# Moving On, Even When You're Broken: Fail-Active Trajectory Generation via Diffusion Policies Conditioned on Embodiment and Task

arXiv: https://arxiv.org/abs/2602.02895 · HTML: https://mlsanity.com/paper/2602.02895/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 31 references that are in the map.
- First posted on arXiv 2 Feb 2026.

## Builds on (most cited first, 13 of 13)

- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [RePaint: Inpainting using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2201.09865/) (2022)
- [NoMaD: Goal Masked Diffusion Policies for Navigation and Exploration](https://mlsanity.com/paper/2310.07896/) (2023)
- [Robots that can adapt like animals](https://mlsanity.com/paper/1407.3501/) (2014)
- [The Ingredients for Robotic Diffusion Transformers](https://mlsanity.com/paper/2410.10088/) (2024)
- [EDMP: Ensemble-of-costs-guided Diffusion for Motion Planning](https://mlsanity.com/paper/2309.11414/) (2023)
- [DiMSam: Diffusion Models as Samplers for Task and Motion Planning under Partial Observability](https://mlsanity.com/paper/2306.13196/) (2023)
- [Online Damage Recovery for Physical Robots with Hierarchical Quality-Diversity](https://mlsanity.com/paper/2210.09918/) (2022)
- [Fault-Aware Robust Control via Adversarial Reinforcement Learning](https://mlsanity.com/paper/2011.08728/) (2020)
- [Reinforcement Learning with Adaptive Curriculum Dynamics Randomization for Fault-Tolerant Robot Control](https://mlsanity.com/paper/2111.10005/) (2021)
- [Learning Quadrupedal Locomotion with Impaired Joints Using Random Joint Masking](https://mlsanity.com/paper/2403.00398/) (2024)
- [Adaptive Compensation for Robotic Joint Failures Using Partially Observable Reinforcement Learning](https://mlsanity.com/paper/2409.14435/) (2024)
- [Exploring How Non-Prehensile Manipulation Expands Capability in Robots Experiencing Multi-Joint Failure](https://mlsanity.com/paper/2410.01102/) (2024)

## Built on by (most cited first, 2 of 2)

- [Uncovering Vulnerability of Vision-Language-Action Models under Joint-Level Physical Faults](https://mlsanity.com/paper/2606.10501/) (2026)
- [CAPABLE: Capability-Aware Policy Adaptation via Behavioral Latent Encoding](https://mlsanity.com/paper/2610.11971/) (2026)

## Abstract (arXiv)

Robot failure is detrimental and disruptive, often requiring human intervention to recover. Our vision is 'fail-active' operation, allowing robots to safely complete their tasks even when damaged. Focusing on 'actuation failures', we introduce DEFT, a diffusion-based trajectory generator conditioned on the robot's current embodiment and task constraints. DEFT generalizes across failure types, supports constrained and unconstrained motions, and enables task completion under arbitrary failure. We evaluate DEFT in both simulation and real-world scenarios using a 7-DoF robotic arm. DEFT outperforms its baselines over thousands of failure conditions, achieving a 99.5% success rate for unconstrained motions versus RRT's 42.4%, and 46.4% for constrained motions versus differential IK's 30.9%. Furthermore, DEFT demonstrates robust zero-shot generalization by maintaining performance on failure conditions unseen during training. Finally, we perform real-world evaluations on two multi-step tasks, drawer manipulation and whiteboard erasing. These experiments demonstrate DEFT succeeding on tasks where classical methods fail. Our results show that DEFT achieves fail-active manipulation across arbitrary failure configurations and real-world deployments.