Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

UniCon: A Unified System for Efficient Robot Learning Transfers

Yunfeng Lin, Li Xu, Yong Yu, Jiangmiao Pang, Weinan Zhang

TL;DR

UniCon tackles the challenge of deploying learning‑based robot controllers across heterogeneous platforms by introducing a lightweight, data‑oriented framework that standardizes states, control flow, and instrumentation. It decomposes workflows into execution graphs comprised of reusable Control Blocks, separating system states from policy logic to enable plug‑and‑play deployment across morphologies and simulators. The paper demonstrates three key contributions: a unified control framework that bridges simulators and hardware, a modular design that facilitates sim‑to‑real transfer with minimal re‑engineering, and improved inference efficiency compared with ROS‑based stacks. Empirically, UniCon reduces transfer effort, delivers lower latency, and supports real‑world deployments across 12 robot models from 7 manufacturers, highlighting its practical impact for scalable cross‑platform robot learning research.

Abstract

Deploying learning-based controllers across heterogeneous robots is challenging due to platform differences, inconsistent interfaces, and inefficient middleware. To address these issues, we present UniCon, a lightweight framework that standardizes states, control flow, and instrumentation across platforms. It decomposes workflows into execution graphs with reusable components, separating system states from control logic to enable plug-and-play deployment across various robot morphologies. Unlike traditional middleware, it prioritizes efficiency through batched, vectorized data flow, minimizing communication overhead and improving inference latency. This modular, data-oriented approach enables seamless sim-to-real transfer with minimal re-engineering. We demonstrate that UniCon reduces code redundancy when transferring workflows and achieves higher inference efficiency compared to ROS-based systems. Deployed on over 12 robot models from 7 manufacturers, it has been successfully integrated into ongoing research projects, proving its effectiveness in real-world scenarios.

UniCon: A Unified System for Efficient Robot Learning Transfers

TL;DR

UniCon tackles the challenge of deploying learning‑based robot controllers across heterogeneous platforms by introducing a lightweight, data‑oriented framework that standardizes states, control flow, and instrumentation. It decomposes workflows into execution graphs comprised of reusable Control Blocks, separating system states from policy logic to enable plug‑and‑play deployment across morphologies and simulators. The paper demonstrates three key contributions: a unified control framework that bridges simulators and hardware, a modular design that facilitates sim‑to‑real transfer with minimal re‑engineering, and improved inference efficiency compared with ROS‑based stacks. Empirically, UniCon reduces transfer effort, delivers lower latency, and supports real‑world deployments across 12 robot models from 7 manufacturers, highlighting its practical impact for scalable cross‑platform robot learning research.

Abstract

Deploying learning-based controllers across heterogeneous robots is challenging due to platform differences, inconsistent interfaces, and inefficient middleware. To address these issues, we present UniCon, a lightweight framework that standardizes states, control flow, and instrumentation across platforms. It decomposes workflows into execution graphs with reusable components, separating system states from control logic to enable plug-and-play deployment across various robot morphologies. Unlike traditional middleware, it prioritizes efficiency through batched, vectorized data flow, minimizing communication overhead and improving inference latency. This modular, data-oriented approach enables seamless sim-to-real transfer with minimal re-engineering. We demonstrate that UniCon reduces code redundancy when transferring workflows and achieves higher inference efficiency compared to ROS-based systems. Deployed on over 12 robot models from 7 manufacturers, it has been successfully integrated into ongoing research projects, proving its effectiveness in real-world scenarios.
Paper Structure (15 sections, 4 equations, 3 figures, 3 tables)

This paper contains 15 sections, 4 equations, 3 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Framework
  3. Vectorized States
  4. Modularized Logic
  5. Software Interoperability
  6. Programming Interface
  7. Workflow Transfers
  8. Evaluation
  9. Transfer Effort
  10. Framework Efficiency
  11. Workflow Usability
  12. Related Work
  13. Learning-based Robot Controllers
  14. Robot Application Middleware
  15. Conclusion

Figures (3)

  • Figure 1: Representative use cases of UniCon: Left: synchronized and reusable locomotion across heterogeneous robots. Middle: Modular interoperation of RL policies with VR teleoperation. Right: Real‑to‑sim data recording and analysis for diagnosing transfer gaps. Data and control flow are standardized across platforms, reducing integration effort and improving efficiency.
  • Figure 2: Architecture of UniCon: (a) global system states with switchable storage backends; (b) modular control blocks covering platform and inference; (c) control flow graph primitives for workflow composition; and (d) unified integration with simulators and hardware.
  • Figure 3: Real-to-sim analysis of inference trajectories. Left & Middle: Reality gap quantified per joint position using built-in metrics, showing deviations in the A1's rear left calf joint. Right: Stable Go2 standing (top) and A1 just before fallover (bottom).