RoboBrain 2.0 Technical Report

TL;DR

RoboBrain 2.0 is a new embodied vision-language foundation model that unifies perception, reasoning, and planning, achieving state-of-the-art results in complex real-world embodied AI tasks with two scalable variants.

Contribution

It introduces RoboBrain 2.0 with a heterogeneous architecture, multi-stage training, and practical applications, advancing embodied AI capabilities and providing open-source resources.

Findings

32B model surpasses prior models on benchmarks

Supports key embodied AI tasks like spatial understanding and temporal decision-making

Achieves strong performance with a compact 7B variant

Abstract

We introduce RoboBrain 2.0, our latest generation of embodied vision-language foundation models, designed to unify perception, reasoning, and planning for complex embodied tasks in physical environments. It comes in two variants: a lightweight 7B model and a full-scale 32B model, featuring a heterogeneous architecture with a vision encoder and a language model. Despite its compact size, RoboBrain 2.0 achieves strong performance across a wide spectrum of embodied reasoning tasks. On both spatial and temporal benchmarks, the 32B variant achieves leading results, surpassing prior open-source and proprietary models. In particular, it supports key real-world embodied AI capabilities, including spatial understanding (e.g., affordance prediction, spatial referring, trajectory forecasting) and temporal decision-making (e.g., closed-loop interaction, multi-agent long-horizon planning, and scene graph updating). This report details the model architecture, data construction, multi-stage training strategies, infrastructure and practical applications. We hope RoboBrain 2.0 advances embodied AI research and serves as a practical step toward building generalist embodied agents. The code, checkpoint and benchmark are available at https://superrobobrain.github.io.