TY - JOUR
T1 - A Bio-Inspired Mechanism for Learning Robot Motion From Mirrored Human Demonstrations
AU - Zahra, Omar
AU - Tolu, Silvia
AU - Zhou, Peng
AU - Duan, Anqing
AU - Navarro-Alarcon, David
N1 - Funding Information:
This work is supported in part by the Key-Area Research and Development Program of Guangdong Province 2020 under grant 2020B090928001, in part by the Research Grants Council of Hong Kong under grants 14203917 and 15212721, in part by the Jiangsu Industrial Technology Research Institute Collaborative Research Program Scheme under grant ZG9V, and in part by The Hong Kong Polytechnic University under grant UAKU.
Publisher Copyright:
Copyright © 2022 Zahra, Tolu, Zhou, Duan and Navarro-Alarcon.
PY - 2022/3/14
Y1 - 2022/3/14
N2 - Different learning modes and mechanisms allow faster and better acquisition of skills as widely studied in humans and many animals. Specific neurons, called mirror neurons, are activated in the same way whether an action is performed or simply observed. This suggests that observing others performing movements allows to reinforce our motor abilities. This implies the presence of a biological mechanism that allows creating models of others' movements and linking them to the self-model for achieving mirroring. Inspired by such ability, we propose to build a map of movements executed by a teaching agent and mirror the agent's state to the robot's configuration space. Hence, in this study, a neural network is proposed to integrate a motor cortex-like differential map transforming motor plans from task-space to joint-space motor commands and a static map correlating joint-spaces of the robot and a teaching agent. The differential map is developed based on spiking neural networks while the static map is built as a self-organizing map. The developed neural network allows the robot to mirror the actions performed by a human teaching agent to its own joint-space and the reaching skill is refined by the complementary examples provided. Hence, experiments are conducted to quantify the improvement achieved thanks to the proposed learning approach and control scheme.
AB - Different learning modes and mechanisms allow faster and better acquisition of skills as widely studied in humans and many animals. Specific neurons, called mirror neurons, are activated in the same way whether an action is performed or simply observed. This suggests that observing others performing movements allows to reinforce our motor abilities. This implies the presence of a biological mechanism that allows creating models of others' movements and linking them to the self-model for achieving mirroring. Inspired by such ability, we propose to build a map of movements executed by a teaching agent and mirror the agent's state to the robot's configuration space. Hence, in this study, a neural network is proposed to integrate a motor cortex-like differential map transforming motor plans from task-space to joint-space motor commands and a static map correlating joint-spaces of the robot and a teaching agent. The differential map is developed based on spiking neural networks while the static map is built as a self-organizing map. The developed neural network allows the robot to mirror the actions performed by a human teaching agent to its own joint-space and the reaching skill is refined by the complementary examples provided. Hence, experiments are conducted to quantify the improvement achieved thanks to the proposed learning approach and control scheme.
KW - imitation learning
KW - robotics
KW - sensor-based control
KW - spiking neural networks
KW - visual servoing
UR - http://www.scopus.com/inward/record.url?scp=85127022431&partnerID=8YFLogxK
U2 - 10.3389/fnbot.2022.826410
DO - 10.3389/fnbot.2022.826410
M3 - Journal article
AN - SCOPUS:85127022431
SN - 1662-5218
VL - 16
JO - Frontiers in Neurorobotics
JF - Frontiers in Neurorobotics
M1 - 826410
ER -