MAT: Multi-Fingered Adaptive Tactile Grasping via Deep Reinforcement Learning
@inproceedings{Wu2019MATMA, title={MAT: Multi-Fingered Adaptive Tactile Grasping via Deep Reinforcement Learning}, author={B. Wu and Iretiayo Akinola and J. Varley and P. Allen}, booktitle={CoRL}, year={2019} }
Vision-based grasping systems typically adopt an open-loop execution of a planned grasp. This policy can fail due to many reasons, including ubiquitous calibration error. Recovery from a failed grasp is further complicated by visual occlusion, as the hand is usually occluding the vision sensor as it attempts another open-loop regrasp. This work presents MAT, a tactile closed-loop method capable of realizing grasps provided by a coarse initial positioning of the hand above an object. Our… CONTINUE READING
Figures, Tables, and Topics from this paper
12 Citations
Generative Attention Learning: a "GenerAL" framework for high-performance multi-fingered grasping in clutter
- Computer Science
- Auton. Robots
- 2020
- 3
- PDF
Deep Reinforcement Learning for Tactile Robotics: Learning to Type on a Braille Keyboard
- Computer Science
- IEEE Robotics and Automation Letters
- 2020
- 1
- PDF
Blind Bin Picking of Small Screws Through In-finger Manipulation With Compliant Robotic Fingers
- Computer Science
- 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
- 2020
Improved Learning of Robot Manipulation Tasks via Tactile Intrinsic Motivation
- Computer Science
- ArXiv
- 2021
- 1
- PDF
Review of Deep Reinforcement Learning-Based Object Grasping: Techniques, Open Challenges, and Recommendations
- Computer Science
- IEEE Access
- 2020
- 1
- PDF
Learning the sense of touch in simulation: a sim-to-real strategy for vision-based tactile sensing
- Computer Science
- 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
- 2020
- 9
- PDF
Reactive grasping using high-resolution tactile sensors
- Computer Science
- 2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)
- 2020
References
SHOWING 1-10 OF 45 REFERENCES
QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation
- Computer Science, Mathematics
- CoRL
- 2018
- 375
- Highly Influential
- PDF
Pixel-Attentive Policy Gradient for Multi-Fingered Grasping in Cluttered Scenes
- Computer Science
- 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
- 2019
- 8
- PDF
Leveraging Contact Forces for Learning to Grasp
- Computer Science
- 2019 International Conference on Robotics and Automation (ICRA)
- 2019
- 12
- PDF
More Than a Feeling: Learning to Grasp and Regrasp Using Vision and Touch
- Computer Science, Engineering
- IEEE Robotics and Automation Letters
- 2018
- 89
- PDF
Closing the Loop for Robotic Grasping: A Real-time, Generative Grasp Synthesis Approach
- Computer Science, Engineering
- Robotics: Science and Systems
- 2018
- 144
- PDF
Planning Multi-Fingered Grasps as Probabilistic Inference in a Learned Deep Network
- Computer Science
- ISRR
- 2017
- 39
- PDF
Learning of grasp adaptation through experience and tactile sensing
- Engineering, Computer Science
- 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems
- 2014
- 88
- PDF
Learning a visuomotor controller for real world robotic grasping using easily simulated depth images
- Computer Science
- ArXiv
- 2017
- 39
Tactile Regrasp: Grasp Adjustments via Simulated Tactile Transformations
- Computer Science, Engineering
- 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
- 2018
- 42
- PDF