Moving Obstacle Representation in Station-Time Coordinate System
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional methods for representing moving obstacles in autonomous driving vehicles using quadrilaterals in the station-time coordinate system introduce inaccuracies due to inconsistencies between the actual shape and the quadrilateral representation, leading to potential planning failures and safety issues.
Innovation Solution
The system represents moving obstacles by determining two points in the station-time coordinate system at each processing interval to model the obstacle's shape, allowing for trajectory planning to avoid collisions, with adjacent pairs of points being merged, reducing processing time complexity from O(N) to O(lgN.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a quadrilateral is used to represent a moving obstacle in the ST coordinate system, then the representation is simple and processing is efficient, but the accuracy of the obstacle shape representation deteriorates
Solution Approach 1:
The patent segments the obstacle representation into multiple key points (at least three points) instead of using a single quadrilateral. Each key point represents a critical position on the obstacle boundary, allowing the system to capture the actual shape characteristics while maintaining computational efficiency through selective point representation rather than continuous boundary modeling.
Solution Approach 2:
The patent transitions from representing obstacles in pure spatial coordinates to the station-time (ST) coordinate system, adding the time dimension to the representation. This allows the obstacle's movement and shape changes over time to be captured explicitly, improving accuracy without proportionally increasing complexity since the ST graph provides a unified framework for temporal-spatial analysis.
2Measurement precision
If more points are used to represent the obstacle shape in the ST coordinate system, then the accuracy improves, but the processing time complexity increases
Solution Approach 1:
The patent uses a minimal sufficient number of key points (at least three points) to represent the obstacle shape rather than using all boundary points or excessive sampling points. This partial action approach captures the essential shape characteristics needed for accurate trajectory planning while avoiding the computational overhead of processing numerous points, achieving the optimal balance between accuracy and efficiency.
Data Source
AI summary
According to some embodiments, a system operates an ADV. In one embodiment, the system perceives a driving environment surrounding the ADV based on sensor data obtained from a plurality of sensors, including perceiving a moving obstacle that is moving relative to the ADV. The system projects the moving obstacle as a figure onto a station-time (ST) coordinate system, wherein the ST coordinate system indicates a distance between the figure and a reference point at different points in time. And the system, for each of a plurality of predetermined processing time intervals, determines two points of the figure in the ST coordinate system to represent a shape of the figure, wherein the shape of the figure is utilized to plan a trajectory to drive the ADV to avoid colliding with the moving obstacle.