Multi-Layer Path Planning for Fast Autonomous Vehicle Replanning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing autonomous navigation systems face challenges in quickly planning and re-planning vehicle trajectories to optimize travel time and safety, especially when encountering obstacles and needing to overtake other vehicles.
Innovation Solution
A tripartite path-planning system comprising a global planner, a fast local planner with a simplified vehicle dynamics model, and a local planner with an advanced vehicle dynamics model, which work together to rapidly calculate and update optimal trajectories while ensuring safety and handling limits.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a single comprehensive path planning system is used to ensure safety and optimize trajectories, then navigation reliability is improved, but computational overhead increases and processing speed decreases
Solution Approach 1:
The path planning system is divided into three independent planners operating at different levels: a global planner for overall route optimization, a local planner for immediate obstacle avoidance, and a recalculation planner for dynamic re-planning. Each planner handles specific aspects of navigation, reducing computational overhead while maintaining comprehensive safety coverage through coordinated operation.
2Reliability
If trajectory recalculation is performed frequently to adapt to new sensor data and obstacles, then navigation safety is improved, but computational resources are overwhelmed
Solution Approach 1:
The system implements dynamic recalculation strategies where the recalculation planner adapts the frequency and depth of trajectory recalculation based on real-time conditions. When obstacles are detected or sensor data changes significantly, intensive recalculation is triggered; during stable conditions, recalculation frequency is reduced, optimizing compute resource usage while maintaining safety.
Solution Approach 2:
The recalculation planner focuses computational resources on locally affected trajectory segments rather than recalculating the entire path. When an obstacle is detected, only the portion of the trajectory impacted by the obstacle and nearby segments are recalculated, preserving safety in critical areas while minimizing overall computational overhead.
3Speed
If a simplified vehicle dynamics model is used in the local planner to accelerate calculation, then processing speed is improved, but trajectory accuracy within handling limits deteriorates
Solution Approach 1:
The planning system uses different levels of vehicle dynamics models appropriate to each planning level. The global planner uses a simplified model for overall route optimization where precise handling limits are less critical, while the local planner and recalculation planner use more accurate dynamics models when calculating trajectories near the vehicle's current position where handling precision is most important for safety.
Data Source
AI summary
A multi-layer path-planning system and method calculates trajectories for autonomous vehicles using a global planner, a fast local planner, and an optimizing local planner. The calculated trajectories are used to guide the autonomous vehicle along a bounded path between a starting point and a destination.