Skill-Aware Diffusion for Generalizable Robotic Manipulation

arXiv:2601.11266 · cs.RO · Submitted 2026-01-16 · Read on arXiv

cs.RO

Submitted: 2026-01-16

Updated: 2026-10-11

Comments: Published in IEEE Transactions on Automation Science and Engineering (T-ASE), 2026

Journal ref: IEEE Transactions on Automation Science and Engineering, vol. 23, pp. 17635-17650, 2026

DOI: 10.1109/TASE.2026.3740160

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Generalization — 4× in this paper · explained in 13 episodes
• Diffusion Model — 1× in this paper · explained in 10 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Sim-to-Real Transfer — 1× in this paper · explained in 2 episodes

Sources

• Bridging Language and Action: A Survey of Language-Conditioned Robot Manipulation
• Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware
• Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation
• EC-Flow: Enabling Versatile Robotic Manipulation from Action-Unlabeled Videos via Embodiment-Centric Flow
• Discovering Generalizable Skills via Automated Generation of Diverse Tasks
• Isaac Lab: A GPU-Accelerated Simulation Framework for Multi-Modal Robot Learning
• Robotic Manipulation via Imitation Learning: Taxonomy, Evolution, Benchmark, and Challenges
• What Matters in Learning from Offline Human Demonstrations for Robot Manipulation
• Perceiver IO: A General Architecture for Structured Inputs & Outputs
• Masked Visual Pre-training for Motor Control
• Any-point Trajectory Modeling for Policy Learning
• Generative Artificial Intelligence in Robotic Manipulation: A Survey
• Imitating Human Behaviour with Diffusion Models
• TesserAct: Learning 4D Embodied World Models
• Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
• AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning
• General Flow as Foundation Affordance for Scalable Robot Learning

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• ARC: A Reasoning Recipe for Robot Foundation Models
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies