Autonomous Path Planning Using 2D Collision Checks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional autonomous vehicle systems face challenges in efficiently selecting safe paths that account for obstacle and collision avoidance, often requiring significant computational resources and being impractical for real-time applications due to complex 3D collision checks.
Innovation Solution
The system weights paths based on obstacle avoidance considerations by projecting 3D trajectories onto a 2D plane and performing edge-based intersection checks, reducing computational requirements and enabling real-time path selection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional systems perform collision checks against every actor in the environment using 3D space simulations, then measurement precision of collision detection is improved, but compute resources required increase significantly making the system impractical for real-time applications
Solution Approach 1:
The patent transforms the collision detection problem from 3D space to 2D space by projecting vehicle trajectories and actor positions onto a two-dimensional plane. This dimensionality reduction maintains sufficient collision detection accuracy while dramatically reducing the computational resources required, enabling real-time path planning applications.
2Reliability
If conventional systems execute comprehensive safety checks for every potential path, then reliability of path safety is improved, but productivity of path selection process deteriorates due to computational complexity
Solution Approach 1:
By projecting 3D trajectory data onto a 2D plane, the system enables faster intersection checks between path segments and actor positions while maintaining reliable collision detection. This dimensional transformation allows comprehensive safety verification across multiple potential paths without the computational burden of full 3D simulations.
3Measurement precision
If conventional systems perform detailed 3D trajectory simulations for safety procedure verification, then measurement precision of safety analysis is improved, but loss of time for computation increases making real-time implementation infeasible
Solution Approach 1:
The patent reduces computation time by projecting detailed 3D trajectory simulations onto a 2D plane for safety analysis. This dimensional reduction preserves the essential spatial relationships needed for accurate collision detection while enabling the system to complete safety verifications within real-time constraints.
Data Source
AI summary
In various examples, systems and methods are disclosed for weighting one or more optional paths based on obstacle avoidance or other safety considerations. In some embodiments, the obstacle avoidance considerations may be computed using a comparison of trajectories representative of safety procedures at present and future projected time steps of an ego-vehicle and other actors to ensure that each actor is capable of implementing their respective safety procedure while avoiding collisions at any point along the trajectory. This comparison may include filtering out a path(s) of an actor at a time step(s)—e.g., using a one-dimensional lookup—based on spatial relationships between the actor and the ego-vehicle at the time step(s). Where a particular path—or point along the path—does not satisfy a collision-free standard, the path may be penalized more negatively with respect to the obstacle avoidance considerations, or may be removed from consideration as a potential path.