MolmoSpaces: A Large-Scale Open Ecosystem for Robot Navigation and Manipulation
Yejin Kim, Wilbert Pumacay, Omar Rayyan, Max Argus, Winson Han, Eli VanderBilt, Jordi Salvador, Abhay Deshpande, Rose Hendrix, Snehal Jauhri, Shuo Liu, Nur Muhammad Mahi Shafiullah, Maya Guru, Ainaz Eftekhar, Karen Farley, Donovan Clay, Jiafei Duan, Arjun Guru, Piper Wolters

TL;DR
MolmoSpaces is an extensive open ecosystem with over 230,000 diverse indoor environments and rich annotations, designed to facilitate large-scale benchmarking and development of robust robot navigation and manipulation policies.
Contribution
It introduces MolmoSpaces, a large-scale, simulator-agnostic ecosystem with diverse environments and a benchmark suite supporting various embodied tasks for robot learning research.
Findings
Strong sim-to-real correlation (R=0.96) and high reproducibility (ρ=0.98).
Newer policies outperform earlier versions in benchmarks.
Identifies sensitivities to prompt phrasing, initial joint positions, and occlusion.
Abstract
Deploying robots at scale demands robustness to the long tail of everyday situations. The countless variations in scene layout, object geometry, and task specifications that characterize real environments are vast and underrepresented in existing robot benchmarks. Measuring this level of generalization requires infrastructure at a scale and diversity that physical evaluation alone cannot provide. We introduce MolmoSpaces, a fully open ecosystem to support large-scale benchmarking of robot policies. MolmoSpaces consists of over 230k diverse indoor environments, ranging from handcrafted household scenes to procedurally generated multiroom houses, populated with 130k richly annotated object assets, including 48k manipulable objects with 42M stable grasps. Crucially, these environments are simulator-agnostic, supporting popular options such as MuJoCo, Isaac, and ManiSkill. The ecosystem…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsRobot Manipulation and Learning · Social Robot Interaction and HRI · Reinforcement Learning in Robotics
