Tele-Operator Sensor View Selection for AV Exception Handling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in handling exceptional situations, such as obstructions, where they cannot assess or understand the intentions of other road users, leading to potential safety issues and inefficiencies, as they may require human intervention for assistance.
Innovation Solution
A system and method for exception handling in autonomous vehicles, which includes identifying exception situations, selecting relevant sensors and tools, and presenting data to a tele-operator for assistance, allowing for real-time decision-making and solution validation to safely navigate through complex scenarios.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If autonomous vehicles rely solely on automated systems to handle exception situations, then automation level is improved, but reliability deteriorates due to inability to assess complex situations
Solution Approach 1:
The patent introduces a tele-operator as an intermediary between the autonomous vehicle and the control system. When exception situations are detected that the automated system cannot confidently resolve, the system transitions to human-in-the-loop operation, allowing a tele-operator to assess sensor data and provide guidance, thus maintaining reliability while preserving high automation for routine operations
Solution Approach 2:
The system dynamically adjusts the level of automation based on the situation. For routine driving, full automation is maintained. When exception situations are detected, the system dynamically switches to a hybrid mode where tele-operator assistance is activated, and can return to full automation once the exception is resolved, optimizing both automation level and reliability contextually
2Reliability
If tele-operator intervention is activated for all exception situations, then reliability is improved, but loss of time increases due to constant human involvement
Solution Approach 1:
Instead of activating tele-operator intervention for all exception situations, the system applies partial action by only engaging human operators when the automated system's confidence in handling the exception falls below a threshold. This selective approach maintains reliability for critical cases while avoiding unnecessary human involvement in situations the automated system can handle
Solution Approach 2:
The autonomous vehicle's automated system serves itself for routine exception handling through its own sensor processing and decision-making algorithms. Only when self-service capability is insufficient does the system escalate to tele-operator intervention, maximizing autonomous self-resolution while minimizing human involvement time
3Loss of information
If comprehensive sensor data from all sensors is presented to tele-operators, then information completeness is improved, but device complexity increases due to data management requirements
Solution Approach 1:
The system extracts and presents only the relevant sensor data necessary for the tele-operator to assess the specific exception situation, rather than transmitting all available sensor data. This selective extraction maintains information completeness for decision-making while significantly reducing data management complexity on the tele-operator side
Solution Approach 2:
The system applies local quality by tailoring the sensor data presentation to the specific exception situation. Different exception types receive different subsets of sensor data relevant to that particular situation, optimizing information completeness for each case while minimizing overall data complexity through context-specific filtering
Data Source
AI summary
A method of exception handing for an autonomous vehicle (AV) includes identifying an exception situation; identifying relevant sensors for the exception situation; identifying relevant tools to the exception situation, the relevant tools usable by a tele-operator to resolve the exception situation; and presenting, on a display of the tele-operator, data from the relevant sensors and the relevant tools.