Autonomous Driving Safety Interaction System
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous driving vehicles face safety risks due to malfunctions in sensors like LiDAR, which can lead to inaccurate obstacle detection, necessitating a system to monitor and switch from autonomous to manual mode when errors occur.
Innovation Solution
A computer-implemented method and system that receives error messages from a patrol module, evaluates the autonomous driving system's status, and decides whether to maintain or switch from autonomous to manual mode based on error levels, using a vehicle controller and CAN bus module to manage the transition.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the autonomous driving system continues to operate in autonomous mode despite sensor errors, then productivity is maintained, but reliability deteriorates due to safety risks
Solution Approach 1:
The patrol module continuously monitors the autonomous driving system in advance to detect sensor errors before they lead to dangerous situations. The system evaluates error messages and determines system status proactively, switching to manual mode before safety is compromised, thus maintaining both productivity and reliability.
Solution Approach 2:
The system implements a feedback mechanism where the patrol module sends error messages to the vehicle controller, which evaluates the system status and determines whether to maintain autonomous mode or switch to manual mode. This closed-loop feedback ensures continuous safety monitoring while maintaining operational efficiency.
2Reliability
If the system switches to manual mode upon detecting sensor errors, then reliability is improved by ensuring safety, but productivity deteriorates due to interruption of autonomous driving
Solution Approach 1:
The system switches to manual mode in advance when sensor errors are detected, preventing dangerous situations before they occur. This preliminary protective action ensures safety (improving reliability) while minimizing the duration of mode switching, thus limiting the impact on productivity.
Solution Approach 2:
The system dynamically adjusts its operational mode based on real-time system status evaluation. When sensor errors are detected, the system transitions from autonomous to manual mode; when errors are resolved, it can return to autonomous mode. This dynamic adaptation optimizes both safety and operational continuity.
3Reliability
If comprehensive monitoring of all sensors is implemented, then reliability is improved through better safety detection, but device complexity increases
Solution Approach 1:
The monitoring system is segmented into a dedicated patrol module that specifically monitors sensor health and sends error messages to the vehicle controller. This segmentation allows comprehensive sensor monitoring to be implemented without overwhelming the entire system, managing complexity while maintaining high reliability.
Solution Approach 2:
The patrol module acts as an intermediary between the sensors and the vehicle controller. It collects error messages from sensors, evaluates them, and communicates with the controller only when necessary. This intermediary role simplifies the overall system architecture while enabling comprehensive monitoring of all sensors.
Data Source
AI summary
The disclosure describes various embodiments for monitoring safety of an autonomous driving vehicle (ADV). In one embodiment, a method includes the operations of receiving, by a vehicle controller, one or more error message from a patrol module, the one or more error messages generated by an autonomous driving system of the ADV operating in an autonomous mode, the patrol module monitoring the autonomous driving system; evaluating a status of the autonomous driving system based on the one or more error messages; and keeping the ADV in the autonomous mode or switching it to a manual mode based on the status of the autonomous driving system.