Rehabilitation State Estimation Using Sensor Thresholds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Rehabilitation support systems face challenges in ensuring trainee safety during abnormal states, such as sudden falls, due to the difficulty for training staff to simultaneously perform multiple operations to prevent accidents.
Innovation Solution
A state estimation program and trained model that utilize sensor outputs and profile data to determine normal or abnormal states, with a rehabilitation support system incorporating a drive unit, sensor, state estimation unit, and information presentation unit to alert staff and control the system to prevent accidents.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a training staff member manually monitors and operates the rehabilitation support system during training, then the system can respond to abnormal states, but the staff member cannot simultaneously perform multiple operations, leading to delayed response and reduced safety
Solution Approach 1:
The rehabilitation support system performs self-monitoring and self-protection functions by automatically detecting abnormal states through sensors and executing protective actions without requiring manual intervention from the training staff member. The system monitors sensor outputs, compares them against thresholds, and autonomously stops operations when abnormalities are detected, enabling the system to serve its own safety needs.
Solution Approach 2:
The system continuously monitors sensor outputs during training and provides real-time feedback by comparing current sensor readings against pre-set thresholds. This feedback mechanism enables the system to detect abnormal states and trigger appropriate protective responses, creating a closed-loop control system that automatically adjusts operations based on real-time conditions.
2Speed
If the rehabilitation support system automatically monitors training state using sensor outputs, then the response speed to abnormal states improves, but the system complexity increases
Solution Approach 1:
The system performs preliminary actions by pre-setting thresholds for sensor outputs that define normal and abnormal states before training begins. These thresholds are configured in advance based on expected sensor readings during normal operation, enabling the system to immediately compare real-time sensor outputs against predetermined criteria and rapidly detect abnormalities without requiring complex real-time analysis algorithms.
3Measurement precision
If multiple sensors are used to monitor trainee state, then the accuracy of abnormal state detection improves, but the cost and complexity of the system increases
Solution Approach 1:
The sensor system is designed with multi-functionality where sensors serve multiple purposes: monitoring trainee position, detecting abnormal states, and providing data for both threshold-based detection and protective action triggering. The same sensor outputs are used for multiple monitoring functions, reducing the need for additional specialized sensors and maintaining detection accuracy while controlling system complexity.
Data Source
AI summary
A state estimation program is for causing a computer to function to determine a state of training in a rehabilitation support system used by a trainee to perform training of a preset motion and includes a threshold setting step and a state estimation step. The threshold setting step is for acquiring a sensor output, the sensor output being an output of a sensor included in the rehabilitation support system in the training performed by the trainee and setting a threshold for determining one of a normal state and an abnormal state of the training based on the sensor output. The state estimation step is for estimating whether the training is performed in the normal state or the abnormal state based on the threshold.