Incremental Development of Multiple Tool Models for Robotic Reaching Through Autonomous Exploration
Autonomy and flexibility are two major requirements for modern robots. In particular, humanoid robots should learn new skills incrementally through autonomous exploration, and adapt to different contexts. In this paper we consider the problem of learning forward models for task space control under d...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
De Gruyter
2012-09-01
|
| Series: | Paladyn |
| Subjects: | |
| Online Access: | https://doi.org/10.2478/s13230-013-0102-z |
| _version_ | 1827610168326619136 |
|---|---|
| author | Jamone Lorenzo Damas Bruno Endo Nobotsuna Santos-Victor José Takanishi Atsuo |
| author_facet | Jamone Lorenzo Damas Bruno Endo Nobotsuna Santos-Victor José Takanishi Atsuo |
| author_sort | Jamone Lorenzo |
| collection | DOAJ |
| description | Autonomy and flexibility are two major requirements for modern robots. In particular, humanoid robots should learn new skills incrementally through autonomous exploration, and adapt to different contexts. In this paper we consider the problem of learning forward models for task space control under dynamically varying kinematic contexts: the robot learns incrementally and autonomously its forward kinematics under different contexts, represented by the inclusion of different tools, and exploits the learned model to realize reaching with those tools. We model the forward kinematics as a multi-valued function, in which different outputs for the same input query are related to different tools (i.e. contexts). The model is estimated using IMLE, a recent online learning algorithm for multi-valued regression, and used for control. No information is given about the tool changes, nor any assumption is made about the tool kinematics. Results are provided both in simulation and with a full-body humanoid. In the latter case we show how the robot successfully performs reaching using a flexible tool, a clear example of complex kinematics. |
| first_indexed | 2024-03-09T07:45:00Z |
| format | Article |
| id | doaj.art-100bfe83da8c4e748ae387689b9b4d73 |
| institution | Directory Open Access Journal |
| issn | 2081-4836 |
| language | English |
| last_indexed | 2024-03-09T07:45:00Z |
| publishDate | 2012-09-01 |
| publisher | De Gruyter |
| record_format | Article |
| series | Paladyn |
| spelling | doaj.art-100bfe83da8c4e748ae387689b9b4d732023-12-03T03:18:30ZengDe GruyterPaladyn2081-48362012-09-013311312710.2478/s13230-013-0102-zIncremental Development of Multiple Tool Models for Robotic Reaching Through Autonomous ExplorationJamone Lorenzo0Damas Bruno1Endo Nobotsuna2Santos-Victor José3Takanishi Atsuo4 Faculty of Science and Engineering, Waseda University, Tokyo, Japan Instituto de Sistemas e Robótica, Instituto Superior Técnico, Lisboa, Portugal Faculty of Science and Engineering, Waseda University, Tokyo, Japan Instituto de Sistemas e Robótica, Instituto Superior Técnico, Lisboa, Portugal Faculty of Science and Engineering, Waseda University, Tokyo, JapanAutonomy and flexibility are two major requirements for modern robots. In particular, humanoid robots should learn new skills incrementally through autonomous exploration, and adapt to different contexts. In this paper we consider the problem of learning forward models for task space control under dynamically varying kinematic contexts: the robot learns incrementally and autonomously its forward kinematics under different contexts, represented by the inclusion of different tools, and exploits the learned model to realize reaching with those tools. We model the forward kinematics as a multi-valued function, in which different outputs for the same input query are related to different tools (i.e. contexts). The model is estimated using IMLE, a recent online learning algorithm for multi-valued regression, and used for control. No information is given about the tool changes, nor any assumption is made about the tool kinematics. Results are provided both in simulation and with a full-body humanoid. In the latter case we show how the robot successfully performs reaching using a flexible tool, a clear example of complex kinematics.https://doi.org/10.2478/s13230-013-0102-zmotor learning and adaptationhumanoid robotsreaching with toolsdevelopmental roboticscontinuous online learning |
| spellingShingle | Jamone Lorenzo Damas Bruno Endo Nobotsuna Santos-Victor José Takanishi Atsuo Incremental Development of Multiple Tool Models for Robotic Reaching Through Autonomous Exploration Paladyn motor learning and adaptation humanoid robots reaching with tools developmental robotics continuous online learning |
| title | Incremental Development of Multiple Tool Models for Robotic Reaching Through Autonomous Exploration |
| title_full | Incremental Development of Multiple Tool Models for Robotic Reaching Through Autonomous Exploration |
| title_fullStr | Incremental Development of Multiple Tool Models for Robotic Reaching Through Autonomous Exploration |
| title_full_unstemmed | Incremental Development of Multiple Tool Models for Robotic Reaching Through Autonomous Exploration |
| title_short | Incremental Development of Multiple Tool Models for Robotic Reaching Through Autonomous Exploration |
| title_sort | incremental development of multiple tool models for robotic reaching through autonomous exploration |
| topic | motor learning and adaptation humanoid robots reaching with tools developmental robotics continuous online learning |
| url | https://doi.org/10.2478/s13230-013-0102-z |
| work_keys_str_mv | AT jamonelorenzo incrementaldevelopmentofmultipletoolmodelsforroboticreachingthroughautonomousexploration AT damasbruno incrementaldevelopmentofmultipletoolmodelsforroboticreachingthroughautonomousexploration AT endonobotsuna incrementaldevelopmentofmultipletoolmodelsforroboticreachingthroughautonomousexploration AT santosvictorjose incrementaldevelopmentofmultipletoolmodelsforroboticreachingthroughautonomousexploration AT takanishiatsuo incrementaldevelopmentofmultipletoolmodelsforroboticreachingthroughautonomousexploration |