Fleet Management Anomaly Detection for Autonomous Vehicles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
As automated and autonomous systems in industrial and manufacturing processes become more complex, they introduce new challenges in identifying and addressing errors or failures that contribute to decreased productivity, as the number of failure points increases, making it crucial to monitor and manage vehicle state information effectively in fleets of self-driving vehicles.
Innovation Solution
A method and system for monitoring self-driving vehicles that involve autonomously navigating vehicles, collecting and comparing state information with reference data to identify outliers, generating alerts, and transmitting notifications to appropriate monitoring devices based on escalation levels and user roles, using sensors and a fleet-management system to maintain vehicle and environment state information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automated and autonomous systems are introduced to increase productivity, then productivity is improved, but the number of failure points increases
Solution Approach 1:
The system segments the monitoring function into multiple independent components: sensors distributed across vehicles, onboard processing units, and centralized fleet management servers. This segmentation allows the system to handle complexity by dividing monitoring tasks across multiple specialized modules, thereby maintaining reliability despite increased system complexity.
Solution Approach 2:
The system implements continuous feedback loops where sensors monitor vehicle state information in real-time, compare it against reference data, and trigger alerts when anomalies are detected. This feedback mechanism enables the system to automatically respond to failures, maintaining productivity by quickly identifying and addressing issues before they escalate.
2Reliability
If more sensors and monitoring components are added to detect failures, then reliability is improved, but device complexity increases
Solution Approach 1:
The fleet management server performs multiple functions: it stores reference data, processes sensor data from multiple vehicles, identifies anomalies, generates alerts, and manages notifications. This multi-functionality reduces the need for separate specialized systems, thereby improving reliability without proportionally increasing complexity.
Solution Approach 2:
The system enables vehicles to autonomously monitor their own state information using onboard sensors and processing capabilities. Vehicles self-identify anomalies by comparing their data against reference information, reducing the burden on centralized systems and simplifying the overall architecture while maintaining high reliability.
3Reliability
If real-time monitoring of vehicle state information is implemented, then reliability is improved, but loss of time in data processing increases
Solution Approach 1:
The system pre-stores reference data representing normal vehicle operating conditions in the fleet management server. By having this reference information readily available before monitoring begins, the system can quickly compare real-time sensor data against established baselines without requiring complex real-time analysis, thereby reducing data processing time while maintaining reliable anomaly detection.
Data Source
AI summary
Systems and methods for monitoring a fleet of self-driving vehicles are disclosed. The system comprises one or more self-driving vehicles having at least one sensor for collecting current state information, a fleet-management system, and computer-readable media for storing reference data. The method comprises autonomously navigating a self-driving vehicle in an environment, collecting current state information using the vehicle's sensor, comparing the current state information with the reference data, identifying outlier data in the current state information, and generating an alert based on the outlier data. A notification based on the alert may be sent to one or more monitoring devices according to the type and severity of the outlier.