Autonomous Vehicle Failover Control for Mode-Specific Response
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in responding to triggering events due to communication latencies with remote monitoring systems, leading to potential mode confusion and inappropriate failover responses.
Innovation Solution
A control system on-board the autonomous vehicle determines its operational mode and tailors the failover response based on the presence of a human driver, allowing for localized decision-making to address triggering events, such as entering manual control mode if a driver is present or stopping if not, thereby reducing reliance on remote systems.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the autonomous vehicle relies on remote monitoring systems for failover responses, then centralized control and monitoring capability are improved, but communication latency and response time deteriorate
Solution Approach 1:
The patent segments the failover control system into two parts: a remote monitoring system for centralized oversight and an on-board computing device for local real-time decision-making. This segmentation allows the system to maintain centralized control capabilities while enabling fast local responses to triggering events, thus resolving the contradiction between centralized control reliability and communication latency.
Solution Approach 2:
The on-board computing device acts as an intermediary between the remote monitoring system and the vehicle's failover systems. It receives monitoring data from remote systems but independently determines and executes failover responses locally, eliminating the need for real-time communication with remote systems during critical failover events and thus reducing communication latency.
2Device complexity
If the autonomous vehicle uses a single failover response mode, then system simplicity is improved, but adaptability to different operational scenarios deteriorates
Solution Approach 1:
The patent implements dynamic failover response selection based on the vehicle's current operational mode. The system automatically adjusts the failover response strategy according to whether the vehicle is in autonomous mode, manual mode, or transition mode, enabling adaptability to different scenarios while maintaining relatively simple control logic through mode-based classification.
Solution Approach 2:
The system changes the failover response parameters based on the operational mode detected by the computing device. Different operational modes trigger different failover actions (e.g., safe stopping in autonomous mode versus maintaining control in manual mode), allowing the system to be adaptable without requiring complex decision-making logic for each possible scenario.
3Reliability
If the autonomous vehicle implements mode-specific failover responses, then response accuracy and safety are improved, but computational resource consumption increases
Solution Approach 1:
The patent implements partial monitoring where the on-board computing device performs selective failover response determination based on operational mode rather than continuously analyzing all possible failure scenarios. This partial action approach provides accurate mode-specific responses while consuming fewer computational resources compared to comprehensive analysis of all failover possibilities.
Data Source
AI summary
Systems and methods for controlling a failover response of an autonomous vehicle are provided. In one example embodiment, a method includes determining, by one or more computing devices on-board an autonomous vehicle, an operational mode of the autonomous vehicle. The autonomous vehicle is configured to operate in at least a first operational mode in which a human driver is present in the autonomous vehicle and a second operational mode in which the human driver is not present in the autonomous vehicle. The method includes detecting a triggering event associated with the autonomous vehicle. The method includes determining actions to be performed by the autonomous vehicle in response to the triggering event based on the operational mode. The method includes providing one or more control signals to one or more of the systems on-board the autonomous vehicle to perform the one or more actions in response to the triggering event.