Bi-HIL: Bilateral Control-Based Multimodal Hierarchical Imitation Learning via Subtask-Level Progress Rate and Keyframe Memory for Long-Horizon Contact-Rich Robotic Manipulation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Buamanee, Thanpimon, Kobayashi, Masato, Uranishi, Yuki
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910074964803584
author Buamanee, Thanpimon
Kobayashi, Masato
Uranishi, Yuki
author_facet Buamanee, Thanpimon
Kobayashi, Masato
Uranishi, Yuki
contents Long-horizon contact-rich robotic manipulation remains challenging due to partial observability and unstable subtask transitions under contact uncertainty. While hierarchical architectures improve temporal reasoning and bilateral imitation learning enables force-aware control, existing approaches often rely on flat policies that struggle with long-horizon coordination. We propose Bi-HIL, a bilateral control-based multimodal hierarchical imitation learning framework for long-horizon manipulation. Bi-HIL stabilizes hierarchical coordination by integrating keyframe memory with subtask-level progress rate that models phase progression within the active subtask and conditions both high- and low-level policies. We evaluate Bi-HIL on unimanual and bimanual real-robot tasks, demonstrating consistent improvements over flat and ablated variants. The results highlight the importance of explicitly modeling subtask progression together with force-aware control for robust long-horizon manipulation. For additional material, please check: https://mertcookimg.github.io/bi-hil
format Preprint
id arxiv_https___arxiv_org_abs_2603_13315
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Bi-HIL: Bilateral Control-Based Multimodal Hierarchical Imitation Learning via Subtask-Level Progress Rate and Keyframe Memory for Long-Horizon Contact-Rich Robotic Manipulation
Buamanee, Thanpimon
Kobayashi, Masato
Uranishi, Yuki
Robotics
Long-horizon contact-rich robotic manipulation remains challenging due to partial observability and unstable subtask transitions under contact uncertainty. While hierarchical architectures improve temporal reasoning and bilateral imitation learning enables force-aware control, existing approaches often rely on flat policies that struggle with long-horizon coordination. We propose Bi-HIL, a bilateral control-based multimodal hierarchical imitation learning framework for long-horizon manipulation. Bi-HIL stabilizes hierarchical coordination by integrating keyframe memory with subtask-level progress rate that models phase progression within the active subtask and conditions both high- and low-level policies. We evaluate Bi-HIL on unimanual and bimanual real-robot tasks, demonstrating consistent improvements over flat and ablated variants. The results highlight the importance of explicitly modeling subtask progression together with force-aware control for robust long-horizon manipulation. For additional material, please check: https://mertcookimg.github.io/bi-hil
title Bi-HIL: Bilateral Control-Based Multimodal Hierarchical Imitation Learning via Subtask-Level Progress Rate and Keyframe Memory for Long-Horizon Contact-Rich Robotic Manipulation
topic Robotics
url https://arxiv.org/abs/2603.13315