Automated Vehicle Deadlock Prediction Using Historical Context
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Automated transportation vehicles face challenges in interpreting and resolving deadlock situations, such as unclear traffic conditions or low confidence in object detection, which can lead to the need for external human intervention, particularly in tele-operated driving scenarios.
Innovation Solution
A method for predicting deadlock situations by analyzing historical data to identify causes and contextual factors, allowing for the monitoring of actual context information to anticipate potential deadlocks, enabling better resource planning and operational mode changes in transportation vehicles.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If automated vehicles use onboard sensor systems to interpret traffic conditions, then the extent of automation is improved, but the reliability deteriorates when facing unclear traffic conditions or low confidence detection scenarios
Solution Approach 1:
A remote operator acts as an intermediary between the automated vehicle system and the environment. When the automated system detects low confidence situations (deadlock), control is transferred to a human operator who can interpret ambiguous traffic conditions and make decisions, thereby maintaining high automation levels while ensuring reliability in critical scenarios.
2Reliability
If tele-operated driving is used to resolve deadlock situations, then the reliability is improved, but the loss of time increases due to end-to-end communication delay
Solution Approach 1:
The system performs preliminary detection and assessment of deadlock situations using onboard sensors and algorithms before actual deadlocks occur. By identifying potential deadlock scenarios in advance and preparing for smooth control transfer to remote operators, the system minimizes the time loss associated with communication delays while maintaining reliable deadlock resolution.
3Reliability
If historical deadlock data is analyzed to predict future deadlocks, then the reliability is improved, but the device complexity increases
Solution Approach 1:
The system uses its own historical deadlock data and sensor information to predict future deadlock situations. By leveraging internally collected data rather than requiring complex external processing systems, the vehicle maintains high prediction accuracy while avoiding excessive device complexity. The prediction algorithm processes locally available context information about the vehicle and environment.
Data Source
AI summary
A method, a computer program, an apparatus, a transportation vehicle, and a network entity for predicting a deadlock situation for an automated transportation vehicle. The deadlock situation is an exceptional traffic situation necessitating a change of an operational mode of the transportation vehicle. The method for predicting a deadlock situation for the automated transportation vehicle includes obtaining information related to a historical deadlock situation cause, determining historical context information for the historical deadlock situation cause, determining information indicative for the deadlock situation cause based on the information related to the historical context information, monitoring actual context information for information indicative for the deadlock situation, and predicting the deadlock situation based on the information indicative for the deadlock situation in the actual context information.