Teleoperator Awareness for Low-Confidence Driverless Navigation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Fully-autonomous vehicles without driving controls face challenges in navigating unpredictable scenarios, leading to potential safety issues and traffic disruptions, as they may slow or stop in ways that irritate passengers or other drivers, and require rapid guidance to ensure safe operation.
Innovation Solution
A teleoperations system that rapidly provides guidance to driverless vehicles by requesting assistance from a remote operator, using sensor data and operation state data to present a clear understanding of the situation, allowing for real-time instructions to be transmitted back to the vehicle to resolve uncertainties and ensure safe navigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If fully-autonomous vehicles are equipped without driving controls to achieve higher automation, then the extent of automation is improved, but the vehicle cannot handle unpredictable scenarios and may slow or stop causing traffic disruptions and safety issues
Solution Approach 1:
A teleoperation system acts as an intermediary between the autonomous vehicle and human operators. When the vehicle encounters an unpredictable scenario it cannot resolve, the system automatically connects to a remote operator who provides real-time guidance, combining autonomous operation with human decision-making capability to maintain both high automation and safety reliability
Solution Approach 2:
The system implements continuous feedback loops where sensor data from the vehicle is monitored in real-time, and when uncertainty thresholds are exceeded, automatic teleoperation requests are triggered. This feedback mechanism ensures the vehicle maintains autonomous operation under normal conditions while seamlessly transitioning to human-assisted control when safety or reliability concerns arise
2Reliability
If the autonomous vehicle slows or stops to ensure safety in uncertain scenarios, then the reliability is improved, but the productivity and traffic flow are worsened due to delays and irritation to passengers and other drivers
Solution Approach 1:
The system dynamically adjusts the vehicle's operational mode based on real-time situational assessment. Instead of static safety protocols that always slow or stop the vehicle, the system continuously evaluates sensor data and confidence levels, maintaining high-speed autonomous operation when safe and dynamically transitioning to teleoperated control only when necessary, thus preserving both safety and productivity
Solution Approach 2:
The system performs preliminary assessments of uncertain scenarios using sensor data and confidence threshold evaluations before deciding to slow or stop. By pre-evaluating situations and only engaging teleoperation when truly necessary, the system avoids unnecessary delays while maintaining safety, thus preserving traffic flow and mission productivity
3Adaptability or versatility
If the vehicle encounters complex scenarios beyond its capability, then the adaptability is tested, but the loss of time occurs due to delays in resolving uncertainties
Solution Approach 1:
The system implements real-time feedback monitoring of confidence levels based on sensor data quality and scenario complexity. When confidence thresholds are exceeded, the system immediately triggers teleoperation requests, eliminating decision delays and enabling rapid response to complex scenarios while maintaining autonomous operation during high-confidence situations
Solution Approach 2:
The vehicle performs self-assessment of its capability to handle encountered scenarios through confidence threshold evaluation. By automatically identifying when human assistance is needed without external monitoring, the system reduces communication overhead and resolves uncertainties faster, thus improving both adaptability and reducing time loss
Data Source
AI summary
A driverless vehicle may include a processor, a sensor, a network interface, and a memory having stored thereon processor-executable instructions. The driverless vehicle may be configured to obtain a stream of sensor signals including sensor data related to operation of the driverless vehicle from the sensor and/or the network interface. The driverless vehicle may be configured to determine a confidence level associated with operation of the driverless vehicle from the sensor data, and store the confidence level and at least a portion of the sensor data. The driverless vehicle may also be configured to transmit via the network interface a request for teleoperator assistance, and the request may include the portion of the sensor data and the confidence level.