CCDP: Model-free Failure Recovery via Guided Diffusion Sampling
| Type of publication: | Conference paper |
| Citation: | Razmjoo_TARO-WS-IROS_2025 |
| Publication status: | Accepted |
| Booktitle: | Workshop on The Art of Robustness: Surviving Failures in Robotics, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) |
| Year: | 2025 |
| Abstract: | Working in constrained environments means that failures are often inevitable, so robots must be able to recover from them. Typical recovery approaches require explicit models of the underlying task, either during learning or reproduction, to accommodate different possibilities and replan accordingly. However, such models are not always available, especially in imitation learning (IL), where one of the main advantages is precisely to avoid explicit environment/task modeling and rely instead on demonstration data. We present \textbf{CCDP (Composition of Conditional Diffusion Policies)}, a method that considers failures during inference and guides the sampling steps of diffusion policies to avoid previously failed actions. Remarkably, CCDP relies solely on successful demonstrations: it infers recovery actions without additional exploratory behavior or a high-level controller. We validate our approach on several tasks, including door opening with unknown directions, object manipulation, and button searching, and show that it consistently outperforms standard baselines. Supplementary material is available at: https://hri-eu.github.io/ccdp/. This paper is a condensed summary of our main publication at IROS 2025. |
| Additional Research Programs: |
Human-AI Teaming |
| Keywords: | |
| Projects: |
Idiap |
| Authors: | |
| Added by: | [UNK] |
| Total mark: | 0 |
|
Attachments
|
|
|
|
|
Notes
|
|
|
|
|
