RLDX-1 Technical Report

TL;DR

RLDX-1 is a versatile robotic policy that integrates multiple modalities to outperform recent vision-language-action models in complex real-world manipulation tasks, including humanoid control.

Contribution

The paper introduces RLDX-1, a novel multi-stream transformer architecture with system-level optimizations for dexterous manipulation, surpassing existing models in simulation and real-world tests.

Findings

RLDX-1 achieves 86.8% success in ALLEX humanoid tasks.

It outperforms recent models like π_{0.5} and GR00T N1.6 in benchmarks.

RLDX-1 demonstrates reliable control of high-DoF humanoid robots.

Abstract

While Vision-Language-Action models (VLAs) have shown remarkable progress toward human-like generalist robotic policies through the versatile intelligence (i.e. broad scene understanding and language-conditioned generalization) inherited from pre-trained Vision-Language Models, they still struggle with complex real-world tasks requiring broader functional capabilities (e.g. motion awareness, long-term memory, and physical sensing). To address this, we introduce RLDX-1, a general-purpose robotic policy for dexterous manipulation built on the Multi-Stream Action Transformer (MSAT), an architecture that unifies these capabilities by integrating heterogeneous modalities through modality-specific streams with cross-modal joint self-attention. RLDX-1 further combines this architecture with system-level design choices, including data synthesis for rare manipulation scenarios, learning procedures specialized for human-like manipulation, and inference optimizations for real-time deployment. Through empirical evaluation, we show that RLDX-1 consistently outperforms recent frontier VLAs (e.g. $\pi_{0.5}$ and GR00T N1.6) across both simulation benchmarks and real-world tasks that require broad functional capabilities beyond general versatility. In particular, RLDX-1 shows superiority in ALLEX humanoid tasks by achieving success rates of 86.8% while $\pi_{0.5}$ and GR00T N1.6 achieve around 40%, highlighting the ability of RLDX-1 to control a high-DoF humanoid robot under diverse functional demands. Together, these results position RLDX-1 as a promising step toward reliable VLAs for complex, contact-rich, and dynamic real-world dexterous manipulation.