TY - GEN
T1 - An Innate Motivation to Tidy Your Room: Online Onboard Evolution of Manipulation Behaviors in a Robot Swarm
AU - Kaiser, Tanja Katharina
AU - Lang, Christine
AU - Marwitz, Florian Andreas
AU - Charles, Christian
AU - Dreier, Sven
AU - Petzold, Julian
AU - Hannawald, Max Ferdinand
AU - Begemann, Marian Johannes
AU - Hamann, Heiko
N1 - DBLP License: DBLP's bibliographic metadata records provided through http://dblp.org/ are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions.
PY - 2021
Y1 - 2021
N2 - As our contribution to the effort of developing methods to make robots more adaptive and robust to dynamic environments, we have proposed our method of ‘minimal surprise’ in a series of previous works. In a multi-robot setting, we use evolutionary computation to evolve pairs of artificial neural networks: an actor network to select motor speeds and a predictor network to predict future sensor input. By rewarding for prediction accuracy, we give robots an innate, task-independent motivation to behave in structured and thus, predictable ways. While we previously focused on feasibility studies using abstract simulations, we now present our first results using realistic robot simulations and first experiments with real robot hardware. In a centralized online and onboard evolution approach, we show that minimize surprise works effectively on Thymio II robots in an area cleaning scenario.
AB - As our contribution to the effort of developing methods to make robots more adaptive and robust to dynamic environments, we have proposed our method of ‘minimal surprise’ in a series of previous works. In a multi-robot setting, we use evolutionary computation to evolve pairs of artificial neural networks: an actor network to select motor speeds and a predictor network to predict future sensor input. By rewarding for prediction accuracy, we give robots an innate, task-independent motivation to behave in structured and thus, predictable ways. While we previously focused on feasibility studies using abstract simulations, we now present our first results using realistic robot simulations and first experiments with real robot hardware. In a centralized online and onboard evolution approach, we show that minimize surprise works effectively on Thymio II robots in an area cleaning scenario.
UR - https://www.mendeley.com/catalogue/d8862dd7-49a4-39cd-86b8-7a9008d09e01/
U2 - 10.1007/978-3-030-92790-5_15
DO - 10.1007/978-3-030-92790-5_15
M3 - Conference contribution
SN - 9783030927899
T3 - Springer Proceedings in Advanced Robotics
SP - 190
EP - 201
BT - Springer Proceedings in Advanced Robotics
ER -
