Evolutionary optimization of sliding contact positions in powered floor systems for mobile robots
-
Eric Medvet
Eric Medvet received the degree in Electronic Engineering cum laude in 2004 and the PhD degree in Computer Engineering in 2008, both from the University of Trieste, Italy. He is currently an Associate Professor in Computer Engineering at the Department of Engineering and Architecture of University of Trieste, Italy, where he leads the Evolutionary Robotics and Artificial Life lab (ERALlab) and is the co-head of the Machine Learning Lab. His research interests include Evolutionary Computation and Machine Learning applications.
,
Stefano Seriani
Stefano Seriani born in Trieste (Italy) in 1986, received his B.E. (2010) and his M.Sc in mechanical engineering (2012) from the University of Trieste, Italy. He received his PhD in April 2016 at the University of Trieste, Italy. In 2016 he was research fellow at the Institute of Robotics and Mechatronics of the German space agency (DLR). He is now research fellow at University of Trieste. His research interests include space robotics, applied mechanics, and computer-vision.
Alberto Bartoli received the degree in Electrical Engineering in 1989 cum laude and the PhD degree in Computer Engineering in 1993, both from the University of Pisa, Italy. Since 1998 he is an Associate Professor at the Department of Engineering and Architecture of University of Trieste, Italy, where he is the Director of the Machine Learning Lab. His research interests include Machine Learning applications, Evolutionary Computation, and security.
Paolo Gallina is currently Associate Professor of Applied Mechanics at the Department of Engineering and Architecture, University of Trieste, Trieste (Italy). He was visiting professor at the Ohio University in 2000/01. In 2002 he implemented a hands-on Mechatronics Laboratory for students in Engineering. In 2003 he implemented a Robotics Laboratory where he carries out his main research in robotics. He was head of the Council for Students in Mechanical Engineering and Industrial Engineering Degrees. He is the Director of the Master in Robotics at the University of Trieste. His interests are in vibrations, human-machine interfaces and robotics.
Abstract
Mobile robotics is a rapidly expanding technology due to its potential for increased safety and lower costs. In many applications, power is supplied to the robot through sliding contacts and a powered floor. Deciding the positions of the contacts on the robot is a difficult task: for any position/orientation of the robot, at least one contact has to touch a positive strip and at least one a negative strip. In this work, we tackle the problem using Differential Evolution (DE). We formally define problem-specific constraints and objectives and then describe how to use DE for evolving contact positions that satisfy those constraints and maximize those objectives. We validate experimentally our proposal by applying it to three real robots and by studying the impact of the main problem parameters on the effectiveness of the evolved designs for the sliding contacts.
Zusammenfassung
Mobile Robotik ist eine schnell wachsende Technologie, da sie die Betriebssicherheit erhöht und die Kosten senkt. In vielen Anwendungen wird der Roboter über Schleifkontakte und Bodenstrom versorgt. Die Bestimmung der Kontaktpositionen auf dem Roboter ist eine schwierige Aufgabe: Für jede Position/Ausrichtung des Roboters muss mindestens ein Kontakt einen positiven und mindestens einen negativen Stromabnehmer berühren. In dieser Arbeit lösen wir das Problem mit Differential Evolution (DE). Wir definieren formell problemspezifische Einschränkungen und Ziele und beschreiben dann, wie eine DE zum Entwurf von Kontaktpositionen verwendet wird, die diese Einschränkungen erfüllt und diese Ziele maximiert. Wir validieren unseren Vorschlag experimentell, indem wir ihn auf drei reale Roboter anwenden und die Wirkung von Haupteinflussfaktoren auf die Leistungsfähigkeit der entwickelten Designs für die Schleifkontakte untersuchen.
About the authors
Eric Medvet received the degree in Electronic Engineering cum laude in 2004 and the PhD degree in Computer Engineering in 2008, both from the University of Trieste, Italy. He is currently an Associate Professor in Computer Engineering at the Department of Engineering and Architecture of University of Trieste, Italy, where he leads the Evolutionary Robotics and Artificial Life lab (ERALlab) and is the co-head of the Machine Learning Lab. His research interests include Evolutionary Computation and Machine Learning applications.
Stefano Seriani born in Trieste (Italy) in 1986, received his B.E. (2010) and his M.Sc in mechanical engineering (2012) from the University of Trieste, Italy. He received his PhD in April 2016 at the University of Trieste, Italy. In 2016 he was research fellow at the Institute of Robotics and Mechatronics of the German space agency (DLR). He is now research fellow at University of Trieste. His research interests include space robotics, applied mechanics, and computer-vision.
Alberto Bartoli received the degree in Electrical Engineering in 1989 cum laude and the PhD degree in Computer Engineering in 1993, both from the University of Pisa, Italy. Since 1998 he is an Associate Professor at the Department of Engineering and Architecture of University of Trieste, Italy, where he is the Director of the Machine Learning Lab. His research interests include Machine Learning applications, Evolutionary Computation, and security.
Paolo Gallina is currently Associate Professor of Applied Mechanics at the Department of Engineering and Architecture, University of Trieste, Trieste (Italy). He was visiting professor at the Ohio University in 2000/01. In 2002 he implemented a hands-on Mechatronics Laboratory for students in Engineering. In 2003 he implemented a Robotics Laboratory where he carries out his main research in robotics. He was head of the Council for Students in Mechanical Engineering and Industrial Engineering Degrees. He is the Director of the Master in Robotics at the University of Trieste. His interests are in vibrations, human-machine interfaces and robotics.
References
1. Manuele Brambilla, Eliseo Ferrante, Mauro Birattari and Marco Dorigo. Swarm robotics: a review from the swarm engineering perspective. Swarm Intelligence, 7(1):1–41, 2013.10.1007/s11721-012-0075-2Search in Google Scholar
2. Janez Brest, Sao Greiner, Borko Boskovic, Marjan Mernik and Viljem Zumer. Self-adapting control parameters in differential evolution: A comparative study on numerical benchmark problems. IEEE transactions on evolutionary computation, 10(6):646–657, 2006.10.1109/TEVC.2006.872133Search in Google Scholar
3. Swagatam Das and Ponnuthurai Nagaratnam Suganthan. Differential evolution: a survey of the state-of-the-art. IEEE transactions on evolutionary computation, 15(1):4–31, 2011.10.1109/TEVC.2010.2059031Search in Google Scholar
4. Jacqueline Heinerman, Massimiliano Rango and AE Eiben. Evolution, individual learning, and social learning in a swarm of real robots. In Computational Intelligence, 2015 IEEE Symposium Series on. pages 1055–1062. IEEE, 2015.10.1109/SSCI.2015.152Search in Google Scholar
5. Jacqueline Heinerman, Alessandro Zonta, Evert Haasdijk and Agoston Endre Eiben. On-line evolution of foraging behaviour in a population of real robots. In European Conference on the Applications of Evolutionary Computation, pages 198–212. Springer, 2016.10.1007/978-3-319-31153-1_14Search in Google Scholar
6. John Klingner, Anshul Kanakia, Nicholas Farrow, Dustin Reishus and Nikolaus Correll. A stick-slip omnidirectional powertrain for low-cost swarm robotics: Mechanism, calibration, and control. In Intelligent Robots and Systems (IROS 2014), 2014 IEEE/RSJ International Conference on. pages 846–851. IEEE, 2014.10.1109/IROS.2014.6942658Search in Google Scholar
7. Eric Medvet, Stefano Seriani, Alberto Bartoli and Paolo Gallina. Design of powered floor systems for mobile robots with differential evolution. In International Conference on the Applications of Evolutionary Computation (Part of EvoStar), pages 19–32. Springer, 2019.10.1007/978-3-030-16692-2_2Search in Google Scholar
8. Stefano Nolfi, Josh Bongard, Phil Husbands and Dario Floreano. Evolutionary robotics. In Springer Handbook of Robotics, pages 2035–2068. Springer, 2016.10.1007/978-3-319-32552-1_76Search in Google Scholar
9. Luigi Pastena. A catenary-free electrification for urban transport: An overview of the tramwave system. IEEE Electrification Magazine, 2(3):16–21, 2014.10.1109/MELE.2014.2333791Search in Google Scholar
10. S. Seriani, P. Gallina and A. Wedler. A modular cable robot for inspection and light manipulation on celestial bodies. Acta Astronautica, 123:145–153, 2016.10.1016/j.actaastro.2016.03.020Search in Google Scholar
11. S. Seriani, P. Gallina and A. Wedler. Dynamics of a tethered rover on rough terrain, volume 47 of Mechanisms and Machine Science, 2017.10.1007/978-3-319-48375-7_38Search in Google Scholar
12. AWC Shing and PPL Wong. Wear of pantograph collector strips. Proceedings of the Institution of Mechanical Engineers, Part F: Journal of Rail and Rapid Transit, 222(2):169–176, 2008.10.1243/09544097JRRT156Search in Google Scholar
13. Fernando Silva, Luís Correia and Anders Lyhne Christensen. Evolutionary online behaviour learning and adaptation in real robots. Royal Society open science, 4(7):160938, 2017.10.1098/rsos.160938Search in Google Scholar
14. Neil JA Sloane and Aaron D Wyner. Claude Elwood Shannon: Collected Papers. IEEE press, 1993.10.1109/9780470544242Search in Google Scholar
15. Rainer Storn and Kenneth Price. Differential evolution–a simple and efficient heuristic for global optimization over continuous spaces. Journal of global optimization, 11(4):341–359, 1997.10.1023/A:1008202821328Search in Google Scholar
16. Junhua Wang, Meilin Hu, Changsong Cai, Zhongzheng Lin, Liang Li and Zhijian Fang. Optimization design of wireless charging system for autonomous robots based on magnetic resonance coupling. AIP Advances, 8(5):055004, 2018.10.1063/1.5030445Search in Google Scholar
17. Richard A Watson, Sevan G Ficici and Jordan B Pollack. Embodied evolution: Distributing an evolutionary algorithm in a population of robots. Robotics and Autonomous Systems, 39(1):1–18, 2002.10.1016/S0921-8890(02)00170-7Search in Google Scholar
18. Mingbo Yang, Guodong Yang, En Li, Zize Liang and Hao Lin. Modeling and analysis of wireless power transmission system for inspection robot. In Industrial Electronics (ISIE), 2013 IEEE International Symposium on. pages 1–5. IEEE, 2013.10.1109/ISIE.2013.6563633Search in Google Scholar
© 2020 Walter de Gruyter GmbH, Berlin/Boston
Articles in the same Issue
- Frontmatter
- Editorial
- EvoStar 2019: Bio-Inspired Computing and Automation
- Methoden
- Phase-space exploration of unit ensembles in energy management
- Anwendungen
- Evolutionary optimization of sliding contact positions in powered floor systems for mobile robots
- Using MAP-Elites to support policy making around Workforce Scheduling and Routing
- A computational intelligence based approach for optimized operation scheduling of energy plants
- Long term predictions of coal fired power plant data using evolved recurrent neural networks
- Process planning and scheduling optimisation with alternative recipes
- Persönliches
- Gedenkkolloquium Ernst Dieter Gilles (1935–2019)
Articles in the same Issue
- Frontmatter
- Editorial
- EvoStar 2019: Bio-Inspired Computing and Automation
- Methoden
- Phase-space exploration of unit ensembles in energy management
- Anwendungen
- Evolutionary optimization of sliding contact positions in powered floor systems for mobile robots
- Using MAP-Elites to support policy making around Workforce Scheduling and Routing
- A computational intelligence based approach for optimized operation scheduling of energy plants
- Long term predictions of coal fired power plant data using evolved recurrent neural networks
- Process planning and scheduling optimisation with alternative recipes
- Persönliches
- Gedenkkolloquium Ernst Dieter Gilles (1935–2019)
