Unified Condition-Action Modeling for Accurate One-Step Action Generation
2026-08-17 • Robotics
Robotics
AI summaryⓘ
The authors propose a new method called UCA-Flow to improve robot control by better combining what the robot sees (conditions) and what it does (actions) into a single, shared representation. This helps the robot quickly and accurately decide its next move by dynamically focusing on the most important information. Their approach uses a specialized transformer model and a training technique to learn this joint representation effectively. Compared to previous methods, UCA-Flow not only makes robots more successful at tasks but also speeds up decision-making significantly.
robot manipulationdiffusion policiesflow policiestransformer modelscondition-action modelingone-step action generationtoken representationdual-pass supervisioninference speedpolicy optimization
Authors
Xinyu Zhou, Zikun Cai, Kuangji Zuo, Gen Li, Boyu Ma, Yanshuo Lu, Yutong Song, Mingqi Yuan, Jiayu Chen, Jianfei Yang
Abstract
Robot manipulation requires policies that are both accurate and efficient, as robot control must respond to changing observations under tight latency constraints. Recent diffusion and flow policies are promising, but they often treat conditions as auxiliary signals rather than jointly evolving them with action trajectories. We find that this limitation can be effectively mitigated by a \textbf{simple yet effective unified condition-action modeling design} that represents conditions and actions in a shared token space, allowing a compact model to achieve high performance while improving both inference speed and accuracy. Therefore, we propose UCA-Flow, a unified condition-action modeling framework for accurate one-step action generation. Our method unifies observation conditions, timestep conditions, interval conditions, and action tokens into a single sequence, and processes them with a Unified Condition-Action Transformer for joint condition-action representation learning. As a result, condition representations are dynamically reconstructed according to the current generation stage, highlighting information most relevant for action refinement. Furthermore, we introduce an improved dual-pass supervision scheme over $u$ and $v$ for stronger optimization of unified condition-action modeling. UCA-Flow improves the average success rate by 9.3 percentage points over the strongest baseline, while achieving $45.6\times$ and $33.4\times$ speedups over DP3 and Simple DP3, and remaining $4.3\times$ and $2.3\times$ faster than one-step FlowPolicy and MP1, respectively.