Sensing flow gradients is necessary for learning autonomous underwater navigation
Abstract Aquatic animals are much better at underwater navigation than robotic vehicles. Robots face major challenges in deep water because of their limited access to global positioning signals and flow maps. These limitations, and the changing nature of water currents, support the use of reinforcem...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-03-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-025-58125-6 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850064038345572352 |
|---|---|
| author | Yusheng Jiao Haotian Hang Josh Merel Eva Kanso |
| author_facet | Yusheng Jiao Haotian Hang Josh Merel Eva Kanso |
| author_sort | Yusheng Jiao |
| collection | DOAJ |
| description | Abstract Aquatic animals are much better at underwater navigation than robotic vehicles. Robots face major challenges in deep water because of their limited access to global positioning signals and flow maps. These limitations, and the changing nature of water currents, support the use of reinforcement learning approaches, where the navigator learns through trial-and-error interactions with the flow environment. But is it feasible to learn underwater navigation in the agent’s Umwelt, without any land references? Here, we tasked an artificial swimmer with learning to reach a specific destination in unsteady flows by relying solely on egocentric observations, collected through on-board flow sensors in the agent’s body frame, with no reference to a geocentric inertial frame. We found that while sensing local flow velocities is sufficient for geocentric navigation, successful egocentric navigation requires additional information of local flow gradients. Importantly, egocentric navigation strategies obey rotational symmetry and are more robust in unfamiliar conditions and flows not experienced during training. Our work expands underwater robot-centric learning, helps explain why aquatic organisms have arrays of flow sensors that detect gradients, and provides physics-based guidelines for transfer learning of learned policies to unfamiliar and diverse flow environments. |
| format | Article |
| id | doaj-art-192ac2301a2b49c1835ed2380e56edee |
| institution | DOAJ |
| issn | 2041-1723 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj-art-192ac2301a2b49c1835ed2380e56edee2025-08-20T02:49:25ZengNature PortfolioNature Communications2041-17232025-03-0116111510.1038/s41467-025-58125-6Sensing flow gradients is necessary for learning autonomous underwater navigationYusheng Jiao0Haotian Hang1Josh Merel2Eva Kanso3Department of Aerospace and Mechanical Engineering, University of Southern CaliforniaDepartment of Aerospace and Mechanical Engineering, University of Southern CaliforniaFauna RoboticsDepartment of Aerospace and Mechanical Engineering, University of Southern CaliforniaAbstract Aquatic animals are much better at underwater navigation than robotic vehicles. Robots face major challenges in deep water because of their limited access to global positioning signals and flow maps. These limitations, and the changing nature of water currents, support the use of reinforcement learning approaches, where the navigator learns through trial-and-error interactions with the flow environment. But is it feasible to learn underwater navigation in the agent’s Umwelt, without any land references? Here, we tasked an artificial swimmer with learning to reach a specific destination in unsteady flows by relying solely on egocentric observations, collected through on-board flow sensors in the agent’s body frame, with no reference to a geocentric inertial frame. We found that while sensing local flow velocities is sufficient for geocentric navigation, successful egocentric navigation requires additional information of local flow gradients. Importantly, egocentric navigation strategies obey rotational symmetry and are more robust in unfamiliar conditions and flows not experienced during training. Our work expands underwater robot-centric learning, helps explain why aquatic organisms have arrays of flow sensors that detect gradients, and provides physics-based guidelines for transfer learning of learned policies to unfamiliar and diverse flow environments.https://doi.org/10.1038/s41467-025-58125-6 |
| spellingShingle | Yusheng Jiao Haotian Hang Josh Merel Eva Kanso Sensing flow gradients is necessary for learning autonomous underwater navigation Nature Communications |
| title | Sensing flow gradients is necessary for learning autonomous underwater navigation |
| title_full | Sensing flow gradients is necessary for learning autonomous underwater navigation |
| title_fullStr | Sensing flow gradients is necessary for learning autonomous underwater navigation |
| title_full_unstemmed | Sensing flow gradients is necessary for learning autonomous underwater navigation |
| title_short | Sensing flow gradients is necessary for learning autonomous underwater navigation |
| title_sort | sensing flow gradients is necessary for learning autonomous underwater navigation |
| url | https://doi.org/10.1038/s41467-025-58125-6 |
| work_keys_str_mv | AT yushengjiao sensingflowgradientsisnecessaryforlearningautonomousunderwaternavigation AT haotianhang sensingflowgradientsisnecessaryforlearningautonomousunderwaternavigation AT joshmerel sensingflowgradientsisnecessaryforlearningautonomousunderwaternavigation AT evakanso sensingflowgradientsisnecessaryforlearningautonomousunderwaternavigation |