# Phase-Conditioned Imitation Learning with Autonomous Failure Recovery for Robust Deformable Object Manipulation

arXiv: https://arxiv.org/abs/2605.29407 · HTML: https://mlsanity.com/paper/2605.29407/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Robot manipulation imitation learning, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 17 of its 29 references that are in the map.
- First posted on arXiv 28 May 2026.

## Placed in

- Offline RL and imitation learning from data / [Robot manipulation imitation learning](https://mlsanity.com/offlinerl/robot-manipulation-imitation-learning/)

## Builds on (most cited first, 17 of 17)

- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023)
- [On the Continuity of Rotation Representations in Neural Networks](https://mlsanity.com/paper/1812.07035/) (2018)
- [The Ingredients for Robotic Diffusion Transformers](https://mlsanity.com/paper/2410.10088/) (2024)
- [Learning Visible Connectivity Dynamics for Cloth Smoothing](https://mlsanity.com/paper/2105.10389/) (2021)
- [RaC: Robot Learning for Long-Horizon Tasks by Scaling Recovery and Correction](https://mlsanity.com/paper/2509.07953/) (2025)
- [A System for Imitation Learning of Contact-Rich Bimanual Manipulation Policies](https://mlsanity.com/paper/2208.00596/) (2022)
- [DeformPAM: Data-Efficient Learning for Long-horizon Deformable Object Manipulation via Preference-based Action Alignment](https://mlsanity.com/paper/2410.11584/) (2024)
- [FILIC: Dual-Loop Force-Guided Imitation Learning with Impedance Torque Control for Contact-Rich Manipulation Tasks](https://mlsanity.com/paper/2509.17053/) (2025)
- [GraphGarment: Learning Garment Dynamics for Bimanual Cloth Manipulation Tasks](https://mlsanity.com/paper/2503.05817/) (2025)
- [Bimanual Deformable Bag Manipulation Using a Structure-of-Interest Based Neural Dynamics Model](https://mlsanity.com/paper/2401.11432/) (2024)
- [SIS: Seam-Informed Strategy for T-shirt Unfolding](https://mlsanity.com/paper/2409.06990/) (2024)
- [Learning Human-Inspired Force Strategies for Robotic Assembly](https://mlsanity.com/paper/2303.12440/) (2023)
- [FoldNet: Learning Generalizable Closed-Loop Policy for Garment Folding via Keypoint-Driven Asset and Demonstration Synthesis](https://mlsanity.com/paper/2505.09109/) (2025)
- [RTFF: Random-to-Target Fabric Flattening Policy using Dual-Arm Manipulator](https://mlsanity.com/paper/2510.00814/) (2025)

## Abstract (arXiv)

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: https://leledeyuan00.github.io/phaser/