Trajectory Manager Process for Autonomous Vehicle Safety Validation
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 challenging to ensure passenger, pedestrian, and property safety.
Innovation Solution
A trajectory manager process (TMP) within the autonomous vehicle system performs validity checks on trajectories, including punctuality, consistency, staleness, and feasibility, to prevent unsafe navigation by evaluating and selecting trajectories that are collision-free and within the vehicle's capabilities, using a hierarchy of trajectories from nominal to emergency stop.
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 patent segments the navigation system into multiple independent subsystems (perception, prediction, planning, control) that process information in modular stages. Each subsystem handles specific aspects of navigation safety independently, allowing the system to consider multiple variables without creating unmanageable complexity. The trajectory validation process further segments safety checks into distinct validation rules that can be applied systematically.
Solution Approach 2:
The patent introduces trajectory validation as an intermediary layer between trajectory generation and execution. This intermediary process acts as a mediator that filters and validates trajectories against multiple safety constraints before they are executed, systematically managing the complexity of multiple subsystem interactions and environmental factors.
2Reliability
If multiple trajectory validation checks are performed, then trajectory safety is improved, but processing time increases
Solution Approach 1:
The patent performs preliminary validation checks on trajectories before they are fully processed and executed. By validating trajectories in advance against predefined safety rules and constraints, the system ensures safety without delaying execution. The validation process checks multiple aspects (collision freedom, constraint satisfaction, consistency) in a systematic sequence that minimizes processing overhead.
Solution Approach 2:
The patent changes the parameters of trajectory validation by using predefined validation rules with adjustable thresholds and constraints. This allows the system to perform comprehensive safety checks while optimizing processing time by adjusting validation stringency based on operational context, balancing safety requirements with real-time processing demands.
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.