Autonomous Vehicle Site Test Using Simulated Obstacles

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current autonomous vehicle testing on real roads is unsafe due to complex and dangerous conditions, which can lead to accidents and damage.

Innovation Solution

A method and apparatus for simulating obstacles in a controlled test site, where state information of the autonomous vehicle is collected in real-time to deploy simulated obstacles, such as people, vehicles, or traffic lights, to test the vehicle's response performance in a controlled environment.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If autonomous vehicle testing is conducted on real roads to improve test accuracy, then the test reflects real road conditions, but the safety of testing deteriorates due to complex and dangerous real road conditions

Engineering Contradiction:
Improvetest accuracyVSAvoidtest safety
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

The patent creates a virtual copy of the real road environment through building a three-dimensional map and simulating road conditions, obstacles, and traffic scenarios in a virtual space. This allows testing to be conducted on a replicated environment rather than the actual road, maintaining test accuracy while eliminating safety risks associated with real road testing

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The patent introduces a virtual environment as an intermediary between the autonomous vehicle and the real road. The vehicle operates in a virtual space that mediates the interaction between the testing system and real-world conditions, allowing safe testing while preserving the ability to evaluate real road performance

Inventive Principle:
Principle #24Intermediary (Mediator)

2Reliability

If simulated obstacles are deployed to improve test safety, then human safety and vehicle damage are avoided, but the complexity of the testing system increases

Engineering Contradiction:
Improvetest safetyVSAvoidtesting system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent uses virtual copies of obstacles and road elements in a three-dimensional map rather than physical simulations. This digital replication approach simplifies the system compared to building physical test environments while maintaining the ability to safely test obstacle detection and response

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The patent replaces physical/mechanical test environments with a computer-based virtual simulation system. Instead of using physical obstacles and real roads, the system uses digital representations controlled by software, reducing mechanical complexity while enabling safe and repeatable testing

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS10814884B2Autonomous vehicle site test method and apparatus, device and readable medium
Publication Date: 2020.10.27 APOLLO INTELLIGENT DRIVING (BEIJING) TECHNOLOGY CO LTD
  • US10814884B2 patent drawing
  • US10814884B2 patent drawing
  • US10814884B2 patent drawing

AI summary

The present disclosure provides an autonomous vehicle site test method and apparatus, a device and a readable medium. The method comprises: in a site test, collecting state information of the autonomous vehicle in real time; according to the state information of the autonomous vehicle and a pre-obtained test demand, obtaining deployment information of a simulated obstacle needed in the test, wherein the deployment information of the simulated obstacle includes a simulated obstacle class, a deployment location of the simulated obstacle and a predetermined action of the simulated obstacle; according to the deployment information of the simulated obstacle, controlling the simulated obstacle corresponding to the simulated obstacle class to perform a predetermined action at the deployment location, to test the autonomous vehicle's response performance to the deployed simulated obstacle.