Autonomous Vehicle MRM Control for Collision-Aware Safe Stopping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous driving systems may enter dangerous states if abnormalities occur and appropriate measures are not taken to rectify them, posing risks to vehicle safety.
Innovation Solution
An autonomous driving vehicle equipped with sensors and a processor that determines a minimum risk maneuver (MRM) strategy based on vehicle state and surrounding environment information when normal driving is impossible, selecting an MRM type to minimize collision risks by calculating safe distances and considering road shoulders and lane detection capabilities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the vehicle performs a minimal risk maneuver (MRM) to remove risk when normal autonomous driving is impossible, then vehicle safety is improved, but the complexity of the control system increases
Solution Approach 1:
The system performs preliminary detection of abnormalities in the autonomous driving system before they can lead to dangerous states. The processor continuously monitors system status and detects issues early, enabling proactive intervention through MRM before the situation escalates to a safety-critical event.
Solution Approach 2:
The system implements a safety buffer by detecting abnormalities and transitioning to MRM in advance, creating a protective buffer between normal operation and dangerous states. This cushioning approach allows the system to handle failures gracefully by having pre-planned fallback maneuvers that prevent catastrophic outcomes.
2Object-affected harmful factors
If the processor determines MRM type based on collision possibility with neighboring vehicles, then collision risk is reduced, but the processing time and computational load increase
Solution Approach 1:
The system applies different evaluation criteria to different spatial zones around the vehicle. It specifically focuses on neighboring vehicles in front and on the front-lateral side, calculating longitudinal and lateral safe distances for these critical areas. This localized approach concentrates computational resources on the most dangerous directions rather than uniformly processing all surrounding areas.
Solution Approach 2:
The system dynamically adjusts safety distance parameters based on the specific MRM type being evaluated. Different MRM types have different required safe distances, and the processor modifies these parameters in real-time based on the chosen maneuver, allowing efficient comparison of collision risks across multiple MRM options without fixed rigid thresholds.
3Measurement precision
If the vehicle calculates longitudinal and lateral safe distances to determine collision possibility, then maneuver selection accuracy is improved, but the computational complexity increases
Solution Approach 1:
The safety distance calculation is segmented into two independent components: longitudinal safe distance and lateral safe distance. This segmentation allows the system to evaluate safety in the forward direction separately from side directions, simplifying the overall computational task while maintaining comprehensive coverage of collision risks in different spatial dimensions.
Data Source
AI summary
A vehicle for autonomous driving is capable of performing a minimum risk maneuver. The vehicle includes: at least one sensor, a processor and a controller, where the processor may detect whether a minimum risk maneuver (MRM) is required based on at least one of surrounding environment information and vehicle state information during autonomous driving of the vehicle, determine an MRM type based on a possibility of colliding with a neighboring vehicle when the MRM is required, and control to stop the vehicle based on the determined MRM type.