Biopotential-Informed Reward Inference and Constraint Design for Consecutive Upper-Limb Motor Coordination Tasks in Robot Manipulation
- 1Department of Computer Science, Yonsei University, Wonju 26493, Republic of Korea
- 2Human Assistive Neurorobotics Laboratory, Yonsei University, Wonju 26493, Republic of Korea
- 3Department of Software, Yonsei University, Wonju 26493, Republic of Korea
Abstract
In consecutive upper-limb motor coordination tasks, where a new condition is imposed once a subgoal is achieved, kinematic demonstrations reveal what a human does but not how cautiously, so existing imitation learning misses the adaptation to the new condition. To close this gap, we propose designing reward and constraint functions from biopotential-informed characteristics of human surface electromyography (sEMG). The task begins as a Markov decision process (MDP) and turns into a constrained MDP (cMDP) once the first subtask is completed. The sEMG data are decomposed into shared and task-specific muscle synergies; the former infers a quadratic-regulator-formed reward by inverse optimal control, and the latter defines a subtlety coefficient bounding the action magnitude in the constrained phase. A two-holes two-balls patience cube exemplifies the task, and the policy is trained by constrained policy optimization and deployed on a robot manipulator. Whereas unconstrained PPO and SAC agents complete the constrained phase in only 1% of the episodes, the proposed agent completes 100% with the shortest completion time (1.76 s) among four constrained variants and most closely reproduces the human’s dwell-time distribution and zone transitions near the hole, yielding a feasible and human-like policy.
Related
- Physics-Informed Graph-Based Safe RL with Constraint-Specific Critics for Community Battery Coordination in Distribution Network
- Asymptotic Optimality of cμ-Rule for LLM Inference Scheduling under Memory Constraint
- Manipulation-Robust Prediction
- Distinct Consecutive Products
- Counting consecutive multiplicatively dependent triples
BibTeX
@article{jung2026biopotentialinformed,
title = {{Biopotential-Informed Reward Inference and Constraint Design for Consecutive Upper-Limb Motor Coordination Tasks in Robot Manipulation}},
author = {Ho-Jin Jung and Jang-Hyeon Kim and Han-Ul Yoon},
journal = {Mathematics},
year = {2026},
month = oct,
doi = {10.3390/math14203718},
url = {https://www.mdpi.com/2227-7390/14/20/3718},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Biopotential-Informed Reward Inference and Constraint Design for Consecutive Upper-Limb Motor Coordination Tasks in Robot Manipulation
AU - Ho-Jin Jung
AU - Jang-Hyeon Kim
AU - Han-Ul Yoon
PY - 2026
DA - 2026/10/13
JO - Mathematics
DO - 10.3390/math14203718
UR - https://www.mdpi.com/2227-7390/14/20/3718
AB - In consecutive upper-limb motor coordination tasks, where a new condition is imposed once a subgoal is achieved, kinematic demonstrations reveal what a human does but not how cautiously, so existing imitation learning misses the adaptation to the new condition. To close this gap, we propose designing reward and constraint functions from biopotential-informed characteristics of human surface electromyography (sEMG). The task begins as a Markov decision process (MDP) and turns into a constrained MDP (cMDP) once the first subtask is completed. The sEMG data are decomposed into shared and task-specific muscle synergies; the former infers a quadratic-regulator-formed reward by inverse optimal control, and the latter defines a subtlety coefficient bounding the action magnitude in the constrained phase. A two-holes two-balls patience cube exemplifies the task, and the policy is trained by constrained policy optimization and deployed on a robot manipulator. Whereas unconstrained PPO and SAC agents complete the constrained phase in only 1% of the episodes, the proposed agent completes 100% with the shortest completion time (1.76 s) among four constrained variants and most closely reproduces the human’s dwell-time distribution and zone transitions near the hole, yielding a feasible and human-like policy.
SN - 2227-7390
ER -