Error-related potential-based shared autonomy via deep recurrent reinforcement learning

Abstract

Error-related potential (ErrP)-based brain-computer interfaces (BCIs) have received a considerable amount of attention in the human-robot interaction community. In contrast to traditional BCI, which requires continuous and explicit commands from an operator, ErrP-based BCI leverages the ErrP, which is evoked when an operator observes unexpected behaviours from the robot counterpart. This paper proposes a novel shared autonomy model for ErrP-based human-robot interaction. We incorporate ErrP information provided by a user as useful observations for an agent and formulate the shared autonomy problem as a partially observable Markov decision process (POMDP). A recurrent neural network-based actor-critic model is used to address the uncertainty in the ErrP signal. We evaluate the proposed framework using a simulated human-in-the-loop robot navigation scenario with both simulated users and real users. The results show that the proposed ErrP-based shared autonomy model enables an autonomous robot to complete navigation tasks more efficiently. In a simulation with 70\% ErrP accuracy, agents completed the task 14.1% faster than in the no ErrP condition, while with real users, agents completed the navigation task 14.9 % faster.

Combining brain-computer interfaces with deep reinforcement learning for robot training: a feasibility study in a simulation environment

“…Possible implications are the design of human-in-the-loop applications while interacting with robots (Salazar-Gomez et al, 2017 ; Xavier Fidêncio et al, 2022 ) or personalized AI systems to support and optimize machine decisions in (shared) autonomous vehicles or assistant interfaces for emergency situations (Shin et al, 2022 ; Wang et al, 2022 ). Another interesting application would be the usage in medical applications as training for a new generation of cognitive-assisted surgical robots (Wagner et al, 2021 ).…”