Related Experiment Video
Updated: May 17, 2026
Training Persons with Spinal Cord Injury to Ambulate Using a Powered Exoskeleton
Published on: June 16, 2016
Case-based reasoning emulation of persons for wheelchair navigation
Jose Manuel Peula1, Cristina Urdiales, Ignacio Herrero
1Grupo Ingenieria de Sistemas Integrados, ISIS, Departamento de Tecnologia Electronica, Universidad of Malaga, Escuela Tecnica Superior de Ingenieria de Telecomunicacion, Campus de Teatinos, 29071 Malaga, Spain. peula@uma.es
This study developed a tool to automatically test power wheelchairs by emulating diverse user driving behaviors using case-based reasoning (CBR). The system realistically simulates individuals with various disabilities, improving safety and testing efficiency for assistive navigation systems.
Area of Science:
- Robotics
- Human-Computer Interaction
- Assistive Technology
Background:
- Power wheelchair testing requires diverse user input, which is practically challenging.
- Realistic simulations are crucial for robust and safe assistive navigation systems.
- Existing simulation methods may lack the nuanced realism of individual user driving patterns.
Purpose of the Study:
- To present a tool for automatic wheelchair testing through realistic emulation of diverse users.
- To improve the safety and efficacy of power wheelchair development.
- To bridge the gap between simulation and real-world user testing.
Main Methods:
- Extracting driving data from real power wheelchair users.
- Training a case-based reasoning (CBR) system to learn individual driving behaviors.
- Using the trained CBR system to emulate specific user driving patterns in new scenarios.
Main Results:
- The system accurately emulated users with different disabilities, showing minimal path deviation (mean 10cm).
- Emulated users exhibited more realistic, less homogeneous driving patterns than traditional methods.
- The approach demonstrated generality by performing well on unseen paths and differentiating behaviors of users with specific conditions like apraxia and dementia.
Conclusions:
- The developed system effectively emulates diverse user driving behaviors in indoor environments.
- This emulation tool is suitable for early-stage testing of assistive navigation systems.
- The approach enhances the realism and practicality of wheelchair testing protocols.
