Embodiment and Manipulation Learning Process for a Humanoid Hand
Babies are born with simple manipulation capabilities such as reflexes to perceived stimuli. Initial discoveries by babies are accidental until they become coordinated and curious enough to actively investigate their surroundings. This thesis explores the development of such primitive learning...
| Main Author: | |
|---|---|
| Language: | en_US |
| Published: |
2004
|
| Online Access: | http://hdl.handle.net/1721.1/7064 |
| _version_ | 1826188795336196096 |
|---|---|
| author | Matsuoka, Yoky |
| author_facet | Matsuoka, Yoky |
| author_sort | Matsuoka, Yoky |
| collection | MIT |
| description | Babies are born with simple manipulation capabilities such as reflexes to perceived stimuli. Initial discoveries by babies are accidental until they become coordinated and curious enough to actively investigate their surroundings. This thesis explores the development of such primitive learning systems using an embodied light-weight hand with three fingers and a thumb. It is self-contained having four motors and 36 exteroceptor and proprioceptor sensors controlled by an on-palm microcontroller. Primitive manipulation is learned from sensory inputs using competitive learning, back-propagation algorithm and reinforcement learning strategies. This hand will be used for a humanoid being developed at the MIT Artificial Intelligence Laboratory. |
| first_indexed | 2024-09-23T08:05:08Z |
| id | mit-1721.1/7064 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T08:05:08Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | mit-1721.1/70642019-04-09T16:33:11Z Embodiment and Manipulation Learning Process for a Humanoid Hand Matsuoka, Yoky Babies are born with simple manipulation capabilities such as reflexes to perceived stimuli. Initial discoveries by babies are accidental until they become coordinated and curious enough to actively investigate their surroundings. This thesis explores the development of such primitive learning systems using an embodied light-weight hand with three fingers and a thumb. It is self-contained having four motors and 36 exteroceptor and proprioceptor sensors controlled by an on-palm microcontroller. Primitive manipulation is learned from sensory inputs using competitive learning, back-propagation algorithm and reinforcement learning strategies. This hand will be used for a humanoid being developed at the MIT Artificial Intelligence Laboratory. 2004-10-20T20:27:54Z 2004-10-20T20:27:54Z 1995-05-01 AITR-1546 http://hdl.handle.net/1721.1/7064 en_US AITR-1546 9161027 bytes 7404933 bytes application/postscript application/pdf application/postscript application/pdf |
| spellingShingle | Matsuoka, Yoky Embodiment and Manipulation Learning Process for a Humanoid Hand |
| title | Embodiment and Manipulation Learning Process for a Humanoid Hand |
| title_full | Embodiment and Manipulation Learning Process for a Humanoid Hand |
| title_fullStr | Embodiment and Manipulation Learning Process for a Humanoid Hand |
| title_full_unstemmed | Embodiment and Manipulation Learning Process for a Humanoid Hand |
| title_short | Embodiment and Manipulation Learning Process for a Humanoid Hand |
| title_sort | embodiment and manipulation learning process for a humanoid hand |
| url | http://hdl.handle.net/1721.1/7064 |
| work_keys_str_mv | AT matsuokayoky embodimentandmanipulationlearningprocessforahumanoidhand |