Robotic Co-Working Fatigue Detection Using Non-Intrusive Force Sensing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current robotic systems face challenges in detecting localized muscle fatigue in co-working environments, particularly when collaborating with humans on tasks that involve heavy loads, as existing methods are either intrusive or ineffective in distinguishing between overall fatigue and localized muscle fatigue, posing safety risks if not addressed proactively.
Innovation Solution
A non-intrusive robotic system equipped with a force sensor mounted on a robotic organ that senses and analyzes the force applied by local muscles of a subject, enabling real-time detection of fatigue states, including non-fatigue, intermediate, and critical fatigue levels, and generates alerts to abort tasks if critical fatigue is detected, ensuring safety without requiring user-specific training or adaptation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If intrusive sensor methods are used to detect muscle fatigue, then measurement precision is improved, but ease of operation deteriorates
Solution Approach 1:
The patent replaces intrusive mechanical sensors (EMG electrodes, force sensors on user body) with an optical vision-based system that captures images and analyzes muscle deformation visually, eliminating the need for physical sensor attachment to the user while maintaining fatigue detection capability
Solution Approach 2:
The patent introduces an intermediary computational model that infers muscle fatigue state from visual observations of muscle deformation, acting as a mediator between the external camera system and the internal physiological state without direct physical contact with the user
2Ease of operation
If video based non-intrusive techniques are used to detect overall fatigue, then ease of operation is improved, but measurement precision deteriorates
Solution Approach 1:
The patent focuses the vision system specifically on detecting localized muscle deformation in the region of interest rather than attempting to detect overall fatigue, using region-of-interest extraction and localized strain calculation to achieve precise measurement of specific muscle groups involved in the collaborative task
Solution Approach 2:
The patent transforms the detection parameter from overall fatigue indicators (yawn frequency, eye closure) to localized muscle deformation parameters (strain, curvature changes) by modifying the image processing and analysis approach to focus on specific muscle regions and their mechanical behavior
3Reliability
If real-time fatigue detection is implemented in co-working environment, then reliability is improved, but device complexity increases
Solution Approach 1:
The patent makes the vision system multi-functional by using the same camera and image processing pipeline for both task monitoring and fatigue detection, allowing the system to serve multiple purposes (safety monitoring, performance analysis, collaboration quality assessment) without requiring separate dedicated sensors for each function
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The system provides accurate, real-time detection of fatigue states with low mis-detections and false positives, ensuring a safer co-working environment by quantifying muscle fatigue states and predicting potential extreme fatigue, allowing proactive measures to prevent accidents.
Implementation Method 1
receive, from the sensor module, a signal corresponding to a force applied by a localized muscle of a subject, sensed by the sensor
Data Source
Figure 1
Figure 2
Figure 3a
AI summary
A method and a robotic system for online localized fatigue-state detection of a subject in a co-working environment using a non-intrusive approach is disclosed. A force sensor, mounted on the robotic system is capable of capturing effective force applied by local muscles of the subject co-working with the robotic system, providing a non-intrusive sensing. The captured force is analyzed on-line by the robotic system 102 to detect current fatigue state of the subject and proactively predict the future state of the subject. Thus, enables alerting the subject before time avoiding any possible accident.