TY - GEN
T1 - Experiences from real-world evolution with DYRET
T2 - 3rd Symposium of the Norwegian AI Society, NAIS 2019
AU - Nygaard, Tønnes F.
AU - Nordmoen, Jørgen
AU - Ellefsen, Kai Olav
AU - Martin, Charles P.
AU - Tørresen, Jim
AU - Glette, Kyrre
N1 - Publisher Copyright:
© Springer Nature Switzerland AG 2019.
PY - 2019
Y1 - 2019
N2 - Creating robust robot platforms that function in the real world is a difficult task. Adding the requirement that the platform should be capable of learning, from nothing, ways to generate its own movement makes the task even harder. Evolutionary Robotics is a promising field that combines the creativity of evolutionary optimization with the real-world focus of robotics to bring about unexpected control mechanisms in addition to whole new robot designs. Constructing a platform that is capable of these feats is difficult, and it is important to share experiences and lessons learned so that designers of future robot platforms can benefit. In this paper, we introduce our robotics platform and detail our experiences with real-world evolution. We present thoughts on initial design considerations and key insights we have learned from extensive experimentation. We hope to inspire new platform development and hopefully reduce the threshold of doing real-world legged robot evolution.
AB - Creating robust robot platforms that function in the real world is a difficult task. Adding the requirement that the platform should be capable of learning, from nothing, ways to generate its own movement makes the task even harder. Evolutionary Robotics is a promising field that combines the creativity of evolutionary optimization with the real-world focus of robotics to bring about unexpected control mechanisms in addition to whole new robot designs. Constructing a platform that is capable of these feats is difficult, and it is important to share experiences and lessons learned so that designers of future robot platforms can benefit. In this paper, we introduce our robotics platform and detail our experiences with real-world evolution. We present thoughts on initial design considerations and key insights we have learned from extensive experimentation. We hope to inspire new platform development and hopefully reduce the threshold of doing real-world legged robot evolution.
KW - Evolutionary robotics
KW - Lessons learned
KW - Real-world evolution
UR - http://www.scopus.com/inward/record.url?scp=85076582204&partnerID=8YFLogxK
U2 - 10.1007/978-3-030-35664-4_6
DO - 10.1007/978-3-030-35664-4_6
M3 - Conference contribution
AN - SCOPUS:85076582204
SN - 9783030356637
T3 - Communications in Computer and Information Science
SP - 58
EP - 68
BT - Nordic Artificial Intelligence Research and Development - Third Symposium of the Norwegian AI Society, NAIS 2019, Proceedings
A2 - Bach, Kerstin
A2 - Ruocco, Massimiliano
PB - Springer
Y2 - 27 May 2019 through 28 May 2019
ER -