cs.RONov 18, 2026

VG-Steer: Visual-Geometric Policy Steering from In-Context Aligned Abstractions

Authors: Arthur Bucker, Pramod Anantharam, Jonathan Francis, Jean Oh

Organizations: Robotics Institute, Carnegie Mellon University, Pittsburgh, PA 15213, USA · Robot Learning Lab, Bosch Center for Artificial Intelligence, Pittsburgh, PA 15222, USA · Lavoro AI, Inc., Pittsburgh, PA 15232, USA

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/

Figures & tables

Appendix figures & tables6 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Retrieve to Act: Motion Primitive Graph Retrieval for Robust VLA Execution

    Oct 27, 2026Pham Tri Quang, Bao-Ngoc Dao, Minh Duc Nguyen +15Robustness of VLAsTest-Time Adaptation of VLAs

  2. Proxy Policy Steering

    Sep 8, 2026Chuanruo Ning, Tianrui Wang, Wei-Chiu Ma +1Robot Policy AdaptationRobot Foundation Models

  3. Inference-time Policy Steering via Vision and Touch

    Jun 12, 2026Yilin Wu, Zilin Si, Zeynep Temel +2Robot Policy LearningRobot Policy Adaptation