DisDP: Robust Imitation Learning via Disentangled Diffusion Policies
Lists
Only you see this
Abstract
This work introduces Disentangled Diffusion Policy(DisDP), an Imitation Learning (IL) method that enhances robustness. Robot policies have to be robust against different perturbations, including sensor noise, complete sensor dropout, and environmental variations. Existing IL methods struggle to generalize under such conditions, as they typically assume consistent, noise-free inputs. To address this limitation, DisDP structures sensors into shared and private representations, pre-serving global features while retaining details from individual sensors. Additionally, Disentangled Behavior Cloning (DisBC) is introduced, a disentangled Behavior Cloning (BC) policy, to demonstrate the general applicance of disentanglement for IL. This structured representation improves resilience against sensor dropouts and perturbations. Evaluations on The Colosseum and Libero benchmarks demonstrate that disentangled policies achieve better performance in general and exhibit greater robustness to perturbations compared to their baseline policies.
BibTeX
@inproceedings{vanjani2025disdp,
author = {Pankhuri Vanjani and Paul Mattes and Kevin Daniel Kuryshev and Xiaogang Jia and Vedant Dave and Rudolf Lioutikov},
title = {{DisDP: Robust Imitation Learning via Disentangled Diffusion Policies}},
booktitle = {ReliableRobotics @ RSS},
year = {2025},
url = {https://openreview.net/forum?id=yOJDPb9zwT},
}Loading related content...