Vehicle Polyline Contours for Accurate Collision Checking

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing autonomous vehicle perception systems face challenges in accurately modeling the vehicle's contour and predicting collisions, particularly due to the use of rectangular or complex polygon representations which can lead to false positive collisions and high computational costs.

Innovation Solution

The method involves using a polyline contour representation of the autonomous vehicle, defined by its width profile, which is converted to a half-plane coordinate system. This representation allows for efficient collision detection by determining collision locations between the vehicle's contour and detected objects, enabling the vehicle to avoid collisions effectively.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a rectangular or complex polygon representation is used to model the autonomous vehicle's contour, then the vehicle's physical aspects including sensors and mirrors are fully bounded, but false positive collisions occur especially at the corners and computational costs increase

Engineering Contradiction:
Improvecollision detection accuracyVSAvoidcomputational complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent segments the vehicle contour into a polyline representation with a limited number of vertices and line segments, dividing the complex bounding problem into manageable geometric components that reduce computational load while maintaining collision detection accuracy

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent creates a simplified polyline copy of the vehicle's actual contour that captures the essential shape characteristics without requiring full geometric fidelity, enabling efficient collision analysis through coordinate transformation and geometric intersection algorithms

Inventive Principle:
Principle #26Copying

2Device complexity

If a rectangular representation is used to model the autonomous vehicle's contour, then the model is simple and computationally efficient, but false positive collisions occur especially at the corners

Engineering Contradiction:
Improvemodel simplicityVSAvoidcollision detection accuracy
Core Design Contradiction:
Device complexityVSReliability

Solution Approach 1:

The patent applies local quality by using a polyline contour that closely follows the actual vehicle shape at critical regions (corners, bumpers, mirrors) while maintaining simplicity elsewhere, achieving both accuracy where needed and computational efficiency in other areas

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The patent employs dynamic coordinate transformation between vehicle-local and world coordinate systems, allowing the polyline contour to adapt to different vehicle orientations and positions while maintaining a fixed, simple representation in the vehicle's local frame

Inventive Principle:
Principle #15Dynamics

Data Source

PatentUS12337835B2Polyline contour representations for autonomous vehicles
Publication Date: 2025.06.24 WAYMO LLC
  • US12337835B2 patent drawing
  • US12337835B2 patent drawing
  • US12337835B2 patent drawing

AI summary

Aspects of the disclosure relate to controlling a vehicle having an autonomous driving mode or an autonomous vehicle. For instance, a polygon representative of the shape and location of a first object may be received. A polyline contour representation of a portion of a polygon representative of the shape and location of a second object may be received. The polyline contour representation may be in half-plane coordinates and including a plurality of vertices and line segments. Coordinates of the polygon representative of the first object may be converted to the half-plane coordinate system. A collision location between the polyline contour representation and the polygon representative of the first object may be determined using the converted coordinates. The autonomous vehicle may be controlled in the autonomous driving mode to avoid a collision based on the collision location.