Two-Level Path Planning for Tractor-Trailer Obstacle Avoidance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles, particularly tractor-trailer trucks, face challenges in determining optimal paths through environments with varying conditions due to their size, steering complexity, and the need for collision prevention, especially in parking and narrow roads, where existing path planning techniques are computationally expensive and may not account for real-time changes.
Innovation Solution
A two-level path planning approach is employed, involving offline path generation using extensive computational resources to create a compressed optimal path library and an online path planner that adapts to real-time conditions, incorporating sensors for obstacle detection and vehicle geometry adjustments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If offline path generation using extensive computational resources is used, then path quality and robustness are improved, but computational time and system complexity increase
Solution Approach 1:
The system pre-generates an offline path library containing optimal paths for various start and end configurations before actual navigation. This preliminary computation stores pre-calculated path data that can be quickly retrieved and adapted during real-time operation, eliminating the need for extensive computational resources during actual path planning while maintaining high path quality and robustness.
2Productivity
If a compressed optimal path library is used, then online computational resources are reduced, but path adaptation to real-time changes becomes more difficult
Solution Approach 1:
The system dynamically adapts the compressed offline path library to real-time conditions by adjusting path parameters based on current sensor data, obstacle detection, and environmental changes. The pre-calculated paths serve as a foundation that is continuously modified online to account for moving obstacles, changing terrain, and real-time vehicle state, thereby maintaining both processing speed and adaptability.
Solution Approach 2:
The system incorporates feedback loops where sensor data from the real environment is continuously compared against the pre-calculated offline path library. Based on this feedback, the system adjusts and refines the selected path in real-time, ensuring adaptation to obstacles and environmental changes while maintaining the computational efficiency provided by the compressed library structure.
3Manufacturing precision
If extensive offline computation is performed, then initial path quality is improved, but system complexity and resource requirements increase
Solution Approach 1:
The path planning system is segmented into distinct offline and online components. The offline component performs extensive computation to generate a compressed path library with high optimization accuracy, while the online component handles real-time path selection and adaptation. This segmentation allows the complex computational tasks to be performed beforehand when full system resources are available, while the running system maintains lower complexity and higher responsiveness.
Data Source
AI summary
Described is a two-level optimal path planning process for autonomous tractor-trailer trucks which incorporates offline planning, online planning, and utilizing online estimation and perception results for adapting a planned path to real-world changes in the driving environment. In one aspect, a method of navigating an autonomous vehicle includes determining, by an online server, a current vehicle state of the autonomous vehicle in a mapped driving area. The method includes receiving, by the online server from an offline path library, a path for the autonomous driving vehicle through the mapped driving area from the current vehicle state to a destination vehicle state, and receiving fixed and moving obstacle information. The method includes adjusting the path to generate an optimized path that avoids the fixed and moving obstacles and ends at a targeted final vehicle state, and navigating the autonomous vehicle based on the optimized path.