Search papers, labs, and topics across Lattice.
This paper introduces MotorMind, a framework that directly connects general-purpose Vision-Language Models (VLMs) to robot control for zero-shot manipulation, bypassing the need for task-specific policies or external grounding tools. By providing a VLM with mid-level actions and an asynchronous feedback loop, MotorMind achieves significantly higher success rates on benchmark manipulation tasks and a real robot compared to prior zero-shot methods. The work demonstrates that VLM capabilities, particularly in visual grounding and embodied reasoning, are the primary drivers of performance in this direct manipulation paradigm.
General-purpose VLMs can achieve state-of-the-art zero-shot robot manipulation by directly interpreting observations and issuing actions, eliminating the need for specialized policies or grounding tools.
Vision-language-action (VLA) models have advanced robotic manipulation, but their zero-shot generalization in new tasks and environments remains limited, and their reliance on specialized training keeps them from benefiting directly from rapidly advancing general-purpose vision-language models (VLMs). In parallel, recent agentic robotic systems leverage VLMs for high-level reasoning or coding agents for robot control, but often depend on extensive external models and tools, introducing additional complexity and cost. This motivates us to ask: Can a general-purpose VLM itself operate a robot more like the human teleoperator by reasoning directly from observations, issuing actions, and continuously adapting to execution feedback, without relying on external models such as learned action experts, coding agents or grounding tools like SAM3? In this work, we introduce MotorMind, a robot manipulation harness that connects VLM-proposed mid-level actions to deterministic robot control and feedback, with asynchronous monitoring and background memory updates. Without task-specific policy training, coding agents, or additional grounding tools such as SAM3, MotorMind achieves 66.7% success on the base LIBERO-PRO suites and 53.8% under perturbations, compared with at most 13.3% and 19.2%, respectively, for the prior zero-shot methods we evaluate. The same interface reaches 95% average success on a real xArm6 robot across direct manipulation and human-perturbation settings. Replacing the backbone with a stronger VLM further improves performance, while the remaining failures - primarily due to visual grounding, embodied reasoning, and action knowledge - decrease as VLM capability improves. These results show that a general-purpose VLM, when equipped with an appropriate mid-level action representation and asynchronous execution harness, can perform effective zero-shot robotic manipulation.
