Proximal State Nudging: Reducing Skill Atrophy from AI Assistance
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917514119741440 |
|---|---|
| author | Srivastava, Megha Ouyang, Jonathan Zhou, Eric Silva, Andrew Sumner, Emily Sadigh, Dorsa Cui, Yuchen Gopinath, Deepak Rosman, Guy |
| author_facet | Srivastava, Megha Ouyang, Jonathan Zhou, Eric Silva, Andrew Sumner, Emily Sadigh, Dorsa Cui, Yuchen Gopinath, Deepak Rosman, Guy |
| contents | Skill atrophy, the gradual decline of human capability under AI assistance, poses a safety risk in shared-control of semi-autonomous systems, where operators may be unable to distinguish their own inputs from autonomous corrections. We propose Proximal State Nudging (PSN), a shared autonomy algorithm that jointly optimizes for skill development and task performance by nudging users toward states estimated to be most learnable. We first show that PSN outperforms existing shared autonomy baselines in balancing student improvement in unassisted reward with overall shared performance, using simulated students in the classic LunarLander environment. We then present, to the best of our knowledge, the first human subject studies of a planner incorporating learning-compatible shared autonomy: across two driving tasks in the CARLA simulator (High Performance Racing and Parallel Parking, n = 60), PSN produces up to 7x larger gains in unassisted skill than standard blended shared autonomy, while incurring 50% fewer collisions than unassisted self-practice. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_20355 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Proximal State Nudging: Reducing Skill Atrophy from AI Assistance Srivastava, Megha Ouyang, Jonathan Zhou, Eric Silva, Andrew Sumner, Emily Sadigh, Dorsa Cui, Yuchen Gopinath, Deepak Rosman, Guy Robotics Human-Computer Interaction Machine Learning Skill atrophy, the gradual decline of human capability under AI assistance, poses a safety risk in shared-control of semi-autonomous systems, where operators may be unable to distinguish their own inputs from autonomous corrections. We propose Proximal State Nudging (PSN), a shared autonomy algorithm that jointly optimizes for skill development and task performance by nudging users toward states estimated to be most learnable. We first show that PSN outperforms existing shared autonomy baselines in balancing student improvement in unassisted reward with overall shared performance, using simulated students in the classic LunarLander environment. We then present, to the best of our knowledge, the first human subject studies of a planner incorporating learning-compatible shared autonomy: across two driving tasks in the CARLA simulator (High Performance Racing and Parallel Parking, n = 60), PSN produces up to 7x larger gains in unassisted skill than standard blended shared autonomy, while incurring 50% fewer collisions than unassisted self-practice. |
| title | Proximal State Nudging: Reducing Skill Atrophy from AI Assistance |
| topic | Robotics Human-Computer Interaction Machine Learning |
| url | https://arxiv.org/abs/2605.20355 |