You are here

ECE MS Thesis Defense: "Implementation of a Shared Control System for Brain-controlled Wheelchair Navigation," Rui Luo


501 ISEC

February 1, 2018 10:00 am
February 1, 2018 10:00 am

Individuals with physical disabilities continue to rely on electric wheelchairs and personalized human-machine interfaces for their mobility.

Even though the problem is well-studied in literature, the development of reliable shared control paradigms that supports different low throughput human machine interfaces for semi-autonomous wheelchairs has been a challenging problem. This work focuses on enhancing the shared position control methodology known as NoVeLTI (Navigation via Low Throughput Interfaces) in four areas. (1) A new wheelchair orientation controller with user interface is developed. This controller infers user's desired orientation of the wheelchair from detected commands using Bayes filter and then generates control commands to rotate the wheelchair after the desired position is reached; (2) The ROS implementation of the system architecture is redesigned to guarantee a stable communication channel among the system modules rather than rely on ROS topic; (3)A nonholonomic robot model is implemented in the original system to simulate the performance of a wheelchair in real environment; (4) An improved user interface has been designed and implemented in RViz according to feedback from the attenders of our simulation experiments . A set of experiments are designed to validate the improvements and evaluate the effect of different parameters in the system. Four human subjects were invited to conduct the experiment.  

Result shows that attenders are able to navigate the wheelchair via only four commands from simulated BCI model to any given destination on a map at an average success rate of 90%. The average navigation time of a 25 meters route is about 60 seconds at the velocity of 1m/s.

  • Professor Taskin Padir (Advisor)
  • Professor Hanumant Singh
  • Professor Robert Platt