Mobility Aid Robot Abnormal Behavior Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current mobility aid robots lack an effective mechanism for detecting and responding to human abnormal behaviors such as not keeping up, abandoning the robot, elevated stress, and drowsiness, which are critical for ensuring user safety and experience, especially for elderly users.
Innovation Solution
The implementation of a human abnormal behavior response method using a user-facing camera and machine-learned models to detect and respond to abnormal behaviors by adjusting the robot's speed, suggesting breaks, or stopping assistance, and providing interventions like suggesting rest, through a navigation module and sensor subunit integrated into the mobility aid robot.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If mobility aid robots are developed with automated functions, then the mobility assistance capability is improved, but the ability to detect and respond to abnormal user behaviors is insufficient
Solution Approach 1:
The abnormal behavior detection system is segmented into multiple independent detection modules: face detection module, drowsiness detection module (detecting eye closure, head position), stress detection module (detecting facial expressions), and abandonment detection module. Each module independently monitors specific abnormal behaviors and triggers appropriate responses.
Solution Approach 2:
The system implements continuous feedback loops where sensor data from cameras and other sensors is constantly analyzed to detect abnormal behaviors. When abnormalities are detected, the system provides immediate feedback by adjusting robot speed, notifying users, or stopping assistance, creating a closed-loop control system that continuously monitors and responds to user state.
2Reliability
If multiple sensors and detection modules are added to detect abnormal behaviors, then the safety and user experience are improved, but the device complexity increases
Solution Approach 1:
The camera system serves multiple functions: it captures images for face detection, analyzes facial features for drowsiness detection, monitors eye closure for stress detection, and tracks user position for abandonment detection. This multi-functional approach allows comprehensive abnormal behavior monitoring using a single primary sensor platform, reducing overall system complexity.
Solution Approach 2:
Multiple detection functions (face detection, drowsiness detection, stress detection, abandonment detection) are merged into a unified abnormal behavior response system that shares common hardware resources (camera, processor) and integration architecture. The navigation module and sensor subunit are integrated to work together, consolidating control functions.
3Measurement precision
If the robot continuously monitors user behavior through camera and sensors, then the abnormal behavior detection accuracy is improved, but the energy consumption increases
Solution Approach 1:
The system performs periodic sampling of user behavior data through the camera and sensors rather than continuous full-resolution monitoring. Image processing and analysis are conducted at predetermined time intervals or triggered by specific events, reducing computational load and energy consumption while maintaining adequate detection accuracy for safety-critical behaviors.
Data Source
AI summary
Response methods to human abnormal behaviors for a mobility aid robot having a user-facing camera are disclosed. The mobility aid robot responds to human abnormal behaviors by detecting a face of a human during the robot aiding the human to move through the camera, comparing an initial size of the face and an immediate size of the face in response to the face of the human having detected during the robot aiding the human to move, determining the human as in abnormal behavior(s) in response to the immediate size of the face being smaller than the initial size of the face, and performing response(s) corresponding to the abnormal behavior(s) in response to the human being in the abnormal behavior(s), where the response(s) include slowing down the robot.