Learning stable in-grasp manipulation in a non-dropping action space

Traditionally, dexterous manipulation controllers are designed using analytic models constrained by strong assumptions about the hand and the objects being manipulated. Reinforcement learning (RL) has become another common approach in which skills are explored openly in an end-to-end manner but is inefficient because of unnoticeable instability and conflicts in learning objectives. This paper attempts to efficiently explore stable and accurate manipulation skills by decomposing dexterous skills into multiple simpler/analyzable components. Each skill component is subsequently learned with constraints and guidance from classical physics and control theory. Our work shows that for stable grasp, in-grasp reposition/reorientation with different objects, sensor/motor noise, latency, and frictional conditions, skill learning becomes efficient and stable with prior knowledge from theory. A video for each skill learning is available on the project website (https://hathanglongdoan.github.io/Learning_stable_in-grasp_manipulation/)

Authors

Institutions

Publication Details

Journal
Advanced Robotics
Published
2026-11-19
DOI
https://doi.org/10.1080/01691864.2026.2759397
Primary Topic
Robot Manipulation and Learning
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Learning stable in-grasp manipulation in a non-dropping action space

Kenji Tahara, Ha Thang Long Doan, Hikaru Arita, Kazuto Nakashima
Advanced Robotics
Robot Manipulation and Learning
article

Learning stable in-grasp manipulation in a non-dropping action space

Kenji Tahara, Ha Thang Long Doan, Hikaru Arita, Kazuto Nakashima
article en

Abstract

Traditionally, dexterous manipulation controllers are designed using analytic models constrained by strong assumptions about the hand and the objects being manipulated. Reinforcement learning (RL) has become another common approach in which skills are explored openly in an end-to-end manner but is inefficient because of unnoticeable instability and conflicts in learning objectives. This paper attempts to efficiently explore stable and accurate manipulation skills by decomposing dexterous skills into multiple simpler/analyzable components. Each skill component is subsequently learned with constraints and guidance from classical physics and control theory. Our work shows that for stable grasp, in-grasp reposition/reorientation with different objects, sensor/motor noise, latency, and frictional conditions, skill learning becomes efficient and stable with prior knowledge from theory. A video for each skill learning is available on the project website (https://hathanglongdoan.github.io/Learning_stable_in-grasp_manipulation/)

Advanced Robotics
Kyushu University (JP)
Japan Society for the Promotion of Science
Robot Manipulation and Learning
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon