Make Your VLA More Robust Without More Data By Interleaving Motion Planning
2026-05-31 • Robotics
Robotics
AI summaryⓘ
The authors found that robots using vision, language, and action models struggle with long tasks because mistakes build up and it's hard to stay on track across many steps. They created a new system called MPVI that combines traditional motion planning with these models, helping robots better find and navigate to objects even in cluttered spaces without extra training. Their approach cleverly switches between different methods using the robot's own senses to check progress. Tests showed their method more than doubled the task success compared to previous models.
Vision-Language-Action (VLA) modelsmotion planningmobile manipulationlong-horizon tasksobject detectionfrontier explorationproprioceptionBEHAVIOR-1K benchmarkcompletion checking
Authors
Dan BW Choe, Sundhar Vinodh Sangeetha, Samuel Coogan, Shreyas Kousik
Abstract
Vision-Language-Action (VLA) models have shown remarkable progress for mobile manipulation, but their performance on long-horizon tasks remains poor. These tasks are especially challenging because (1) progress toward high-level goals must be maintained across extended sequences of spatially distributed subtasks, and (2) early execution errors compound rapidly over the task horizon. These challenges persist despite finetuning on large human teleoperated mobile manipulation data, indicating that more data alone may not resolve the problem. To address these challenges, we propose MPVI: Motion Planner / VLA Interleaving, a framework that integrates model-based motion planning with VLAs to improve robustness without further training. The proposed integration enables localization and navigation to distant or occluded target objects through cluttered scenes using open-vocabulary object detection, frontier exploration and motion planning. However, such integration is non-trivial, requiring reliable switching between modules; we show one way forward via VLM-based completion checking with proprioceptive triggers. We evaluate our approach on the BEHAVIOR-1K benchmark and demonstrate 113% improvement in task progress over a top end-to-end VLA baseline. Additional details are available at the project page: https://mpvi.netlify.app/.