Autonomous Vehicle Avoidance Control with Dual Passing Constraints
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current avoidance control methods for autonomous driving vehicles lack rationality and stability, often resulting in conservative and human-unlike decision-making, especially when faced with sudden dangers, leading to instability and poor passenger experience.
Innovation Solution
Implementing an avoidance control method that uses outer and inner soft constraints based on target object appearance and speed information to determine passing areas, allowing the vehicle to avoid obstacles while maintaining a safe distance and direction away from them, with visual feedback to users.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If avoidance control is implemented to prevent collision with target objects, then safety is improved, but the stability and rationality of avoidance behavior deteriorates due to sudden and sensitive control responses
Solution Approach 1:
The patent divides the avoidance control into two distinct constraint layers: outer constraints that define the boundary of the target object's occupation area, and inner constraints that define a safety margin area inside the outer constraint. This segmentation allows the system to first ensure basic collision avoidance through outer constraints, then enhance stability and rationality through inner constraints that guide the vehicle to maintain a safer distance from the target object, avoiding sudden and sensitive responses.
2Stability of the object's composition
If the vehicle maintains a larger safety distance from target objects, then stability and rationality of avoidance behavior is improved, but the passing area available for maneuvering is reduced
Solution Approach 1:
The patent implements dynamic constraint adjustment based on the relative motion state between the autonomous vehicle and the target object. When the target object is moving away or stationary, the inner constraint allows the vehicle to approach closer, maximizing the passing area. When the target object is moving towards the vehicle or in a state that increases collision risk, the inner constraint automatically expands to maintain a larger safety distance. This dynamic adjustment resolves the contradiction by adapting the safety margin to the actual risk level, ensuring stability when needed while preserving maneuvering space when safe.
Data Source
AI summary
An intelligent device may determine a first constraint of avoidance control based on first information of the target object in a surrounding environment of the intelligent device, where the first constraint indicates a first passing area in which the intelligent device avoids the target object; and determine a second constraint of avoidance control based on second information of the target object, where the second constraint indicates a second passing area that is in the first passing area and in which the intelligent device is away from the target object. Based on the first constraint and the second constraint, the intelligent device can keep the vehicle away from the target object as far as possible while ensuring safety by avoidance.