Autonomous Vehicle Path Drifting Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous driving vehicles face challenges in accurately planning paths due to drafting issues caused by factors like tire wear, wheel alignment, and road conditions, leading to inaccuracies in navigation.
Innovation Solution
The system calculates a drifting error based on the difference between the expected and actual vehicle location, using sensors like LIDAR and RADAR, and applies a drifting correction factor to modify the path planning, ensuring the vehicle stays closer to the intended route by shifting the starting point of the path in the station-lateral space.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional path planning is used without drifting correction, then the path planning process is simple, but the navigation accuracy deteriorates due to drafting errors from tire wear, wheel alignment, and road conditions
Solution Approach 1:
The system performs preliminary drifting correction by calculating a drifting correction factor based on expected versus actual vehicle locations before final path execution. This advance correction compensates for anticipated drafting errors due to tire wear, wheel alignment issues, and road conditions, improving navigation accuracy without adding complex real-time adjustments during path following
Solution Approach 2:
The system implements feedback by continuously monitoring the difference between expected vehicle locations (from path planning) and actual vehicle locations (from sensor data). This feedback loop calculates drifting errors and generates correction factors that are applied to subsequent path planning, creating a self-correcting system that maintains accuracy despite mechanical wear and environmental factors
2Measurement precision
If drifting correction is applied to path planning, then navigation accuracy is improved, but the computational complexity and processing requirements increase
Solution Approach 1:
The drifting correction is applied locally at the starting point of the path rather than requiring continuous adjustment of the entire path trajectory. By modifying only the starting location based on calculated drifting correction factors, the system achieves accuracy improvement with minimal computational overhead, avoiding the need to recalculate entire path plans
Data Source
AI summary
In one embodiment, when planning a path for a current driving cycle for an autonomous driving vehicle (ADV), a current location of the ADV is determined based on sensor data provided by a variety of sensors mounted on the ADV. A path is generated for the current driving cycle to drive the ADV from the current location for a predetermined period of time. An expected location of the ADV calculated based on a previous path, which was generated during a previous driving cycle. A drifting error is then calculated based on the expected location and the current location of the ADV. At least a starting point of the path for the current driving cycle is modified based on the drifting error, generating a modified path. The ADV is then controlled according to the modified path.