UniCon: A Unified System for Efficient Robot Learning Transfers

2026-01-21

AI Summary

Deploying learning-based controllers across heterogeneous robotic platforms is often hindered by platform-specific differences, inconsistent interfaces, and inefficient middleware. To address these challenges, this work proposes UniCon, a lightweight unified framework that standardizes state representations, control flows, and instrumentation interfaces. By decoupling control logic into reusable execution graph components and adopting a modular, data-oriented architecture, UniCon replaces conventional middleware with batched, vectorized data streams. This design significantly reduces communication overhead and enhances inference efficiency, enabling seamless sim-to-real transfer. UniCon has been successfully deployed on 12 distinct robots from seven manufacturers, substantially reducing code redundancy compared to ROS and demonstrating practical utility in multiple real-world research projects.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Planning, Routing, and Scheduling: Learning for Planning and Scheduling
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• robot learning transfer
• heterogeneous robots
• middleware inefficiency
• sim-to-real transfer
• platform differences

Innovation

• Unified Robot Learning
• Execution Graph
• Vectorized Data Flow
• Sim-to-Real Transfer
• Plug-and-Play Deployment