cs.ROOct 30, 2026

RTPolicy: Real-Time (32.9 Hz) Multi-View Visuomotor Policy for Robotic Manipulation on Edge Devices

Authors: Xianbao Hou, Zehao Ni, Yonghao He, Lingfeng Qian, Xin Shi, Hu Su, Wei Sui, Cong Yang

Organizations: School of Future Science and Engineering, Soochow University · D-Robotics · Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University · State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences

Abstract

Low inference latency is critical for closed-loop robotic manipulation, especially under asynchronous inference, where action chunks must be updated promptly to correct accumulated deviations. However, existing visuomotor policies rely on computationally expensive visual backbones, resulting in high inference latency and deployment overhead. In this paper, we propose RTPolicy, a multi-view visuomotor policy that attains accurate manipulation with high inference efficiency. Its core design combines view-aware feature fusion with visual compression to aggregate complementary information across camera views into a compact token representation. The representation conditions a flow-matching action generator with the robot state and flow time, reducing the cost of action generation. Extensive experiments demonstrate that this design reduces the computational cost of visual representation and action generation while preserving visual information required for manipulation. On the RoboTwin~2.0 single-task clean evaluation across 50 tasks, RTPolicy attains a mean success rate of 52.26%, outperforming the strongest leaderboard baseline π0π_0 (46.4%). We further evaluate RTPolicy under asynchronous streaming inference on a real bimanual platform, where RTPolicy attains a mean success rate of 72.0% and sustains real-time inference at 30.35 ms (32.9 Hz) on the RDK S600 and 149.72 ms (6.7 Hz) on the RDK S100, both in INT16. Project Page: https://d-robotics-ai-lab.github.io/RTPolicy.project.

Figures & tables

Explore similar work

CardsList
  1. ReactVLA: Fast and Lightweight Reactive Robot Manipulation via Improved Mean Flow Action Generation

    Jun 12, 2026Yanzhao Guo, Wenkai Chen, Jianwei ZhangLanguage-Conditioned Robot ManipulationEfficient VLM Inference

  2. Inference-time Policy Steering via Vision and Touch

    Jun 12, 2026Yilin Wu, Zilin Si, Zeynep Temel +2Robot Policy LearningRobot Policy Adaptation

  3. Control-Aware Command Generation for Asynchronous Control and Action Inference with Vision-Based Policies towards Fast Execution

    Nov 8, 2026Takayuki Osa, Kazuki OtaRobotic ControlVision-Based Robot Control