Autonomous Vehicle Path Planning Using Lateral Surface Profile Energy Function
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicle systems face challenges in generating effective driving plans on roadways with dynamic environments, particularly those with snow ruts, as existing frameworks struggle to accommodate changing conditions and optimize wheel positions for smooth navigation.
Innovation Solution
The method involves using a perception module and a planning/decision-making module to determine future lateral positions of a vehicle based on a lateral surface profile of the roadway, employing an energy function that favors low vertical wheel positions, thereby guiding the vehicle to follow existing tracks in snow ruts while avoiding snow piles.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the autonomous operation system uses a conventional driving path determination framework, then the vehicle can operate on standard roadways, but it fails to accommodate dynamic changes in the environment such as snow ruts
Solution Approach 1:
The system dynamically adjusts the driving path determination by incorporating real-time detection of lateral surface profiles and vertical wheel positions. The energy function continuously evaluates candidate future lateral positions based on current environmental conditions, allowing the vehicle to adapt to snow ruts and other dynamic roadway changes while maintaining reliable navigation through optimized path selection.
2Reliability
If the vehicle follows the center of the roadway lane, then it maintains proper lane positioning, but it may encounter snow piles and lose stability
Solution Approach 1:
The system applies local quality by evaluating specific lateral positions within the lane rather than uniformly following the lane center. The energy function assesses vertical wheel positions at multiple candidate lateral positions, identifying local minima that correspond to stable positions in snow ruts. This allows the vehicle to deviate locally from the lane center when necessary to avoid snow piles while maintaining overall lane positioning.
3Measurement precision
If the autonomous operation system calculates multiple candidate future lateral positions, then it can find optimal paths, but the computational complexity increases
Solution Approach 1:
The system changes parameters by using an energy function that evaluates candidate lateral positions based on vertical wheel positions and lateral surface profiles. By transforming the path determination problem into an energy minimization problem, the system can efficiently compare multiple candidate positions and select the optimal path without requiring excessively complex computational structures. The energy function parameters are adjusted based on detected roadway conditions.
Data Source
AI summary
A method of autonomous driving includes identifying, from detected information about an environment surrounding a vehicle on a roadway, a lateral surface profile of the roadway. Based on the lateral surface profile of the roadway, vertical wheel positions at identified candidate future lateral positions of the vehicle are determined. Based on the determined vertical wheel positions, as part of a driving path along the roadway, future lateral positions of the vehicle from among the identified candidates therefor are determined using an energy function that algorithmically favors low vertical wheel positions.