Achieving natural behavior in a robot using neurally inspired hierarchical perceptual control
Summary: Terrestrial locomotion presents tremendous computational challenges on account of the enormous degrees of freedom in legged animals, and complex, unpredictable properties of natural environments, including the body and its effectors, yet the nervous system can achieve locomotion with ease....
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2021-09-01
|
| Series: | iScience |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2589004221009160 |
| _version_ | 1818669816159928320 |
|---|---|
| author | Joseph W. Barter Henry H. Yin |
| author_facet | Joseph W. Barter Henry H. Yin |
| author_sort | Joseph W. Barter |
| collection | DOAJ |
| description | Summary: Terrestrial locomotion presents tremendous computational challenges on account of the enormous degrees of freedom in legged animals, and complex, unpredictable properties of natural environments, including the body and its effectors, yet the nervous system can achieve locomotion with ease. Here we introduce a quadrupedal robot that is capable of posture control and goal-directed locomotion across uneven terrain. The control architecture is a hierarchical network of simple negative feedback control systems inspired by the organization of the vertebrate nervous system. This robot is capable of robust posture control and locomotion in novel environments with unpredictable disturbances. Unlike current robots, our robot does not use internal inverse and forward models, nor does it require any training in order to perform successfully in novel environments. |
| first_indexed | 2024-12-17T06:58:13Z |
| format | Article |
| id | doaj.art-d2508258bb274342be2d7048b79186ce |
| institution | Directory Open Access Journal |
| issn | 2589-0042 |
| language | English |
| last_indexed | 2024-12-17T06:58:13Z |
| publishDate | 2021-09-01 |
| publisher | Elsevier |
| record_format | Article |
| series | iScience |
| spelling | doaj.art-d2508258bb274342be2d7048b79186ce2022-12-21T21:59:21ZengElsevieriScience2589-00422021-09-01249102948Achieving natural behavior in a robot using neurally inspired hierarchical perceptual controlJoseph W. Barter0Henry H. Yin1Department of Psychology and Neuroscience, Duke University, Durham, NC 27708, USADepartment of Psychology and Neuroscience, Duke University, Durham, NC 27708, USA; Department of Neurobiology, Duke University School of Medicine, Durham, NC 27708, USA; Corresponding authorSummary: Terrestrial locomotion presents tremendous computational challenges on account of the enormous degrees of freedom in legged animals, and complex, unpredictable properties of natural environments, including the body and its effectors, yet the nervous system can achieve locomotion with ease. Here we introduce a quadrupedal robot that is capable of posture control and goal-directed locomotion across uneven terrain. The control architecture is a hierarchical network of simple negative feedback control systems inspired by the organization of the vertebrate nervous system. This robot is capable of robust posture control and locomotion in novel environments with unpredictable disturbances. Unlike current robots, our robot does not use internal inverse and forward models, nor does it require any training in order to perform successfully in novel environments.http://www.sciencedirect.com/science/article/pii/S2589004221009160Biological sciencesNeuroscienceSensory neuroscienceRobotics |
| spellingShingle | Joseph W. Barter Henry H. Yin Achieving natural behavior in a robot using neurally inspired hierarchical perceptual control iScience Biological sciences Neuroscience Sensory neuroscience Robotics |
| title | Achieving natural behavior in a robot using neurally inspired hierarchical perceptual control |
| title_full | Achieving natural behavior in a robot using neurally inspired hierarchical perceptual control |
| title_fullStr | Achieving natural behavior in a robot using neurally inspired hierarchical perceptual control |
| title_full_unstemmed | Achieving natural behavior in a robot using neurally inspired hierarchical perceptual control |
| title_short | Achieving natural behavior in a robot using neurally inspired hierarchical perceptual control |
| title_sort | achieving natural behavior in a robot using neurally inspired hierarchical perceptual control |
| topic | Biological sciences Neuroscience Sensory neuroscience Robotics |
| url | http://www.sciencedirect.com/science/article/pii/S2589004221009160 |
| work_keys_str_mv | AT josephwbarter achievingnaturalbehaviorinarobotusingneurallyinspiredhierarchicalperceptualcontrol AT henryhyin achievingnaturalbehaviorinarobotusingneurallyinspiredhierarchicalperceptualcontrol |