SOURCE-LINKED INTELLIGENCE

Self-Adaptive VLA for Robust Robot Deployment

arXiv · AI, language, vision and robotics · article · Sep 24, 2026 · UTC

While Vision-Language-Action (VLA) models demonstrate impressive capabilities in robotic manipulation, their memoryless nature renders them brittle to test-time environment shifts, particularly hardware shifts caused by wear or imperfect calibration. Enabling these models to self-adapt during deployment without requiring continuous on-site recalibration remains a critical bottleneck for real-world scalability. In this work, we introduce Self-Adaptive VLA, a novel post-training recipe that enables the policy to iteratively adapt to deployment-time hardware shifts leveraging its own rollouts as

Read original source ↗ Open in workspace

recordType

paper

region

Global