AI & ML
VG-Steer: Visual-Geometric Policy Steering from In-Context Aligned Abstractions
arXiv cs.RO0 views
arXiv:2611.25199v1 Announce Type: new Abstract: Adapting robot policies to out-of-distribution (OOD) settings with limited real-world data remains a key bottleneck to generalist robots. The multimodality and scarcity of robotics data lead end-to-end approaches to overfit and break under small distribution shifts. Test-time adaptation can alleviate this by correcting frozen policies at inference, but most methods ground their correction in a signal learned implicitly from robotic datasets, making it susceptible to the same shifts as the policy it corrects. Recent methods that instead exploit explicit spatial information are typically limited to coarse corrections, missing the nuanced, task-relevant motion most manipulation tasks require. We propose VG-Steer, which corrects existing policies by transferring the nuanced motion of successful in-distribution rollouts, captured along meaningful geometric axes, known here as object-relational distance pairs. VG-Steer leverages the semantic understanding of Large Vision Models (LVMs) and Vision-Language Models (VLMs) reasoning, which combines the task-relevant entity pairs and their object-relational distance projections into a single tailored visual-geometric guidance signal. In a simulation benchmark, it efficiently corrects flow-matching policies under pose and task-goal shifts; on a real robot experiment, it widens the region of the workspace the frozen policy covers, more than doubling its success rate on cable placements one grid step outside the training positions, and steers a single-task policy toward objects it was never trained on while nearly eliminating object confusion. Project website: https://arthurfenderbucker.github.io/VG-Steer/
Source:https://arxiv.org/abs/2611.25199PreviousFrom Self-Play RL to Constrained Control: Distilling DiffMPC Students with DAggerNextBridging vision-language reasoning and learned control for legged navigation in the wild
Related posts
One red light, four stalls
0dev.to
Testing Political Alignment in Chinese AI Models: What Developers Need to Know
0dev.to
LLM Inference Optimization Interview Questions and Answers
0dev.to
How to Close a Deal That Keeps Stalling: A Mutual Action Plan Template and Closing Techniques for Founder-Led Sales
0dev.to

Roast My Dev Desktop: Zero Minimalism, Maximum Chaos
0dev.to
랩트 모네로 붕괴: 익숙한 신뢰 배신 이야기
0dev.to