Constraint-Aware Policy for Compliant Manipulation
Robot manipulation in a physically constrained environment requires compliant manipulation. Compliant manipulation is a manipulation skill to adjust hand motion based on the force imposed by the environment. Recently, reinforcement learning (RL) has been applied to solve household operations involvi...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Robotics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2218-6581/13/1/8 |
| _version_ | 1797342572563136512 |
|---|---|
| author | Daichi Saito Kazuhiro Sasabuchi Naoki Wake Atsushi Kanehira Jun Takamatsu Hideki Koike Katsushi Ikeuchi |
| author_facet | Daichi Saito Kazuhiro Sasabuchi Naoki Wake Atsushi Kanehira Jun Takamatsu Hideki Koike Katsushi Ikeuchi |
| author_sort | Daichi Saito |
| collection | DOAJ |
| description | Robot manipulation in a physically constrained environment requires compliant manipulation. Compliant manipulation is a manipulation skill to adjust hand motion based on the force imposed by the environment. Recently, reinforcement learning (RL) has been applied to solve household operations involving compliant manipulation. However, previous RL methods have primarily focused on designing a policy for a specific operation that limits their applicability and requires separate training for every new operation. We propose a constraint-aware policy that is applicable to various unseen manipulations by grouping several manipulations together based on the type of physical constraint involved. The type of physical constraint determines the characteristic of the imposed force direction; thus, a generalized policy is trained in the environment and reward designed on the basis of this characteristic. This paper focuses on two types of physical constraints: prismatic and revolute joints. Experiments demonstrated that the same policy could successfully execute various compliant manipulation operations, both in the simulation and reality. We believe this study is the first step toward realizing a generalized household robot. |
| first_indexed | 2024-03-08T10:35:14Z |
| format | Article |
| id | doaj.art-351ea0d35c4f4b5b84b4c4696b478b2b |
| institution | Directory Open Access Journal |
| issn | 2218-6581 |
| language | English |
| last_indexed | 2024-03-08T10:35:14Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Robotics |
| spelling | doaj.art-351ea0d35c4f4b5b84b4c4696b478b2b2024-01-26T18:21:33ZengMDPI AGRobotics2218-65812023-12-01131810.3390/robotics13010008Constraint-Aware Policy for Compliant ManipulationDaichi Saito0Kazuhiro Sasabuchi1Naoki Wake2Atsushi Kanehira3Jun Takamatsu4Hideki Koike5Katsushi Ikeuchi6School of Computing, Tokyo Institute of Technology, Tokyo 152-8550, JapanApplied Robotics Research, Microsoft, Redmond, WA 98052, USAApplied Robotics Research, Microsoft, Redmond, WA 98052, USAApplied Robotics Research, Microsoft, Redmond, WA 98052, USAApplied Robotics Research, Microsoft, Redmond, WA 98052, USASchool of Computing, Tokyo Institute of Technology, Tokyo 152-8550, JapanApplied Robotics Research, Microsoft, Redmond, WA 98052, USARobot manipulation in a physically constrained environment requires compliant manipulation. Compliant manipulation is a manipulation skill to adjust hand motion based on the force imposed by the environment. Recently, reinforcement learning (RL) has been applied to solve household operations involving compliant manipulation. However, previous RL methods have primarily focused on designing a policy for a specific operation that limits their applicability and requires separate training for every new operation. We propose a constraint-aware policy that is applicable to various unseen manipulations by grouping several manipulations together based on the type of physical constraint involved. The type of physical constraint determines the characteristic of the imposed force direction; thus, a generalized policy is trained in the environment and reward designed on the basis of this characteristic. This paper focuses on two types of physical constraints: prismatic and revolute joints. Experiments demonstrated that the same policy could successfully execute various compliant manipulation operations, both in the simulation and reality. We believe this study is the first step toward realizing a generalized household robot.https://www.mdpi.com/2218-6581/13/1/8compliant manipulationreinforcement learningLearning-from-Observation |
| spellingShingle | Daichi Saito Kazuhiro Sasabuchi Naoki Wake Atsushi Kanehira Jun Takamatsu Hideki Koike Katsushi Ikeuchi Constraint-Aware Policy for Compliant Manipulation Robotics compliant manipulation reinforcement learning Learning-from-Observation |
| title | Constraint-Aware Policy for Compliant Manipulation |
| title_full | Constraint-Aware Policy for Compliant Manipulation |
| title_fullStr | Constraint-Aware Policy for Compliant Manipulation |
| title_full_unstemmed | Constraint-Aware Policy for Compliant Manipulation |
| title_short | Constraint-Aware Policy for Compliant Manipulation |
| title_sort | constraint aware policy for compliant manipulation |
| topic | compliant manipulation reinforcement learning Learning-from-Observation |
| url | https://www.mdpi.com/2218-6581/13/1/8 |
| work_keys_str_mv | AT daichisaito constraintawarepolicyforcompliantmanipulation AT kazuhirosasabuchi constraintawarepolicyforcompliantmanipulation AT naokiwake constraintawarepolicyforcompliantmanipulation AT atsushikanehira constraintawarepolicyforcompliantmanipulation AT juntakamatsu constraintawarepolicyforcompliantmanipulation AT hidekikoike constraintawarepolicyforcompliantmanipulation AT katsushiikeuchi constraintawarepolicyforcompliantmanipulation |