Skip to main content Skip to main navigation

Publikation

Ark: An Open-source Python-based Framework for Robot Learning

Magnus Dierking; Christopher E. Mower; Sarthak Das; Helong Huang; Jiacheng Qiu; Cody Reading; Wei Chen; Huidong Liang; Guowei Huang; Xingyue Quan; Jun Wang; Haitham Bou-Ammar; Jan Peters
In: Computing Research Repository eprint Journal (CoRR), Vol. abs/2506.21628, Pages 1-29, arXiv, 2025.

Zusammenfassung

Robotics has made remarkable hardware strides-from DARPA’s Urban and Robotics Challenges to the first humanoid-robot kickboxing tournament-yet com- mercial autonomy still lags behind progress in machine learning. A major bot- tleneck is software: current robot stacks demand steep learning curves, low-level C/C++ expertise, fragmented tooling, and intricate hardware integration, in stark contrast to the Python-centric, well-documented ecosystems that propelled mod- ern AI. We introduce Ark, an open-source, Python-first robotics framework de- signed to close that gap. Ark presents a Gym-style environment interface that al- lows users to collect data, preprocess it, and train policies using state-of-the-art imitation-learning algorithms (e.g., ACT, Diffusion Policy) while seamlessly toggling between high-fidelity simulation and physical robots. A lightweight client–server architecture provides networked publisher-subscriber communication, and op- tional C/C++ bindings ensure real-time performance when needed. Ark ships with reusable modules for control, SLAM, motion planning, system identification, and visualization, along with native ROS interoperability. Comprehensive documenta- tion and case studies-from manipulation to mobile navigation-demonstrate rapid prototyping, effortless hardware swapping, and end-to-end pipelines that rival the convenience of mainstream machine-learning workflows. By unifying robotics and AI practices under a common Python umbrella, Ark lowers entry barriers and accel- erates research and commercial deployment of autonomous robots.

Weitere Links