Hierarchical Grid Collision Evaluation for Autonomous Trajectories
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in evaluating planned trajectories to avoid collisions with other objects, as existing methods are inefficient and may not effectively validate trajectories before execution, potentially leading to collisions.
Innovation Solution
The method involves generating a set of grids centered around the vehicle's location, with cell sizes determined by object sizes, to evaluate predicted trajectories for occupancy by other objects, allowing for efficient collision detection and trajectory adjustment or generation of new paths to avoid collisions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional collision evaluation methods are used, then collision detection can be performed, but the evaluation time is excessive and efficiency is low
Solution Approach 1:
The patent divides the continuous spatial environment into discrete grid cells with different sizes. By segmenting the space into a hierarchy of grids (coarse grids for distant objects, fine grids for nearby objects), the system can efficiently evaluate collisions at multiple scales without processing every possible trajectory point, thus dramatically reducing evaluation time while maintaining accuracy.
Solution Approach 2:
The patent introduces a hierarchical dimension to the grid structure, creating multiple levels of grid resolution. This dimensional transformation allows the system to first evaluate collisions in coarse grids to quickly eliminate unsafe trajectories, then refine the evaluation in finer grids only for potentially safe trajectories, reducing the overall computational burden.
2Measurement precision
If uniform grid sizes are used, then grid generation is simple, but the precision of collision detection varies for objects of different sizes
Solution Approach 1:
The patent applies local quality by assigning different grid cell sizes to different regions of space based on the size and importance of objects in those regions. Larger objects or regions of interest receive finer grid resolution for more precise collision detection, while empty or less critical regions use coarser grids, optimizing both precision and computational efficiency.
Solution Approach 2:
The grid structure is made dynamic by adjusting cell sizes based on object characteristics and trajectory evaluation needs. The system can adaptively refine or coarsen grids in different spatial regions during the evaluation process, allowing precision to be allocated where it is most needed rather than uniformly across the entire environment.
Data Source
AI summary
Aspects of the disclosure provide for evaluation of a planned trajectory for an autonomous vehicle. For instance, for each of a plurality of objects, a predicted trajectory may be received. The planned trajectory may identify locations and times that the vehicle will be at those locations. For each of the plurality of objects, a grid including a plurality of cells may be generated. Occupancy of each grid for each of the plurality of objects may be determined based on the predicted trajectories. A cell of each grid which will be occupied by the vehicle at a location and time of the planned trajectory may be identified. The planned trajectory may be evaluated based on whether any identified cell is occupied by any of the plurality of objects at the time.