2. The Robotic Manipulation Data Engine

The Robotic Manipulation Data Engine

Robot Manipulation Arena
Alberto Rodriguez

The goal of this project is to develop the technologies for a robot manipulator to perform autonomous object exploration of previously unseen objects and to iteratively adapt/refine/verify its own perception and manipulation skills. In particular, we want to demonstrate that the following are possible and practical:

  1. Unsupervised and safe exploration of a novel object.
  2. Automatic data collection, experiment labeling, and feature/parameter extraction.
  3. Iterative improvement and verification of manipulation skills for novel objects.

We want to study the processes of on-line data collection and skill testing. In some cases, a robot will have good priors from similar objects previously explored, and will need to verify them. In other cases, a robot will have to gather new data and update its manipulation behaviors.

[January-1-2018 to current]

 

Publications:

  1. S. Dong, S. Wang, Y. She, N. Sunil, A. Rodriguez, and E. Adelson, “Cable Manipulation with a Tactile-Reactive Gripper,” in Robotics: Science and Systems XVI, 2020, doi: 10.15607/RSS.2020.XVI.029 [Online]. Available: https://doi.org/10.15607/RSS.2020.XVI.029
  2. A. Kloss, M. Bauza, J. Wu, J. B. Tenenbaum, A. Rodriguez, and J. Bohg, “Accurate Vision-based Manipulation through Contact Reasoning,” in 2020 IEEE International Conference on Robotics and Automation (ICRA), Paris, France, 2020, pp. 6738–6744, doi: 10.1109/ICRA40945.2020.9197409 [Online]. Available: https://doi.org/10.1109/ICRA40945.2020.9197409
  3. F. Hogan, J. Ballester, S. Dong, and A. Rodriguez, “Tactile Dexterity: Manipulation Primitives with Tactile Feedback,” in 2020 IEEE International Conference on Robotics and Automation (ICRA), 2020, doi: 10.1109/ICRA40945.2020.9196976 [Online]. Available: https://doi.org/10.1109/ICRA40945.2020.9196976
  4. A. Ajay, J. Wu, N. Fazeli, M. Bauza, L. P. Kaelbling, J. B. Tenenbaum, and A. Rodriguez, “Augmenting Physical Simulators with Stochastic Neural Networks: Case Study of Planar Pushing and Bouncing,” in 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Madrid, 2018, pp. 3066–3073, doi: 10.1109/IROS.2018.8593995 [Online]. Available: https://doi.org/10.1109/IROS.2018.8593995
  5. S. Dong and A. Rodriguez, “Tactile-Based Insertion for Dense Box-Packing,” in 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Macau, China, 2019, pp. 7953–7960, doi: 10.1109/IROS40897.2019.8968204 [Online]. Available: https://doi.org/10.1109/IROS40897.2019.8968204
  6. S. Dong, D. Ma, E. Donlon, and A. Rodriguez, “Maintaining Grasps within Slipping Bounds by Monitoring Incipient Slip,” in 2019 International Conference on Robotics and Automation (ICRA), Montreal, QC, Canada, 2019, pp. 3818–3824 [Online]. Available: https://doi.org/10.1109/ICRA.2019.8793538. [Accessed: 09-Sep-2019]
  7. M. Bauza, O. Canal, and A. Rodriguez, “Tactile Mapping and Localization from High-Resolution Tactile Imprints,” in 2019 International Conference on Robotics and Automation (ICRA), Montreal, QC, Canada, 2019, pp. 3811–3817 [Online]. Available: https://doi.org/10.1109/ICRA.2019.8794298. [Accessed: 09-Sep-2019]
  8. E. Donlon, S. Dong, M. Liu, J. Li, E. Adelson, and A. Rodriguez, “GelSlim: A High-Resolution, Compact, Robust, and Calibrated Tactile-sensing Finger,” in IROS 2018, 2018 [Online]. Available: https://doi.org/10.1109/IROS.2018.8593661