 |
 |
|
Existing applicants/evaluators log in here
|
|
Cooperability
| Project leader |
Kragic Danica |
| Project co-leader: |
Prof. Bojan Jerbic |
| Administering organization: |
Faculty of Mechanical Engineering and Naval ArchitectureDepartment of Robotics and Production System AutomationIvana Lučića 5, 10000 Zagreb, Croatia |
| Partner Institution/Company: |
Royal Institute of Technology (KTH) |
| Grant type: |
1B |
| Project title: |
Improving GRAsping Movements by predictions based on Observation |
| Project summary: |
For the future, we want to build robots that can in and easy and flexible way learn how to solve tasks in unknown environments. Traditional automation approaches are cost ineffective, inflexible and unreliable, because the world is dynamic and unpredictable. However, inexperienced, ordinary users cannot use these classical approaches. Recent scientific achievements in cognitive science and robotics enable modeling of different, nondeterministic approaches to automation of production systems. It is expected from such approaches to provide adaptability and high level of intelligence and autonomy enabling the machines to work in unstructured environment, learn and improve and cooperate with other agents including humans. The adaptability and autonomy imply hardware and software evolvable reconfigurability bringing up an issue of a higher level of system control and wider abstraction aspects at the autonomous learning level. In humans, learning involves changes in behavior that arise from interaction with the environment. The principles and the inspiration for this project are adopted from the human psychology and physiology. This project concentrates on grasping and manipulation of known and new objects that is currently recognized as one of the most important open problems in the field of robotics. How to provide suitable models and develop flexible and safe systems is a topic of several ongoing EU projects (CoSy, PACO-PLUS, GRASP, DexSmart, CogX). Grasping is motor skill based on perception, interaction with environment and neural/control machinery. Although much of our motor repertoire is acquired during our lifetime, we do not start life as tabula rasa. Evolutionary processes drive an innate pattern of behavior to hardwire motor skills into the brain before birth and support subsequent learning. Motor learning is a consequence of the co-adaptation of the neural machinery and structural anatomy. In the project, we will use human movement data to derive the „innate“ motor primitives and used these to build complex robot-hand movements. Here we will explore the need for motor learning, what is learned, how it is represented, and the mechanisms of learning. The perception system will interpret the environment and the objects, mapping the knowledge about the world with the set of primitive motor behaviors the agent can initially execute and from which all the more complex behaviors derive. The evaluation of the proposed methodology will be evaluated both on actual physical systems and in simulation. |
| Hrvatski sažetak: |
Jedan od vaznih ciljeva za buducnost je dizajn i izgradnja robota i
autonomnih sistema koji, na lak i fleksibilan nacin, mogu rijesavati
teske probleme u razlicitim okolinama. Klasicna automatska postrojenja i
autonomni sustavi ne mogu se prilagoditi okolini koja je dinamicna i
gdje se dogadjaju neocekivane aktivnosti. Nadalje, korisnici ovakvih
sistema moraju biti tehnicki obuceni. Moderni istrazivacki rad u uvom
podrucju bazira se na razvoju kognitivnih sistema i njihovoj
adaptaciji u industrijskim postrojenjima. Ocekuje se da ce ti sistemi
imati bitnu ulogu za buducnost robotike s namjerom da novi sistemi
imaju mogucnost inteligentnog kontakta s ljudima i mogucnost ucenja
tijekom kontakta.
Adaptacija i autonmni rad zahtjevaju bitne novosti u rijesenju na
podrucju software-a i hardware-a specijalno sto se tice strane
masinskog ucenja. Ucenje je kod ljudi urodjeno i u ovom projektu sluzi
kao inspiracija izgradnji inteligentnih sistema. Iz tog razloga,
istrazivacki se rad djelimicno temelji na istrazivanjima iz
psihologije i fiziologije temeljito na podrucju manipulacije
objekata. Manipulacija objekata sa strane robota je bitan i trenutno nerijesen
problem u podrucju robotike. Na evropskoj razini danas postoji mnogo
velikig projekata koji se bave problemom manipulacije: CoSy, PACO-PLUS,
GRASP, DexSmart, CogX. Svaki od ovih projekata raspolaze financijskim
sredstvima od minimalno 6 milijuna EUR-a. Manipulacija objekata ovisi
o senzorima, kontaktu s okolinom i nacinu kontrole robotskog sistema.
Kod ljudi, manipulacija objekata je djelimicno urodjena i bazira se na
evoluciji.
Cilj ovog projekta je dizajn i razvoj sistema za manipulaciju objekata
i robotims gdje se ucenje bazira na imitaciji ljudske manipulacije
objekata. Drugim rijecima, roboti ce uciti kako manipulirati
objekte na slican nacin kao i djeca - gledajuci odrasle i imitirajuci
ih. Ovaj projekt istraziti ce sto je bitno u samom modeliranju procesa
za masinsko ucenje i kako se ono sto je reprezentirano moze
implementirati na razlicim robotickim sistemima cija je kinematika
razlicita od ljudske.
|
| Amount requested from UKF: |
458.934 HRK |
| Amount of matching funding: |
300.200 HRK |
|
|
|
