Parallel Obstacle Buffers for Road-Centered Path Planning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous driving vehicles face challenges in maintaining a safe buffer distance from obstacles while avoiding being too far away from the road center during path planning, which affects their navigation efficiency and safety.
Innovation Solution
The implementation of a parallel obstacle buffer system using quadratic programming (QP) to generate multiple paths with varying buffer distances, allowing multiple threads to calculate paths in parallel, and selecting the path with the smallest successful buffer distance to ensure safe navigation while staying close to the road center.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a large buffer distance is maintained from obstacles, then safety is improved, but the vehicle becomes too far from the road center affecting navigation efficiency
Solution Approach 1:
The system dynamically adjusts the buffer distance from obstacles based on real-time conditions. Multiple threads calculate different buffer distances (from minimum to maximum) and select the optimal path that balances safety and efficiency, allowing the buffer to be adaptive rather than fixed.
Solution Approach 2:
The system changes the buffer distance parameter across multiple parallel calculations. By computing paths with varying buffer distances simultaneously and selecting the best result, the system optimizes both safety (larger buffer) and navigation efficiency (smaller buffer closer to road center).
2Measurement precision
If multiple paths with different buffer distances are calculated sequentially, then path planning accuracy is improved, but calculation time increases
Solution Approach 1:
The system uses dynamic parallel processing where multiple path calculation threads run simultaneously instead of sequentially. This maintains high path planning accuracy through multiple buffer distance calculations while reducing total calculation time through parallel execution.
Solution Approach 2:
The system maintains continuous useful action by having multiple threads calculate different paths in parallel without idle time. All buffer distance calculations occur simultaneously, eliminating the sequential waiting time and maintaining continuous productive computation.
Data Source
AI summary
A path planning of the ADV is performed. A set of obstacle boundaries are generated for one or more obstacles, where each of the set of obstacle boundaries has a corresponding buffer distance ranging from a predetermined minimum buffer distance to a predetermined maximum buffer distance. A set of paths of the ADV is generated using quadratic programming based on the set of obstacle boundaries in parallel, where each path of the set of paths corresponds to one of the set of obstacle boundaries. A path is selected from successful paths of the set of paths based on a corresponding obstacle boundary having a smallest corresponding buffer distance, where the ADV is at least a predetermined distance away from the one or more obstacles in the successful paths. The ADV is controlled to drive autonomously according the selected path to avoid the one or more obstacles.