Simulation Vehicle Region Control for Parallel Multi-Vehicle Testing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current automatic driving simulation methods are inefficient due to reliance on fixed scene models with short distances, lack of stability and reliability in long-period simulations, and limited verification of interactions among multiple vehicles, leading to resource idleness and slow calculation speeds.

Innovation Solution

A method for controlling simulation vehicles by determining environment information for specific regions and adjacent areas, allowing for parallel calculation and reducing the need for synchronization across all vehicles, thereby improving calculation efficiency and resource utilization.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If all vehicles complete calculation and synchronize results before next simulation moment, then simulation accuracy is maintained, but calculation efficiency decreases and resources become idle

Engineering Contradiction:
Improvesimulation accuracyVSAvoidcalculation efficiency
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The simulation system divides the calculation process into segments based on spatial regions. Each region's vehicles are calculated independently without requiring synchronization with all other vehicles in the system. This segmentation allows parallel processing across regions, maintaining accuracy within each region while eliminating system-wide synchronization waits, thus resolving the contradiction between reliability and productivity.

Inventive Principle:
Principle #1Segmentation

2Speed

If simulation uses fixed scene model with short distance, then calculation speed is fast, but stability and reliability verification under long period running is insufficient

Engineering Contradiction:
Improvecalculation speedVSAvoidsimulation duration
Core Design Contradiction:
SpeedVSDuration of action of stationary object

Solution Approach 1:

The scene model transitions from a fixed static structure to a dynamic one where the simulation range extends indefinitely in the vehicle's traveling direction. The scene updates dynamically as vehicles move, maintaining computational efficiency by only processing relevant regions while enabling long-duration simulations. This dynamic approach preserves calculation speed while allowing extended simulation periods for stability verification.

Inventive Principle:
Principle #15Dynamics

3Quantity of substance

If only one vehicle is simulated with others as obstacles, then calculation resources are reduced, but verification ability for interaction and overtaking among multiple vehicles is lost

Engineering Contradiction:
Improvenumber of vehiclesVSAvoidinteraction verification ability
Core Design Contradiction:
Quantity of substanceVSReliability

Solution Approach 1:

The system applies local quality by making obstacle vehicles in the control vehicle's region fully interactive with verification capabilities, while vehicles in other regions can be treated as simpler obstacles. This localized enhancement of interaction quality in critical regions maintains verification ability for important scenarios while avoiding the computational overhead of full interaction across all vehicles, thus balancing quantity and reliability.

Inventive Principle:
Principle #3Local quality

Data Source

PatentEP3913596B1Method for controlling simulation vehicle and electronic device
Publication Date: 2023.11.01 APOLLO INTELLIGENT DRIVING (BEIJING) TECHNOLOGY CO LTD
  • EP3913596B1 patent drawingFigure 1
  • EP3913596B1 patent drawingFigure 2~3
  • EP3913596B1 patent drawingFigure 4~5

AI summary

The present disclosure disclose a method for controlling a simulation vehicle and an electronic device. In the method, a simulation vehicle determines a first region corresponding to a first simulation position where the simulation vehicle is located at a first time point; obtains first environment information about the first region and second environment information about a second region adjacent to the first region; sends the first environment information and the second environment information to a control device of the simulation vehicle; and determines a first action performed by the simulation vehicle at a second time point after the first time point based on a control signal in response to receiving the control signal from the control device, the control signal being determined by the control device based on the first environment information and the second environment information. In this way, the calculation efficiency is improved and resources idleness is avoided.