Autonomous Vehicle Exception Handling With Risk-Based Teleoperation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles often encounter situations that exceed their programming capabilities, requiring human tele-operator assistance, leading to inefficiencies and a high demand for tele-operators, which is not sustainable or cost-effective.
Innovation Solution
An autonomous vehicle system that identifies exception situations, assesses risks, and autonomously decides whether to request tele-operator assistance by determining if the risk exceeds a predefined threshold, allowing for reduced tele-operator intervention by autonomously navigating around obstructions if the risk is below the threshold.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the autonomous vehicle requests tele-operator assistance for all exception situations, then the reliability of exception handling is improved, but the quantity of tele-operators required increases and operational efficiency deteriorates
Solution Approach 1:
The system changes the parameter of risk assessment by introducing a risk threshold parameter. The autonomous vehicle evaluates exception situations against predefined risk thresholds and only requests tele-operator assistance when the assessed risk exceeds the threshold. This parameter-based filtering resolves the contradiction by maintaining high reliability for critical situations while improving operational efficiency by autonomously handling low-risk situations.
Solution Approach 2:
The autonomous vehicle performs self-service by autonomously evaluating and resolving exception situations that fall within its risk threshold capabilities. The vehicle uses its own sensors, processors, and decision-making algorithms to handle routine exceptions without external intervention, thereby reducing the burden on tele-operators while maintaining system reliability for more complex situations.
2Productivity
If the autonomous vehicle autonomously resolves exception situations, then operational efficiency is improved, but the reliability of handling complex situations deteriorates
Solution Approach 1:
The system introduces a risk threshold parameter that dynamically determines the boundary between autonomous and tele-operator handled situations. By changing this parameter, the system can adjust the level of autonomy, allowing efficient autonomous handling of routine exceptions while ensuring reliable tele-operator intervention for complex, high-risk situations that exceed the threshold.
Solution Approach 2:
The risk threshold acts as an intermediary mechanism between autonomous vehicle operation and tele-operator assistance. It mediates the decision-making process by automatically filtering situations based on risk level, enabling the vehicle to autonomously resolve low-risk exceptions while reliably escalating high-risk situations to human operators.
3Reliability
If tele-operator assistance is requested for every exception, then the quality of exception handling is improved, but the cost of tele-operation increases
Solution Approach 1:
The system implements a risk threshold parameter that filters exception situations based on their assessed risk level. This parameter change enables the vehicle to autonomously handle low-risk situations, significantly reducing the number of tele-operator requests and associated costs, while maintaining high-quality handling for high-risk situations that exceed the threshold.
Solution Approach 2:
The autonomous vehicle provides self-service for routine exception handling by autonomously evaluating and resolving situations within its risk threshold. This self-capability eliminates the need for expensive tele-operator intervention for common exceptions, thereby reducing operational costs while preserving quality assistance for complex situations.
Data Source
AI summary
Exception handing, such as of obstruction situations, by an autonomous vehicle (AV) is disclosed. A method includes identifying an exception situation; identifying a risk associated with autonomously resolving the exception situation; and in response to the risk exceeding a risk threshold, initiating a request for assistance from a tele-operator, and halting for the tele-operator to respond to the request; and receiving a response from the tele-operator.