Project description DEENESFRITPL Validating an autonomous robot skill learning system With robotics technologies advancing fast, numerous sectors are embracing these new devices. One of these is the industrial sector that benefits from industrial robots which have been built to automatically repeat several tasks thousands of times. What about programming robots to perform one complex motor task? Unfortunately, this is challenging and remains time-consuming and expensive. The EU-funded AssemblySkills project aims to overcome this challenge by validating an autonomous skill learning system that would allow industrial robots to obtain a multitude of motor skills at lower cost and in less time. Show the project objective Hide the project objective Objective Present-day industrial robots are made for the purpose of repeating several tasks thousands of times. What themanufacturing industry needs instead is a robot that can do thousands of tasks, a few times. Programming a robot to solvejust one complex motor task has remained a challenging, costly and time-consuming task. In fact, it has become the keybottleneck in industrial robotics. Empowering robots with the ability to autonomously learn such tasks is a promisingapproach, and, in theory, machine learning has promised fully adaptive control algorithms which learn both by observationand trial-and-error. However, to date, learning techniques have yet to fulfil this promise, as only few methods manage toscale into the high-dimensional domains of manipulator robotics, or even the new upcoming trend of collaborative robots.The goal of the AssemblySkills ERC PoC is to validate an autonomous skill learning system that enables industrial robots toacquire and improve a rich set of motor skills. Using structured, modular control architectures is a promising concept to scalerobot learning to more complex real-world tasks. In such a modular control architecture, elemental building blocks – calledmovement primitives, need to be adapted, sequenced or co-activated simultaneously. Within the ERC PoC AssemblySkills,our goal is to group these modules into an industry-scale complete software package that can enable industrial robots tolearn new skills (particularly in assembly tasks). The value proposition of our ERC PoC is a cost-effective, novel machinelearning system that can unlock the potential of manufacturing robots by enabling them to learn to select, adapt andsequence parametrized building blocks such as movement primitives. Our approach is unique in the sense that it canacquire more than just a single desired trajectory as done in competing approaches, capable of save policy adaptation,requires only little data and can explain the solution to the robot operator. Fields of science natural sciencescomputer and information sciencessoftwareengineering and technologyelectrical engineering, electronic engineering, information engineeringelectronic engineeringroboticsnatural sciencescomputer and information sciencesartificial intelligencemachine learning Programme(s) H2020-EU.1.1. - EXCELLENT SCIENCE - European Research Council (ERC) Main Programme Topic(s) ERC-2020-POC - Call for proposals for ERC Proof of Concept Grant Call for proposal ERC-2020-PoC See other projects for this call Funding Scheme ERC-POC-LS - ERC Proof of Concept Lump Sum Pilot Coordinator TECHNISCHE UNIVERSITAT DARMSTADT Net EU contribution € 150 000,00 Address Karolinenplatz 5 64289 Darmstadt Germany See on map Region Hessen Darmstadt Darmstadt, Kreisfreie Stadt Activity type Higher or Secondary Education Establishments Links Contact the organisation Opens in new window Website Opens in new window Participation in EU R&I programmes Opens in new window HORIZON collaboration network Opens in new window Other funding € 0,00 Beneficiaries (1) Sort alphabetically Sort by Net EU contribution Expand all Collapse all TECHNISCHE UNIVERSITAT DARMSTADT Germany Net EU contribution € 150 000,00 Address Karolinenplatz 5 64289 Darmstadt See on map Region Hessen Darmstadt Darmstadt, Kreisfreie Stadt Activity type Higher or Secondary Education Establishments Links Contact the organisation Opens in new window Website Opens in new window Participation in EU R&I programmes Opens in new window HORIZON collaboration network Opens in new window Other funding € 0,00
