Robot Learning – An Industrial Perspective on Challenges and Opportunities

Konferenz: ISR 2020 - 52th International Symposium on Robotics
09.12.2020 - 10.12.2020 in online

Tagungsband: ISR 2020

Seiten: 7Sprache: EnglischTyp: PDF

Wahrburg, Arne; Kirsten, Rene; Enayati, Nima (ABB AG, Corporate Research Center, Ladenburg, Germany)
Reisinger, Thomas (ABB Automation GmbH, Friedberg, Germany)
Listmann, Kim D. (ABB Future Labs, Baden-Dättwil, Switzerland)

Robot Learning has been a very active field of research recently with a lot of impressive scientific results especially in the application of reinforcement learning to robotic tasks. From an industrial perspective, the rapid scientific developments in Robot Learning come with a number of promises including reduced commissioning times, simplified programming, increased productivity, and cost reduction. In this paper, we attempt to put the potential of this promising but in the media sometimes hyped technology to perspective by matching it to industrial requirements. Key challenges and opportunities on how to potentially tackle them are presented.