Reinforcement Learning for Energy Optimization Under Human Fatigue Constraints of Power-Assisted Wheelchairs - Université Polytechnique des Hauts-de-France Access content directly
Conference Papers Year :

Reinforcement Learning for Energy Optimization Under Human Fatigue Constraints of Power-Assisted Wheelchairs

Guoxi Feng
  • Function : Author
Lucian Busoniu
  • Function : Author
  • PersonId : 933138
Sami Mohammad
  • Function : Author

Abstract

In the last decade, Power-Assisted Wheelchairs (PAWs) have been widely used for improving the mobility of disabled persons. The main advantage of PAWs is that users can keep a suitable physical activity. Moreover, the metabolic-electrical energy hybridization of PAWs provides more flexibility for optimal control design. In this context, we propose an optimal control for minimizing the electrical energy consumption under human fatigue constraints, including a human fatigue model. The electrical motor has to cooperate with the user over a given distance-to-go. As the human fatigue model is unknown in practice, we use model-free Policy Gradient methods to directly learn controllers for a given driving task. We verify that the model-free solution is near-optimal by computing the model-based controller, which is generated by Approximate Dynamic Programming. Simulation results confirm that the model-free Policy Gradient method provides near-optimal solutions.

Domains

Automatic
Not file

Dates and versions

hal-03411218 , version 1 (02-11-2021)

Identifiers

Cite

Guoxi Feng, Lucian Busoniu, Thierry-Marie Guerra, Sami Mohammad. Reinforcement Learning for Energy Optimization Under Human Fatigue Constraints of Power-Assisted Wheelchairs. 2018 Annual American Control Conference (ACC), Jun 2018, Milwaukee, WI, United States. pp.4117-4122, ⟨10.23919/ACC.2018.8431038⟩. ⟨hal-03411218⟩
6 View
0 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More