iFlyBot-VLM Technical Report

TL;DR

iFlyBot-VLM is a versatile vision-language model designed to enhance embodied intelligence in robots by bridging perception and action through a transferable operational language, enabling diverse robotic tasks and coordination.

Contribution

The paper introduces iFlyBot-VLM, a novel general-purpose VLM that abstracts complex visual data into a transferable language for improved embodied AI capabilities.

Findings

Achieved optimal performance on multiple embodied intelligence benchmarks.

Demonstrated scalable and generalizable capabilities across robotic platforms.

Enabled seamless perception-action coordination in diverse tasks.

Abstract

We introduce iFlyBot-VLM, a general-purpose Vision-Language Model (VLM) used to improve the domain of Embodied Intelligence. The central objective of iFlyBot-VLM is to bridge the cross-modal semantic gap between high-dimensional environmental perception and low-level robotic motion control. To this end, the model abstracts complex visual and spatial information into a body-agnostic and transferable Operational Language, thereby enabling seamless perception-action closed-loop coordination across diverse robotic platforms. The architecture of iFlyBot-VLM is systematically designed to realize four key functional capabilities essential for embodied intelligence: 1) Spatial Understanding and Metric Reasoning; 2) Interactive Target Grounding; 3) Action Abstraction and Control Parameter Generation; 4) Task Planning and Skill Sequencing. We envision iFlyBot-VLM as a scalable and generalizable foundation model for embodied AI, facilitating the progression from specialized task-oriented systems toward generalist, cognitively capable agents. We conducted evaluations on 10 current mainstream embodied intelligence-related VLM benchmark datasets, such as Blink and Where2Place, and achieved optimal performance while preserving the model's general capabilities. We will publicly release both the training data and model weights to foster further research and development in the field of Embodied Intelligence.