Vehicle Collision Avoidance with Independent Trajectory Validation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing autonomous vehicle collision detection systems can be inoperable or ineffective due to errors in complex processing pipelines, leading to unsafe vehicle maneuvers.
Innovation Solution
Implement a secondary system that independently localizes the vehicle, detects objects, predicts trajectories, and validates primary system outputs to ensure collision avoidance, including a trajectory manager that evaluates and selects safe trajectories to control the vehicle.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Difficulty of detecting and measuring
If a complex processing pipeline is used for collision detection, then detection capability is improved, but system reliability deteriorates due to potential errors
Solution Approach 1:
The system divides the collision detection function into two independent segments: a primary system that performs comprehensive processing and a secondary system that performs independent validation. Each system operates separately with its own processing pipeline, allowing the complex detection capability to be maintained while reducing the risk of systematic errors affecting the entire system.
Solution Approach 2:
The secondary system acts as an intermediary validation layer between the primary system and the vehicle control. It independently verifies the primary system's outputs and can override them if errors are detected, serving as a mediator that ensures reliability without compromising the primary detection capability.
2Reliability
If a secondary validation system is added, then collision avoidance reliability is improved, but device complexity increases
Solution Approach 1:
The validation function is extracted as a separate, dedicated secondary system rather than being integrated into the primary system. This extraction allows the validation logic to be independently developed, tested, and maintained, improving reliability while making the overall system architecture more manageable despite the increased complexity.
Solution Approach 2:
The secondary system creates a simplified copy or model of the primary system's detection logic to independently validate its outputs. Rather than fully replicating the complex primary system, it uses analogous processing pipelines that are sufficient for validation purposes, thereby improving reliability without proportionally increasing complexity.
Data Source
AI summary
A vehicle may include a primary system for generating data to control the vehicle and a secondary system that validates the data and/or other data to avoid collisions. For example, the primary system may localize the vehicle, detect an object around the vehicle, predict an object trajectory, and generate a trajectory for the vehicle. The secondary system may localize the vehicle, detect an object around the vehicle, predict an object trajectory, and evaluate a trajectory generated by the primary system. The secondary system may also monitor components of the vehicle to detect an error. If the secondary system detects an error with a trajectory generated by the primary system and/or an error with a component of the vehicle, the secondary system may cause the vehicle to perform a maneuver, such as decelerating, changing lanes, swerving, etc.