Autonomous Car Path Planning With Layered Trajectory Replanning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicle navigation systems face challenges in quickly planning and re-planning trajectories to optimize travel time and safety, as existing methods impose significant computational overhead due to the need for frequent recalculations and obstacle avoidance.
Innovation Solution
A tripartite path-planning system comprising a global planner, a fast local planner with simplified vehicle dynamics, and a local planner with advanced vehicle dynamics, which rapidly calculates and updates trajectories to ensure safety and minimize computational load, using Vehicle-to-Everything (V2X) communication and Model Predictive Control (MPC) to handle dynamic environments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If frequent trajectory recalculation is performed to ensure safety and optimize travel time, then navigation reliability and response time improve, but computational overhead increases and processing speed decreases
Solution Approach 1:
The patent divides the path planning system into three distinct planners operating at different levels: a global planner for long-term route optimization, a local planner for medium-term trajectory adjustments, and a reactive planner for immediate obstacle avoidance. This segmentation allows each planner to operate with appropriate computational complexity for its time scale, reducing overall computational overhead while maintaining navigation reliability through coordinated operation across all three levels.
2Measurement precision
If advanced vehicle dynamics models are used in all planners, then trajectory accuracy and safety improve, but computational load increases significantly
Solution Approach 1:
The patent applies different levels of vehicle dynamics model complexity to different planners based on their specific needs. The global planner uses simplified models suitable for long-term route planning, the local planner uses moderate complexity models for trajectory adjustments, and only the reactive planner employs advanced vehicle dynamics models for immediate safety-critical decisions. This local quality approach ensures trajectory accuracy where needed while minimizing computational load overall.
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.