Phase-Conditioned Imitation Learning with Autonomous Failure Recovery for Robust Deformable Object Manipulation
This paper presents a phase-conditioned, force-aware framework for robust deformable object manipulation. Using FiLM-conditioned ACT encoder and multi-modal phase predictor, the system autonomously detects and recovers from contact failures, improving T-shirt hanging success rate from 56% to 87%.
Article intelligence
Key points
- Standard imitation learning (e.g., ACT) suffers from state aliasing due to Markovian assumption, preventing autonomous failure recovery.
- The proposed framework uses FiLM-conditioned encoder to enable phase-specific behaviors in a single policy.
- A multi-modal phase predictor fuses visual, force, and pose feedback to detect contact failures and trigger recovery.
- Validated on dual-arm T-shirt hanging and removal, success rate increased from 56% to 87%.
Why it matters
This matters because standard imitation learning (e.g., ACT) suffers from state aliasing due to Markovian assumption, preventing autonomous failure recovery.
Technical impact
May affect model selection, inference cost, product capability, and evaluation benchmarks.
[2605.29407] Phase-Conditioned Imitation Learning with Autonomous Failure Recovery for Robust Deformable Object Manipulation
[Submitted on 28 May 2026]
Title:Phase-Conditioned Imitation Learning with Autonomous Failure Recovery for Robust Deformable Object Manipulation
View a PDF of the paper titled Phase-Conditioned Imitation Learning with Autonomous Failure Recovery for Robust Deformable Object Manipulation, by Dayuan Chen and 4 other authors
View PDF HTML (experimental)
Abstract:This paper presents a phase-conditioned, force-aware framework for robust deformable object manipulation. Standard imitation learning policies such as Action Chunking with Transformers (ACT) rely on a Markovian assumption at inference, causing state aliasing when visually similar observations require contradictory actions and preventing autonomous recovery from execution failures. We address this with a closed-loop hierarchical architecture. A FiLM-conditioned ACT encoder modulates feature extraction based on the current task phase, enabling a single unified policy to produce phase-specific behaviors while sharing action dynamics across phases. A multi-modal phase predictor fusing visual, force, and pose feedback estimates the phase in real time, detecting contact failures that are invisible to vision alone and autonomously triggering recovery trajectories. The system is completed by a hybrid impedance controller for compliant execution and a haptic teleoperation interface for force-aware data collection. Ablation studies show that FiLM-based modulation significantly outperforms both unconditioned and token-level conditioned baselines, and t-SNE analysis confirms that FiLM induces well-separated, phase-specific feature representations. Validated on hanging and removing a T-shirt with dual arms, the closed-loop system improves the hanging success rate from 56\% to 87\% through autonomous error recovery. Code and videos: this https URL
Comments: Accepted to IEEE/ASME Transactions on Mechatronics
Subjects:
Robotics (cs.RO)
Cite as: arXiv:2605.29407 [cs.RO]
(or arXiv:2605.29407v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2605.29407
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Kai Tang [view email] [v1] Thu, 28 May 2026 05:59:53 UTC (14,374 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Phase-Conditioned Imitation Learning with Autonomous Failure Recovery for Robust Deformable Object Manipulation, by Dayuan Chen and 4 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.RO
new | recent | 2026-05
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
Data provided by:
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)