Smooth Reference Path Generator for Autonomous Vehicles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing autonomous driving vehicle path trajectory planning methods often result in sudden changes due to the use of naive solutions that connect midpoints of road lane edges, leading to inefficient and unstable navigation.
Innovation Solution
A scalable smooth reference path generator system that collects data points from historical vehicle paths, segments them, applies a smoothing function to select relevant points, and interpolates segment reference points to create a stable reference line for navigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If midpoints of road lane edges are connected to generate path trajectory, then path planning is simplified, but sudden changes in path trajectory occur
Solution Approach 1:
The patent divides the road lane into multiple segments and generates path trajectories for each segment separately. By segmenting the overall path planning task into smaller sub-tasks, the system can apply smoothing operations to each segment while maintaining overall path simplicity, thus resolving the contradiction between planning simplicity and trajectory stability
Solution Approach 2:
The patent applies curvature-based smoothing to the generated path trajectory, replacing sharp angular connections between midpoints with curved transitions. This curvature application eliminates sudden changes in the path while maintaining the essential routing information, thereby improving trajectory stability without significantly increasing planning complexity
2Stability of the object's composition
If historical data points are collected and processed for each path segment, then path smoothness is improved, but data processing complexity increases
Solution Approach 1:
The patent segments the historical data processing task by associating data points with specific road lane segments. Instead of processing all data points globally, the system processes data segment-by-segment, reducing the computational complexity of each processing step while achieving overall path smoothness through the aggregation of segmented results
Solution Approach 2:
The patent performs preliminary filtering and organization of historical data points before path generation. By pre-processing and categorizing data points according to their spatial relationships with road segments, the system reduces the complexity of subsequent path smoothing operations while maintaining the quality of the generated trajectories
Data Source
AI summary
In one embodiment, a computer system generates a first vehicular path based on map information. The system collects data points representing geographical coordinates of vehicles that drove on a vehicular path lane at different points in time. The system segments the first vehicular path into path segments based on the collected data points. For each of the path segments, the system applies a smoothing function to select a subset of the data points that are within a predetermined proximity of the corresponding path segment and calculates a segment reference point to represent the path segment by combining the selected data points. The segment reference points of the path segments of the first vehicular path are interpolated to generate a second vehicular path such that the second vehicular path is used as a reference line to control ADVs driving on the first vehicular path.