EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

FMB: A functional manipulation benchmark for generalizable robotic learning

Jianlan Luo, Charles Xu, Fangchen Liu, Liam Tan, Zipeng Lin, Jeffrey Wu, Pieter Abbeel, Sergey Levine

The International Journal of Robotics Research · 2025-04 · 44 (4) · 592-606

DOI: 10.1177/02783649241276017 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The International Journal of Robotics Research, online erschienen am 22.09.2024. Verfasst von Jianlan Luo und 7 weiteren Autor:innen. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Intrinsic Innovation LLC, The AI Institute, Division of Information and Intelligent Systems.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In this paper, we propose a real-world benchmark for studying robotic learning in the context of functional manipulation: a robot needs to accomplish complex long-horizon behaviors by composing individual manipulation skills in functionally relevant ways. The core design principles of our Functional Manipulation Benchmark (FMB) emphasize a harmonious balance between complexity and accessibility. Tasks are deliberately scoped to be narrow, ensuring that models and datasets of manageable scale can be utilized effectively to track progress. Simultaneously, they are diverse enough to pose a significant generalization challenge. Furthermore, the benchmark is designed to be easily replicable, encompassing all essential hardware and software components. To achieve this goal, FMB consists of a variety of 3D-printed objects designed for easy and accurate replication by other researchers. The objects are procedurally generated, providing a principled framework to study generalization in a controlled fashion. We focus on fundamental manipulation skills, including grasping, repositioning, and a range of assembly behaviors. The FMB can be used to evaluate methods for acquiring individual skills, as well as methods for effectively combining and ordering such skills in order to solve complex, multi-stage manipulation tasks. We also offer an imitation learning framework that includes a suite of policies trained to solve the proposed tasks. This enables researchers to utilize our tasks as a versatile toolkit for examining various parts of the pipeline. For example, researchers could propose a better design for a grasping controller and evaluate it in combination with our baseline reorientation and assembly policies as part of a pipeline for solving multi-stage tasks. Our dataset, object CAD files, code, and evaluation videos can be found on our project website: https://functional-manipulation-benchmark.github.io .

Förderung

  • Intrinsic Innovation LLC
  • The AI Institute
  • Division of Information and Intelligent Systems
  • Office of Naval Research

Zitieren

APA

Luo, J., Xu, C., Liu, F., Tan, L., Lin, Z., Wu, J., Abbeel, P., & Levine, S. (2025). FMB: A functional manipulation benchmark for generalizable robotic learning. The International Journal of Robotics Research, 44(4), 592-606. https://doi.org/10.1177/02783649241276017

Vancouver

Luo J, Xu C, Liu F, Tan L, Lin Z, Wu J, et al. FMB: A functional manipulation benchmark for generalizable robotic learning. The International Journal of Robotics Research. 2025;44(4):592-606. doi:10.1177/02783649241276017

BibTeX
@article{Luo2025,
  author = {Luo, Jianlan and Xu, Charles and Liu, Fangchen and Tan, Liam and Lin, Zipeng and Wu, Jeffrey and Abbeel, Pieter and Levine, Sergey},
  title = {FMB: A functional manipulation benchmark for generalizable robotic learning},
  journal = {The International Journal of Robotics Research},
  year = {2025},
  volume = {44},
  number = {4},
  pages = {592--606},
  doi = {10.1177/02783649241276017}
}
Kostenlos starten →