Surgical Assistance Control Handover Using ML Self-Evaluation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing assistance systems struggle with the handover of automation back to the operator when they can no longer reliably perform planning and/or control tasks autonomously.
Innovation Solution
An assistance system with an evaluation component and machine learning capabilities that allows for learning and evaluation modes, enabling it to assess its own performance and switch between guidance and assistance modes based on the reliability of generated instructions, ensuring a seamless handover to the operator when necessary.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the assistance system operates in control mode with high automation, then productivity and safety are improved, but the system cannot reliably determine when to handover control back to the operator
Solution Approach 1:
The patent implements a feedback mechanism where the assistance system continuously evaluates the current situation and compares it against learned patterns from the machine learning system. This feedback loop enables the system to autonomously determine when automation can no longer perform reliably and when handover to the operator is necessary, resolving the contradiction between maintaining high automation and ensuring reliable handover capability
Solution Approach 2:
The system employs self-service through autonomous self-evaluation capabilities. The assistance system uses the machine learning system to independently assess its own performance and reliability in real-time, determining when it should maintain control or transfer control to the operator without external intervention, thus enabling reliable handover decisions while maintaining high automation
2Reliability
If the assistance system continuously monitors situation state to maintain situational awareness, then reliability is improved, but the system complexity increases
Solution Approach 1:
The patent introduces the machine learning system as an intermediary component that processes and evaluates situation data. This intermediary handles the complex analysis of situational awareness requirements, allowing the main assistance system to maintain reliability through continuous monitoring while offloading computational complexity to the specialized machine learning module, thus managing system complexity effectively
Data Source
Figure 1
AI summary
The invention relates to an assistance system for supporting an operator in planning and/or control tasks of a situation to be monitored, wherein the assistance system automatically generates planning and/or control-related instructions in a control mode with respect to specific states of the situation to be monitored and is configured to carry out the planning and/or control task of the situation to be monitored essentially autonomously based on the generated planning and/or control-related instructions, characterized in that the assistance system has an evaluation component which has an optionally activatable learning mode and evaluation mode and is configured to train an evaluation of planning and/or control-related instructions with respect to a specific state of the situation to be monitored in a machine learning system in learning mode.and - in evaluation mode, to determine an evaluation of a specific planning and/or control-related instruction with respect to a specific state of the situation to be monitored from the trained machine learning system; wherein the assistance system is further configured - to activate the evaluation mode of the evaluation component when the control mode is activated, - then to determine, using the evaluation component, an evaluation of a planning and/or control-related instruction automatically generated from the trained machine learning system based on a specific state of the situation to be monitored, and - depending on the determined evaluation, to leave the control mode in the activated state or to deactivate it.