Self-Driving Car Reference Path Amendment for Lane-Bound Turns
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing self-driving car systems face challenges in planning operations when approaching turns, particularly in lanes with curves, leading to potential unsafe situations where the vehicle may fall outside the lane boundaries.
Innovation Solution
An electronic device equipped with sensors and modules to continuously verify the vehicle's position relative to the lane center line, amend the reference path to ensure it stays within lane constraints, and predict paths for dynamic objects to avoid collisions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the SDC follows the default reference path (center line of the lane), then the navigation accuracy is improved, but the vehicle may fall outside the lane boundaries when approaching turns
Solution Approach 1:
The system performs preliminary verification of the reference path by simulating vehicle movement along the path and checking for boundary violations before actual navigation. This advance checking allows the system to identify potential lane boundary violations and amend the reference path proactively, ensuring both navigation accuracy and lane boundary compliance during actual driving.
Solution Approach 2:
The system introduces an intermediary verification and amendment mechanism between the default reference path and the actual vehicle navigation. This intermediary layer simulates vehicle movement, verifies boundary compliance, and generates amended reference paths when necessary, acting as a mediator that reconciles the conflict between following the center line and staying within lane boundaries.
2Reliability
If the reference path is amended to stay within lane boundaries, then the safety is improved, but the path may deviate from the optimal center line trajectory
Solution Approach 1:
The system changes the parameters of the reference path by adjusting anchor points and modifying path geometry based on simulated vehicle movement and boundary verification results. This parameter adjustment allows the path to deviate from the exact center line when necessary to maintain boundary compliance, optimizing the balance between safety and path accuracy.
3Reliability
If the system continuously verifies vehicle alignment and amends the reference path, then the lane boundary compliance is improved, but the computational complexity increases
Solution Approach 1:
The system performs verification and amendment operations selectively rather than continuously at full detail. By skipping redundant verification steps and rushing through routine checks, the system maintains lane boundary compliance while reducing unnecessary computational overhead, thereby lowering overall computational complexity.
Data Source
AI summary
A method and device for amending a reference path associated with a vehicle are disclosed. The method includes: (i) acquiring road segment data and reference path data, the reference path data having a plurality of anchor points defining the reference path along the road segment, (ii) using the road segment data and the reference path data to determine a safe deviation interval for each one of the plurality of anchor points, a given safe deviation interval for a given anchor point being indicative of an acceptable deviation of the vehicle from the reference path; and (iii) using the safe deviation intervals to determine an amended path for the vehicle instead of the reference path, such that by following the amended path the vehicle falls within the constraints of the road segment.