Judo: A User-Friendly Open-Source Package for Sampling-Based Model Predictive Control

2025-06-20

AI Summary

The robotics community lacks a general-purpose toolkit supporting rapid prototyping, benchmarking, and hardware deployment of sampling-based Model Predictive Control (MPC). Method: We introduce the first open-source Python toolkit for sampling-based MPC, featuring asynchronous execution, an interactive GUI for real-time parameter tuning, standardized task interfaces, and seamless simulation-to-hardware transfer. Built on a modular architecture, it integrates the MuJoCo physics engine and supports user-defined controllers, tasks, and parallel sampling strategies. Contribution/Results: The toolkit achieves millisecond-level real-time control on both consumer-grade and server-class hardware. It is fully open-sourced, accompanied by a comprehensive suite of benchmark tasks and an extensible API. This significantly improves development efficiency and engineering deployability of sampling-based MPC methods, enabling broader adoption and systematic evaluation across diverse robotic platforms.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Intelligent Robots: Motion and Path Planning
• Planning, Routing, and Scheduling: Model-Based Reasoning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Recent advancements in parallel simulation and successful robotic applications are spurring a resurgence in sampling-based model predictive control. To build on this progress, however, the robotics community needs common tooling for prototyping, evaluating, and deploying sampling-based controllers. We introduce Judo, a software package designed to address this need. To facilitate rapid prototyping and evaluation, Judo provides robust implementations of common sampling-based MPC algorithms and standardized benchmark tasks. It further emphasizes usability with simple but extensible interfaces for controller and task definitions, asynchronous execution for straightforward simulation-to-hardware transfer, and a highly customizable interactive GUI for tuning controllers interactively. While written in Python, the software leverages MuJoCo as its physics backend to achieve real-time performance, which we validate across both consumer and server-grade hardware. Code at https://github.com/bdaiinstitute/judo.

Problem

• Lack of common tools for sampling-based MPC prototyping
• Need for standardized benchmark tasks in robotics
• Challenges in simulation-to-hardware controller transfer

Innovation

• Robust sampling-based MPC algorithms
• Simple extensible controller interfaces
• Real-time Python with MuJoCo backend