DEEP REINFORCEMENT LEARNING FOR MYOELECTRIC CONTROL OF UPPER LIMB MOVEMENTS

Limb dysfunction and, in some cases, even amputation is a reality that several people worldwide have to face on a daily basis. The objective of this research is to implement a Deep Reinforcement Learning model capable of moving a virtual arm in response to a person's brain activity. It also aims to explore and study the advantages and limitations of using these approaches to solve control problems in prosthetic robotics. With this in mind, the implementation structure can be divided into three main components. Firstly, processing the data that consists of electromyography (EMG) signals from the bicep and tricep muscles. Afterwards, the development and analysis of a supervised learning approach followed by different Reinforcement Learning scenarios. Finally, the work also addresses the generalisation problem by testing the performance of a trained model when facing a new subject's EMG signals. According to this analysis, the algorithm that offered the best results was a Deep Deterministic Policy Gradient version optimised for sample efficiency. It showed great potential to be used in real-life scenarios. However, when approaching the generalisation, this same algorithm showed inferior results, suggesting that further research is required.