Trajectory Validation Limits for Safe Autonomous Vehicle Routing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face complexity in safe navigation due to interactions among multiple subsystems and environmental changes, making it difficult to ensure passenger, pedestrian, and property safety.
Innovation Solution
A trajectory manager process (TMP) is implemented within the autonomous vehicle's management system to verify and select safe trajectories by performing validity checks, including punctuality, consistency, staleness, feasibility, and collision tests, ensuring the vehicle follows a collision-free and safe path.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple subsystems and environmental variables are considered for safe navigation, then navigation safety is improved, but system complexity increases dramatically
Solution Approach 1:
The navigation system is segmented into multiple independent subsystems (trajectory generation, trajectory validation, trajectory selection) that can be developed, tested, and maintained separately. Each subsystem handles specific aspects of navigation safety, reducing overall system complexity while maintaining comprehensive safety coverage.
Solution Approach 2:
A trajectory manager process acts as an intermediary between the complex environment/subsystems and the vehicle control system. It receives trajectories from multiple sources, validates them against safety criteria, and selects the safest trajectory, thereby managing complexity centrally without increasing individual subsystem complexity.
2Reliability
If redundant trajectory validation is performed, then navigation safety is improved, but processing time increases
Solution Approach 1:
Trajectory validation checks are performed preliminarily and continuously in the background before trajectories are executed. The system pre-validates trajectories against safety constraints, so when a trajectory needs to be selected or modified, the validation work is already done, minimizing real-time processing delays.
Solution Approach 2:
The trajectory manager continuously monitors and validates trajectories throughout their execution rather than performing discrete, time-consuming validation checks. This continuous validation ensures safety is maintained without requiring repeated full validation cycles, reducing processing time while maintaining redundant safety checks.
Data Source
AI summary
The present disclosure is directed to performing one or more validity checks on potential trajectories for a device, such as an autonomous vehicle, to navigate. In some examples, a potential trajectory may be validated based on whether it is consistent with a current trajectory the vehicle is navigating such that the potential and current trajectories are not too different, whether the vehicle can feasibly or kinematically navigate to the potential trajectory from a current state, whether the potential trajectory was punctual or received within a time period of a prior trajectory, and/or whether the potential trajectory passes a staleness check, such that it was created within a certain time period. In some examples, determining whether a potential trajectory is feasibly may include updating a set of feasibility limits based on one or more operational characteristics of statuses of subsystems of the vehicle.