Xiaomi-Robotics-0: An Open-Sourced Vision-Language-Action Model with Real-Time Execution

TL;DR

Xiaomi-Robotics-0 is a novel vision-language-action model designed for real-time robotic control, achieving state-of-the-art results in simulation and real-world tasks through optimized training and deployment strategies.

Contribution

The paper introduces Xiaomi-Robotics-0, a new VLA model with a unique training recipe and deployment techniques for real-time execution on robots, maintaining broad capabilities without forgetting pre-trained knowledge.

Findings

Achieves state-of-the-art performance in simulation benchmarks.

Runs smoothly and efficiently on real robots with consumer-grade GPUs.

Demonstrates high success rates and throughput in real-robot tasks.

Abstract

In this report, we introduce Xiaomi-Robotics-0, an advanced vision-language-action (VLA) model optimized for high performance and fast and smooth real-time execution. The key to our method lies in a carefully designed training recipe and deployment strategy. Xiaomi-Robotics-0 is first pre-trained on large-scale cross-embodiment robot trajectories and vision-language data, endowing it with broad and generalizable action-generation capabilities while avoiding catastrophic forgetting of the visual-semantic knowledge of the underlying pre-trained VLM. During post-training, we propose several techniques for training the VLA model for asynchronous execution to address the inference latency during real-robot rollouts. During deployment, we carefully align the timesteps of consecutive predicted action chunks to ensure continuous and seamless real-time rollouts. We evaluate Xiaomi-Robotics-0 extensively in simulation benchmarks and on two challenging real-robot tasks that require precise and dexterous bimanual manipulation. Results show that our method achieves state-of-the-art performance across all simulation benchmarks. Moreover, Xiaomi-Robotics-0 can roll out fast and smoothly on real robots using a consumer-grade GPU, achieving high success rates and throughput on both real-robot tasks. To facilitate future research, code and model checkpoints are open-sourced at https://xiaomi-robotics-0.github.io