Lateral Offset Bias for Autonomous Vehicle Trajectory Planning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in maintaining precise control while navigating curves due to lateral tracking errors, which are exacerbated by difficulties in accurately accounting for vehicle dynamics and kinematics, leading to reduced cornering rates and increased risk of drifting.
Innovation Solution
Implementing a lateral offset bias in the trajectory planning system, which deviates the vehicle's path from the center of the road towards the inside of curves, using cost functions and real-time calculations based on speed, curvature, and lateral acceleration to compensate for tracking errors and improve cornering performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If the vehicle follows the center of the road as reference trajectory, then the trajectory planning is simple, but lateral tracking errors increase and cornering precision deteriorates
Solution Approach 1:
The patent applies asymmetry by introducing a lateral offset bias that shifts the reference trajectory from the road center toward the inside of curves. This asymmetric adjustment compensates for the vehicle's natural tendency to drift outward during cornering, improving lateral tracking precision without significantly increasing planning complexity.
Solution Approach 2:
The patent changes the parameter of reference trajectory position by applying a lateral offset that varies with curve characteristics. The offset is calculated based on vehicle speed, curve radius, and other dynamic parameters, allowing the reference trajectory to adapt to different cornering conditions and improve tracking accuracy.
2Productivity
If the vehicle increases speed through curves, then productivity improves, but lateral tracking errors increase and control stability deteriorates
Solution Approach 1:
The patent applies preliminary action by pre-calculating the lateral offset bias before the vehicle enters the curve. The offset is determined based on predicted vehicle speed, curve geometry, and dynamic characteristics, allowing the control system to proactively compensate for expected tracking errors and maintain stability at higher speeds.
Solution Approach 2:
The patent implements feedback by continuously monitoring actual vehicle position and trajectory tracking errors, then adjusting the lateral offset bias in real-time. This closed-loop control ensures that the reference trajectory adapts to actual vehicle behavior, maintaining lateral control stability even at increased cornering speeds.
3Loss of time
If conventional trajectory planning is used without lateral offset bias, then computation is faster, but trajectory accuracy and cornering performance deteriorate
Solution Approach 1:
The patent applies segmentation by dividing the trajectory planning into two stages: first generating a basic reference trajectory using conventional methods, then applying lateral offset bias calculations to adjust the trajectory. This segmented approach maintains the computational efficiency of conventional planning while adding accuracy improvements through the offset calculation.
Data Source
AI summary
A trajectory for a vehicle can be generated using a lateral offset bias. The vehicle, such as an autonomous vehicle (AV), may be directed to follow reference trajectory for through an environment. The AV may determine a segment associated with the reference trajectory based on curvatures of the reference trajectory, determine a lateral offset bias associated with the segment based at least in part on, for example, one or more of a speed or acceleration of the vehicle, and determine a candidate trajectory for the autonomous vehicle based at least in part on the lateral offset bias. The candidate trajectory may then be used to control the autonomous vehicle.