown, the obstacle detection method may include the following steps:

[0087] 101. The detection device acquires the expected trajectory of the vehicle to be driven.

[0088] In the embodiment of the present invention, the detection device can obtain the expected trajectory sent by the vehicle's trajectory planning module (such as the navigation module, etc.). It can be understood that the expected trajectory sent by the trajectory pla...

Embodiment 2

[0150] see Figure 5 , Figure 5 is a schematic flowchart of another obstacle detection method disclosed in the embodiment of the present invention. Such as Figure 5 As shown, the obstacle detection method may include the following steps:

[0151] 501. The detection device acquires the expected trajectory of the vehicle to be driven.

[0152] In the embodiment of the present invention, the expected trajectory is the trajectory under the Frenet coordinate system, and the specific implementation manner of converting the trajectory under the Cartesian coordinate system into the Frenet coordinate system can be as described in steps S11 to S14 or as described in steps S21 to S25. , the following content will not be repeated.

[0153] 502. The detection device performs longitudinal sampling on the expected trajectory along its tangential direction to obtain discrete trajectory points.

[0154] In the embodiment of the present invention, longitudinal sampling refers to sampling...

Embodiment 3

[0183] see Figure 10 , Figure 10 It is a schematic structural diagram of an obstacle detection device disclosed in an embodiment of the present invention. Such as Figure 10 As shown, the obstacle detection device may include:

[0184] An acquisition unit 601, configured to acquire an expected trajectory of the vehicle to be driven;

[0185] In the embodiment of the present invention, if the desired trajectory obtained from other units, modules or devices such as the trajectory planning module is a trajectory curve in the Cartesian coordinate system, then the desired trajectory can be first converted to the Frenet coordinate system;

[0186] As an optional implementation manner, the manner in which the acquiring unit 601 acquires the expected trajectory that the vehicle is about to travel may specifically be as follows:

[0187] The obtaining unit 601 is configured to use the least square method to fit the expected trajectory in the Cartesian coordinate system to the exp...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

An obstacle detection method, device, and vehicle, the method comprising: acquiring a desired trajectory that the vehicle is about to drive; constructing a trajectory detection range centered on the desired trajectory; detecting obstacles corresponding to obstacles within the trajectory detection range point; the distance required when the vehicle travels to a point-contact position with the obstacle according to the desired trajectory is taken as the relative distance between the obstacle and the vehicle. The implementation of the embodiment of the present invention can improve the accuracy of obstacle detection, and the calculation amount is small, which is more suitable for the bottom controller of the vehicle.

Description

technical field [0001] The invention relates to the technical field of intelligent driving, in particular to an obstacle detection method, device and vehicle. Background technique [0002] Currently, most of the advanced driver assistance systems (Advanced Driver Assistant System, ADAS) on the market can provide obstacle avoidance functions. Most of its principles are based on ultrasonic radar, laser radar and other sensors detecting the direction and position of obstacles relative to the vehicle, so as to determine the relative distance of obstacles relative to the vehicle. According to the relative distance between the obstacle and the vehicle, the ADAS system can generate a series of control strategies. For example, calculate the braking timing, braking force, steering angle, etc. of the vehicle. [0003] However, it has been found in practice that this detection method may have insufficient accuracy in complex environments, does not meet the vehicle kinematics constrai...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G08G1/16
CPCG08G1/16G08G1/165
Inventor 张超昱李弼超邓志权孙崇尚陈集辉李良
Owner GUANGZHOU XIAOPENG MOTORS TECH CO LTD