AI & ML
On the Utility of Pre-Trained Visual Representations for Policy Learning of Contact-Rich Insertion Tasks
arXiv cs.RO0 views
arXiv:2611.17631v1 Announce Type: new Abstract: Visuomotor imitation learning has become a predominant paradigm for real-world robotic manipulation, yet it remains data-inefficient and brittle to task-irrelevant visual shifts. Pre-trained visual representations promise to ease this burden by distilling priors from internet-scale data, but the ``right'' representation for robotics remains unresolved: existing studies span broad but sparse task distributions and reach conclusions that vary and even conflict, pointing to strong task and setting dependence. We examine this question by bringing a magnifying glass to a common contact-rich manipulation task: insertion. We compare representations from widely used vision foundation models against an explicit contact-centric representation on two closely related insertion tasks, perturb each along controlled axes of occlusion and physical tolerance, and test whether conclusions transfer to the real world. Task dependence proves to be more subtle than previous, broadly scoped evaluations revealed: the best representation differs even between our near-identical tasks, and small changes shift trends in unpredictable ways. Despite this variability, results across simulation and real-world experiments demonstrate the distinct value of spatially-grounded, and in particular, contact-centric information for contact-rich policy learning, while underscoring how difficult it is to estimate such cues reliably under realistic visual complexity and sensor noise. We hope these findings motivate further study of representations in contact-rich manipulation, along with advances in contact perception and its integration into visuomotor policy learning.
Source:https://arxiv.org/abs/2611.17631PreviousTouchTwin: Scaling Human Touch Data via Real-to-Sim-to-RealNextAI-guided robotic in situ fabrication of curvature- and tissue-adaptive wireless bioelectronics
Related posts
AttentionSwitch: Jailbreak Defense for LLMs via Joint Learning of Sparse Attention-Head Selection and Scaling
0arXiv cs.CR
Denoising the US Census: Succinct Block Hierarchical Regression
0arXiv cs.CR
Adversarial Attacks on Downstream Weather Forecasting Models: Application to Tropical Cyclone Trajectory Prediction
0arXiv cs.CR
Cyber-Zero: Training Cybersecurity Agents without Runtime
0arXiv cs.CR
Coordinate Frame Recovery, Per Class NMS and Null Return Modelling for Sim2Real V2X LiDAR Detection
0arXiv cs.RO
Geometric Refinement and Distributional Alignment for Sim2Real Roadside LiDAR Detection
0arXiv cs.RO