Challenges in Robotic Dexterous Manipulation

Outline
00:00 - Intro
00:58 - Early steps… in physics!
05:17 - AI in Edinburgh
08:00 - Connectionism
10:37 - Robot learning
19:02 - Imitation learning
23:00 - On pursuing a PhD
24:45 - Californian chronicles
30:10 - Modularity
33:20 - Challenges in robot learning
39:44 - Dexterous manipulation
43:52 - Dynamical systems
47:37 - Combining ML and control
51:25 - Human-robot interaction
54:24 - Safety and compliance
57:54 - Deadlines for papers
1:06:38 - Advice to future students
1:07:08 - Outro

Links
Aude’s lab: http://tinyurl.com/4nsx2kra
Robot learning: http://tinyurl.com/2ty25t2r
Connectionism: http://tinyurl.com/mrd76zfx
I. Demiris: http://tinyurl.com/nhhn6ymu
Hebbian learning: http://tinyurl.com/35ey7um5
DRAMA (paper): http://tinyurl.com/4fvbs867
Imitation learning: http://tinyurl.com/2af3aew4
Mirror neurons: http://tinyurl.com/4nd3sm75
G. Rizzolatti: http://tinyurl.com/5b4xfab5
Embodied cognition: http://tinyurl.com/5284kp8f
A biologically inspired robotic model for learning by imitation: http://tinyurl.com/4j33nphv
M. Airbib: http://tinyurl.com/3bu3y5dz
Recent Advances in Robot Learning from Demonstration: http://tinyurl.com/487pm3xk
Synthetic brain imaging (paper): http://tinyurl.com/38uerwk7
Catching Objects in Flight (paper): http://tinyurl.com/38d8fk9m
Feasibility not optimality (video): http://tinyurl.com/mwa8b7et
Learning multiple-attractors (paper): http://tinyurl.com/2j3yxwm8
On human compliance (paper): http://tinyurl.com/4vp2kmhw
Deadlines for conferences: http://tinyurl.com/mpwntkty

Support the show

Podcast info
Podcast website: https://www.incontrolpodcast.com/
Apple Podcasts: https://tinyurl.com/5n84j85j
Spotify: https://tinyurl.com/4rwztj3c
RSS: https://tinyurl.com/yc2fcv4y
Youtube: https://tinyurl.com/bdbvhsj6
Facebook: https://tinyurl.com/3z24yr43
Twitter: https://twitter.com/IncontrolP
Instagram: https://tinyurl.com/35cu4kr4

Acknowledgments and sponsors
This episode was supported by the National Centre of Competence in Research on «Dependable, ubiquitous automation» and the IFAC Activity fund. The podcast benefits from the help of an incredibly talented and passionate team. Special thanks to L. Seward, E. Cahard, F. Banis, F. Dörfler, J. Lygeros, ETH studio and mirrorlake . Music was composed by A New Element.