Supercharge Your Innovation With Domain-Expert AI Agents!

Obstacle avoidance prediction method based on speed obstacle model and collision probability density model

A speed obstacle and collision probability technology, applied in the field of obstacle avoidance prediction based on the speed obstacle model/collision probability density model, can solve problems such as increasing computational complexity, and achieve the effect of reducing fatigue and complexity.

Active Publication Date: 2020-05-29
SHANGHAI UNIV OF ENG SCI
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The existing anti-collision prediction research is mainly based on machine vision and sensor methods, so that the vehicle can safely and autonomously drive to the destination in an unknown complex environment. However, with the development of the times, commercial use is inevitable, which requires Consider the cost of sensors and on-board computers
The study by Fulgenzi et al. uses Bayesian Occupancy Filter (BOF) to represent obstacle vehicles, estimates the speed of obstacle vehicles in unknown environment, and uses probabilistic velocity obstacles (PVOs) to find the safe speed of itself, but the corresponding The computational complexity has also increased a lot

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 avoidance prediction method based on speed obstacle model and collision probability density model
  • Obstacle avoidance prediction method based on speed obstacle model and collision probability density model
  • Obstacle avoidance prediction method based on speed obstacle model and collision probability density model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0063] Such as figure 2 As shown, the speed obstacle model is established by the following method: suppose the own vehicle is the mass point A, the puffing treatment of the obstacle vehicle is circle O, and the radius of circle O is R 1 Is the sum of the larger size of the length and width of the obstacle vehicle and the larger size of the length and width of the own vehicle. The distance between the mass point A and the circle O is the distance between the own vehicle and the obstacle. Point A leads two rays L 1 And L 2 , Respectively circumscribe both sides of circle O, L 1 And L 2 The sandwiched conical surface forms a speed obstacle cone, and the speed vector of the own vehicle is v A , The speed vector of the obstacle vehicle is v O , Then the relative speed vector of the own vehicle relative to the obstacle vehicle is v AO .

[0064] Based on the speed obstacle model, the on-board controller determines the possibility of collision between its own vehicle and the obstacle ve...

Embodiment 2

[0066] Such as Figure 3~5 As shown, the collision probability density model is established by the following method:

[0067] Ⅰ. Calculation of acceleration a of own vehicle: such as image 3 As shown, the current own vehicle is driving at acceleration a, and the centripetal acceleration is a N , The tangential acceleration is a T ;

[0068] Centripetal acceleration of own vehicle a N The calculation formula is as follows:

[0069]

[0070] Among them: v is the current driving speed of the own vehicle, ρ(s) is the radius of the path trajectory arc of the own vehicle, which are all obtained by the on-board controller through the on-board sensing module. When ρ(s) is 0, the own vehicle is currently traveling in a straight line When, mark it as a N =0;

[0071] Tangential acceleration of own vehicle a T The formula for the relationship with the rate of change of velocity v is as follows:

[0072]

[0073] Where: k 1 And k 2 Are given constant values, k 1 Is the rolling friction coefficie...

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

The invention discloses an obstacle avoidance pre-judging method based on a speed obstacle model / collision probability density model. The obstacle avoidance pre-judging method comprises the followingsteps: S1, a vehicle-mounted sensing module of a self vehicle monitors the speed and relative position information within the set time period of the self vehicle and an obstacle vehicle in the set range by taking the self vehicle as the center and passes the speed and relative position information back to a vehicle-mounted controller; S2, the vehicle-mounted controller judges whether the self vehicle and the obstacle vehicle simultaneously move at a constant speed or not and establishes a correlation model; S3, the vehicle-mounted controller judges the collision possibility of the self vehicleand the obstacle vehicle; S4, the vehicle-mounted controller gives an alarm prompt and / or controls the self vehicle to have obstacle avoidance operation or directly goes to the step 5; and S5, the steps 1-4 are repeated until the obstacle vehicle does not exist in the set range. According to the obstacle avoidance pre-judging method, the three-dimensional realistic environment is subject to two-dimensional treatment, so that the calculating complexity level is greatly lowered; and based on intelligent driving, the degree of fatigue of a driver is greatly lowered to assist in driving.

Description

Technical field [0001] The invention relates to the field of intelligent driving, in particular to an obstacle avoidance prediction method based on a speed obstacle model / collision probability density model. Background technique [0002] Vehicle anti-collision prediction is a research hotspot in the field of intelligent driving in recent years. In order to ensure the safe driving of vehicles in a complex environment, it is not only necessary to rely on people to identify emergencies around the vehicle, but also to rely on the vehicle to sense through various sensors. Vehicles that may collide around can provide early warning and rapid response to avoid obstacles in time. [0003] The existing anti-collision prediction research is mainly based on machine vision and sensor methods, so that vehicles can safely and autonomously drive to the destination in an unknown and complex environment. However, with the development of the times, commercial use is inevitable. Consider the cost of ...

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): B60W30/095
CPCB60W30/0953B60W2520/10B60W2520/105
Inventor 陆林东张伟伟
Owner SHANGHAI UNIV OF ENG SCI
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com