Neural Circuit Architectural Priors for Quadruped Locomotion
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917798932905984 |
|---|---|
| author | Bhattasali, Nikhil X. Pattabiraman, Venkatesh Pinto, Lerrel Lindsay, Grace W. |
| author_facet | Bhattasali, Nikhil X. Pattabiraman, Venkatesh Pinto, Lerrel Lindsay, Grace W. |
| contents | Learning-based approaches to quadruped locomotion commonly adopt generic policy architectures like fully connected MLPs. As such architectures contain few inductive biases, it is common in practice to incorporate priors in the form of rewards, training curricula, imitation data, or trajectory generators. In nature, animals are born with priors in the form of their nervous system's architecture, which has been shaped by evolution to confer innate ability and efficient learning. For instance, a horse can walk within hours of birth and can quickly improve with practice. Such architectural priors can also be useful in ANN architectures for AI. In this work, we explore the advantages of a biologically inspired ANN architecture for quadruped locomotion based on neural circuits in the limbs and spinal cord of mammals. Our architecture achieves good initial performance and comparable final performance to MLPs, while using less data and orders of magnitude fewer parameters. Our architecture also exhibits better generalization to task variations, even admitting deployment on a physical robot without standard sim-to-real methods. This work shows that neural circuits can provide valuable architectural priors for locomotion and encourages future work in other sensorimotor skills. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_07174 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Neural Circuit Architectural Priors for Quadruped Locomotion Bhattasali, Nikhil X. Pattabiraman, Venkatesh Pinto, Lerrel Lindsay, Grace W. Neurons and Cognition Artificial Intelligence Machine Learning Neural and Evolutionary Computing Robotics Learning-based approaches to quadruped locomotion commonly adopt generic policy architectures like fully connected MLPs. As such architectures contain few inductive biases, it is common in practice to incorporate priors in the form of rewards, training curricula, imitation data, or trajectory generators. In nature, animals are born with priors in the form of their nervous system's architecture, which has been shaped by evolution to confer innate ability and efficient learning. For instance, a horse can walk within hours of birth and can quickly improve with practice. Such architectural priors can also be useful in ANN architectures for AI. In this work, we explore the advantages of a biologically inspired ANN architecture for quadruped locomotion based on neural circuits in the limbs and spinal cord of mammals. Our architecture achieves good initial performance and comparable final performance to MLPs, while using less data and orders of magnitude fewer parameters. Our architecture also exhibits better generalization to task variations, even admitting deployment on a physical robot without standard sim-to-real methods. This work shows that neural circuits can provide valuable architectural priors for locomotion and encourages future work in other sensorimotor skills. |
| title | Neural Circuit Architectural Priors for Quadruped Locomotion |
| topic | Neurons and Cognition Artificial Intelligence Machine Learning Neural and Evolutionary Computing Robotics |
| url | https://arxiv.org/abs/2410.07174 |