Roberto Calandra
Facebook AI Research
Re-Work Deep Reinforcement Learning Summit - 21 June 2019
From YouTube: https://www.youtube.com/watch?v=g0TaYhjpOfo
From the lab of Dr. Ronald Johansson, Dept. of Physiology, University of Umea, Sweden
[Allen et al. 1999]
[Chebotar et al. 2016]
[Bekiroglu et al. 2011]
[Sommer and Billard 2016]
[Schill et al. 2012]
[Yuan, W.; Dong, S. & Adelson, E. H. GelSight: High-Resolution Robot Tactile Sensors for Estimating Geometry and Force Sensors, 2017]
Collected 6450 grasps from over 60 training objects over ~2 weeks.
83.8% grasp success on 22 unseen objects
(using only vision yields 56.6% success rate)
Tian, S.; Ebert, F.; Jayaraman, D.; Mudigonda, M.; Finn, C.; Calandra, R. & Levine, S.
Manipulation by Feel: Touch-Based Control with Deep Predictive Models
IEEE International Conference on Robotics and Automation (ICRA), 2019
Calandra, R.; Owens, A.; Jayaraman, D.; Yuan, W.; Lin, J.; Malik, J.; Adelson, E. H. & Levine, S.
More Than a Feeling: Learning to Grasp and Regrasp using Vision and Touch
IEEE Robotics and Automation Letters (RA-L), 2018, 3, 3300-3307
Andrew
Owens
Dinesh
Jayaraman
Wenzhen
Yuan
Justin
Lin
Jitendra
Malik
Sergey
Levine
Edward H.
Adelson
Vision:
Towards active feedback control from multi-modal sensing
Thank you for your attention
Tian, S.; Ebert, F.; Jayaraman, D.; Mudigonda, M.; Finn, C.; Calandra, R. & Levine, S.
Manipulation by Feel: Touch-Based Control with Deep Predictive Models
IEEE International Conference on Robotics and Automation (ICRA), 2019