Scalable, Training-Free Visual Language Robotics: A Modular Multi-Model Framework for Consumer-Grade GPUs

TL;DR

This paper presents SVLR, a scalable, modular, training-free framework for vision-language robotic control that integrates lightweight open-source models to enable flexible, real-time task execution on consumer-grade GPUs.

Contribution

Introduces SVLR, a novel open-source framework that allows scalable, retraining-free robotic control using modular AI models for visual and language understanding.

Findings

Operates effectively on NVIDIA RTX 2070 GPU

Successfully performs pick-and-place tasks

Supports easy integration of new tasks without retraining

Abstract

The integration of language instructions with robotic control, particularly through Vision Language Action (VLA) models, has shown significant potential. However, these systems are often hindered by high computational costs, the need for extensive retraining, and limited scalability, making them less accessible for widespread use. In this paper, we introduce SVLR (Scalable Visual Language Robotics), an open-source, modular framework that operates without the need for retraining, providing a scalable solution for robotic control. SVLR leverages a combination of lightweight, open-source AI models including the Vision-Language Model (VLM) Mini-InternVL, zero-shot image segmentation model CLIPSeg, Large Language Model Phi-3, and sentence similarity model all-MiniLM to process visual and language inputs. These models work together to identify objects in an unknown environment, use them as parameters for task execution, and generate a sequence of actions in response to natural language instructions. A key strength of SVLR is its scalability. The framework allows for easy integration of new robotic tasks and robots by simply adding text descriptions and task definitions, without the need for retraining. This modularity ensures that SVLR can continuously adapt to the latest advancements in AI technologies and support a wide range of robots and tasks. SVLR operates effectively on an NVIDIA RTX 2070 (mobile) GPU, demonstrating promising performance in executing pick-and-place tasks. While these initial results are encouraging, further evaluation across a broader set of tasks and comparisons with existing VLA models are needed to assess SVLR's generalization capabilities and performance in more complex scenarios.