Design and Evaluation of an Uncertainty-Aware Shared-Autonomy System with Hierarchical Conservative Skill Inference
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909650580930560 |
|---|---|
| author | Kim, Taewoo Kim, Donghyung Jang, Minsu Kim, Jaehong |
| author_facet | Kim, Taewoo Kim, Donghyung Jang, Minsu Kim, Jaehong |
| contents | Shared-autonomy imitation learning lets a human correct a robot in real time, mitigating covariate-shift errors. Yet existing approaches ignore two critical factors: (i) the operator's cognitive load and (ii) the risk created by delayed or erroneous interventions. We present an uncertainty-aware shared-autonomy system in which the robot modulates its behaviour according to a learned estimate of latent-space skill uncertainty. A hierarchical policy first infers a conservative skill embedding and then decodes it into low-level actions, enabling rapid task execution while automatically slowing down when uncertainty is high. We detail a full, open-source VR-teleoperation pipeline that is compatible with multi-configuration manipulators such as UR-series arms. Experiments on pouring and pick-and-place tasks demonstrate 70-90% success in dynamic scenes with moving targets, and a qualitative study shows a marked reduction in collision events compared with a non-conservative baseline. Although a dedicated ablation that isolates uncertainty is impractical on hardware for safety and cost reasons, the reported gains in stability and operator workload already validate the design and motivate future large-scale studies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_02488 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Design and Evaluation of an Uncertainty-Aware Shared-Autonomy System with Hierarchical Conservative Skill Inference Kim, Taewoo Kim, Donghyung Jang, Minsu Kim, Jaehong Robotics Shared-autonomy imitation learning lets a human correct a robot in real time, mitigating covariate-shift errors. Yet existing approaches ignore two critical factors: (i) the operator's cognitive load and (ii) the risk created by delayed or erroneous interventions. We present an uncertainty-aware shared-autonomy system in which the robot modulates its behaviour according to a learned estimate of latent-space skill uncertainty. A hierarchical policy first infers a conservative skill embedding and then decodes it into low-level actions, enabling rapid task execution while automatically slowing down when uncertainty is high. We detail a full, open-source VR-teleoperation pipeline that is compatible with multi-configuration manipulators such as UR-series arms. Experiments on pouring and pick-and-place tasks demonstrate 70-90% success in dynamic scenes with moving targets, and a qualitative study shows a marked reduction in collision events compared with a non-conservative baseline. Although a dedicated ablation that isolates uncertainty is impractical on hardware for safety and cost reasons, the reported gains in stability and operator workload already validate the design and motivate future large-scale studies. |
| title | Design and Evaluation of an Uncertainty-Aware Shared-Autonomy System with Hierarchical Conservative Skill Inference |
| topic | Robotics |
| url | https://arxiv.org/abs/2312.02488 |