Autonomous Vehicle Fallback Trajectories for Seamless Safe Stop
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in ensuring safety when the primary computing system fails, as they require complex software and sensors to navigate safely without human intervention, and existing solutions complicate the secondary computing system with trajectory switching and divergent control interfaces.
Innovation Solution
The implementation of a method where the primary computing system generates both a nominal and a fallback trajectory, with the secondary computing system initially following the nominal trajectory and seamlessly transitioning to the fallback trajectory in case of primary system failure, allowing safe vehicle navigation without complex trajectory switching or separate control interfaces for speed and heading.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the primary computing system fails, then the secondary computing system must take control to ensure safety, but the complexity of implementing trajectory switching and separate control interfaces increases system complexity
Solution Approach 1:
The secondary computing system pre-loads both the nominal trajectory (for normal operation) and the fallback trajectory (for emergency stopping) before a failure occurs. This allows the system to seamlessly switch to the pre-prepared fallback trajectory without requiring complex real-time trajectory generation or switching logic when the primary system fails, thus improving reliability while minimizing the increase in system complexity
Solution Approach 2:
The secondary computing system is designed to handle multiple functions: it controls both speed and heading using a single unified control interface that works for both nominal and fallback trajectories. This eliminates the need for separate control interfaces for different trajectory types, reducing system complexity while maintaining the ability to perform both normal operation and emergency stopping functions
2Device complexity
If the secondary computing system uses a unified control interface for both speed and heading, then system complexity is reduced, but the ability to independently control trajectory parameters is limited
Solution Approach 1:
The unified control interface dynamically adjusts its behavior based on which trajectory is active. When the nominal trajectory is active, the interface enables both speed and heading control for normal navigation. When the fallback trajectory is activated due to primary system failure, the interface automatically transitions to enable only speed control for emergency stopping, while heading control is disabled. This dynamic adaptation maintains trajectory control flexibility while using a single unified interface
Data Source
Figure 1
Figure 2
Figure 3A
AI summary
A method for controlling a vehicle 100 includes generating, by a primary computing system 110, a nominal trajectory from a location in order to achieve a mission goal and a fall back trajectory from the location in order to safely stop the vehicle. The nominal and the fall back are identical between the location and a divergent point and where the nominal and the fall back diverge after the divergent point. The fall back is sent to and received by a secondary computing system 210. The secondary computing system waits for an updated trajectory from the primary computing system while controlling the vehicle according to the fall back. When the vehicle reaches a threshold point on the fall back, or a predetermined threshold period of time from a time when the fall back trajectory was received has passed, and an updated trajectory has not yet been received by the secondary computing system, the secondary computing system continues to control the vehicle according to the fall back in order to safely stop the vehicle.