Corpus ID: 159041553

REPLAB: A Reproducible Low-Cost Arm Benchmark Platform for Robotic Learning

@article{Yang2019REPLABAR,
  title={REPLAB: A Reproducible Low-Cost Arm Benchmark Platform for Robotic Learning},
  author={Brian Yang and Jesse M. Zhang and Vitchyr H. Pong and Sergey Levine and Dinesh Jayaraman},
  journal={ArXiv},
  year={2019},
  volume={abs/1905.07447}
}
  • Brian Yang, Jesse M. Zhang, +2 authors Dinesh Jayaraman
  • Published 2019
  • Engineering, Computer Science
  • ArXiv
  • Standardized evaluation measures have aided in the progress of machine learning approaches in disciplines such as computer vision and machine translation. In this paper, we make the case that robotic learning would also benefit from benchmarking, and present the "REPLAB" platform for benchmarking vision-based manipulation tasks. REPLAB is a reproducible and self-contained hardware stack (robot arm, camera, and workspace) that costs about 2000 USD, occupies a cuboid of size 70x40x60 cm, and… CONTINUE READING

    Citations

    Publications citing this paper.
    SHOWING 1-8 OF 8 CITATIONS

    ROBEL: Robotics Benchmarks for Learning with Low-Cost Robots

    Rigid-Soft Interactive Learning for Robust Grasping

    PyRobot: An Open-source Robotics Framework for Research and Benchmarking

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Morphology-Agnostic Visual Robotic Control

    VIEW 1 EXCERPT
    CITES METHODS

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 37 REFERENCES

    Deep learning for detecting robotic grasps

    VIEW 1 EXCERPT

    Supersizing self-supervision: Learning to grasp from 50K tries and 700 robot hours

    • Lerrel Pinto, Abhinav Gupta
    • Mathematics, Computer Science
    • 2016 IEEE International Conference on Robotics and Automation (ICRA)
    • 2016
    VIEW 3 EXCERPTS

    The ACRV picking benchmark: A robotic shelf picking benchmark to foster reproducible research

    VIEW 2 EXCERPTS

    The OpenGRASP benchmarking suite: An environment for the comparative analysis of grasping and dexterous manipulation

    VIEW 1 EXCERPT

    End-to-End Training of Deep Visuomotor Policies

    VIEW 1 EXCERPT