Autonomous Vehicle Trajectory Evaluation Using Arrival Times
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional autonomous vehicle systems lack the ability to proactively adjust trajectories based on dynamic environmental conditions, particularly for collision avoidance, leading to sub-optimal behavior due to inflexible decision-making processes that do not account for changing variables in complex urban scenarios.
Innovation Solution
The system evaluates trajectories by determining if the autonomous vehicle can occupy points in space-time while avoiding potential future collisions through predicted arrival times and safety procedures, comparing object arrival times to vehicle occupancy times, and scoring or eliminating trajectories based on conflict analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If conventional systems use inflexible decision-making processes that select routes with lowest travel time and follow lanes, then travel efficiency is improved, but adaptability to dynamic environmental conditions deteriorates
Solution Approach 1:
The system dynamically adjusts trajectory selection by continuously evaluating multiple candidate trajectories against updated environmental conditions. Instead of following a fixed pre-determined route, the behavior planner re-evaluates and selects optimal trajectories in real-time based on changing conditions such as detected objects, traffic patterns, and environmental factors, making the system adaptable while maintaining efficiency.
Solution Approach 2:
The system performs preliminary evaluation of multiple candidate trajectories before final selection, assessing potential conflicts and safety conditions in advance. By pre-calculating and ranking multiple trajectory options with their associated risk profiles, the system is prepared to quickly switch to alternative trajectories when dynamic conditions change, rather than reactively adjusting a single fixed path.
2Device complexity
If behavior planning and collision avoidance are determined separately, then computational simplicity is improved, but trajectory optimality deteriorates
Solution Approach 1:
The system merges behavior planning and collision avoidance into a unified trajectory evaluation framework. The behavior planner generates candidate trajectories while simultaneously evaluating them for potential collisions with detected objects. This integrated approach ensures that collision avoidance considerations are embedded within the trajectory selection process itself, producing trajectories that are both behaviorally appropriate and collision-free without requiring separate reactive adjustments.
3Reliability
If the system evaluates trajectories by comparing vehicle occupancy times with object arrival times at trajectory points, then collision avoidance reliability is improved, but computational complexity increases
Solution Approach 1:
The system segments the trajectory evaluation process into discrete time steps and spatial points along each candidate trajectory. By dividing the continuous trajectory into manageable segments and evaluating collision risk at each segment point independently, the system can systematically compare vehicle occupancy times with object arrival times without overwhelming computational complexity. This segmented approach allows for efficient parallel processing of multiple trajectory candidates.
Data Source
AI summary
A trajectory for an autonomous machine may be evaluated for safety based at least on determining whether the autonomous machine would be capable of occupying points of the trajectory in space-time while still being able to avoid a potential future collision with one or more objects in the environment through use of one or more safety procedures. To do so, a point of the trajectory may be evaluated for conflict based at least on a comparison between points in space-time that correspond to the autonomous machine executing the safety procedure(s) from the point and arrival times of the one or more objects to corresponding position(s) in the environment. A trajectory may be sampled and evaluated for conflicts at various points throughout the trajectory. Based on results of one or more evaluations, the trajectory may be scored, eliminated from consideration, or otherwise considered for control of the autonomous machine.