Published on March 16, 2016
1. Some observation on current state of robotics Albert Yefimov Russian Federation Skolkovo
2. Humans are better with weapons it is comparatively easy to make computers exhibit adult level performance on intelligence tests or playing checkers, and difficult or impossible to give them the skills of a one-year-old when it comes to perception and mobility Hans Moravec, 1988
3. Robot definition is very difficult Can you give definition of Robot? Robot is what an Expert call a Robot!
4. State of Machine Learning ”If intelligence was a cake, unsupervised learning would be the cake, supervised learning would be the icing on the cake, and reinforcement learning would be the cherry on the cake. We know how to make the icing and the cherry, but we don't know how to make the cake.”
5. Hardware for Artificial Brains Hypothetical ‘Full AI’ would need ~ 10 exaFLOPS, ~500 MW Cray Titan ~18 pFLOPS Tianhe-2 ~34 pFLOPS, ~25 MW Cray-2 (1985) iPhone 5 (2012) 2.7 times more powerful 27 years
6. Cambrian Moment of Modern Robotics
7. Enabling trends in Robotics • Moor’s Law • Digitalization of everything, including production • Better Battery • Huge communication bandwidth increase • Cloud robotics • 3 devices/human in 2019 • Storage is cheap commodity
8. Human Soldier vs Robot Soldier Human Robot Listening 16 -20 000 Hz 1 - unfinity Viewing 160 mlns of colors 150 MP Touching 13 nm Depends on materials If feels cold, hot or hunger unhappy Doesn’t care Emotions A lot of Not at all
9. Autonomy in military robotics
10. Drivers to full autonomy in military robotics • It is so easy to jam communications of tele/supervised robots or drones. Examples: DARPA Robotics Challenge Iran–U.S. RQ-170 incident
11. Drivers to full autonomy in military robotics • Dramatically increase firepower with fewer personnel
12. Autonomous systems •Sea •Ground •Air
13. Autonomous robots at Sea ACTUV Sea Hunter Autonomy: Mission level Duration: 20-120 h Speed: 1-2 M/s Connection: radio, hydroacoustic Deepth: 3-6km Range: 200-300 km Examples: Klavesin (Ru), Remus (US), Autosub (GB), Hugin (Nw) Remora Klavesin Sanpa • Level of Autonomy is very high • Range is limited • No weapons • Only reconnaissance missions Reliable communications are needed!
14. Autonomous ground vehicles Full Functionality Everywhere FunctionalityLimited Full SomewhereEverywhere Space
15. Unmanned Aerial Vehicles • Weight and power source is the biggest limiting factor • Hydrogen Cells are coming to market very soon
16. Robotics in Russia
17. ‘Therefore, the more technical the world becomes, the more necessary is the promotion of individual freedom and the individual's awareness of himself as a counterbalance.’ Albert Speer
Observation on state of robotics. Embedded from: http://www.slideshare.net/ Slides for presentation on International Committee of Red Cross on ...
Direkter Zugriff auf über 50.000 Fachbücher, 300 Fachzeitschriften, 1,2 Mio. Dokumente, Dossiers, Grafiken und Videos aus allen Fachgebieten:
State Representation Learning in Robotics: Using Prior Knowledge about Physical Interaction Rico Jonschkowski and Oliver Brock Robotics and Biology ...
ROBOTIC MANIPULATORS STATE OBSERVATION 315 Three main frameworks have been used for designing observers for various classes of nonlinear systems: a ...
On-line Cooperative Observation Based on ESMF in Three ... 4 Professor, State Key Laboratory of Robotics, Shenyang Institute of Automation, ...
ElSayed M. ElBeheiry Affiliated with Intelligent Manufacturing Systems (IMS) Centre, University of Windsor, Hoda A. ElMaraghy Affiliated with Intelligent ...
... State Representation Learning in Robotics: ... of this approach is that we have to define an observation-state-mapping for every robotic task to meet ...
An approach for motion control and observation of robotic manipulators is ... “State Observation of Nonlinear Uncertain Dynamical Systems ...
Robotics%drove%advances%in%artiﬁcial%intelligence:% planning,%learning,%reasoning,%vision,%natural%language ... continuous%state,%action,%observation%spaces%