An Evolutionary Robotics Approach to the Control of Plant Growth and Motion: Modeling Plants and Crossing the Reality Gap

Mostafa Wahby; Daniel Nicolas Hofstadler; Mary Katherine Heinrich; Payam Zahadat; Heiko Hamann

doi:10.1109/SASO.2016.8

An Evolutionary Robotics Approach to the Control of Plant Growth and Motion: Modeling Plants and Crossing the Reality Gap

Mostafa Wahby
, Daniel Nicolas Hofstadler
, Mary Katherine Heinrich
, Payam Zahadat
, Heiko Hamann

Research output: Conference Article in Proceeding or Book/Report chapter › Article in proceedings › Research › peer-review

Abstract

The self-organizing bio-hybrid collaboration ofrobots and natural plants allows for a variety of interestingapplications. As an example we investigate how robots can beused to control the growth and motion of a natural plant, using LEDs to provide stimuli. We follow an evolutionaryrobotics approach where task performance is determined bymonitoring the plant's reaction. First, we do initial plantexperiments with simple, predetermined controllers. Then weuse image sampling data as a model of the dynamics ofthe plant tip xy position. Second, we use this approach toevolve robot controllers in simulation. The task is to makethe plant approach three predetermined, distinct points in anxy-plane. Finally, we test the evolved controllers in real plantexperiments and find that we cross the reality gap successfully. We shortly describe how we have extended from plant tipto many points on the plant, for a model of the plant stemdynamics. Future work will extend to two-axes image samplingfor a 3-d approach.

Original language	English
Title of host publication	2016 IEEE 10th International Conference on Self-Adaptive and Self-Organizing Systems
Number of pages	10
Publisher	IEEE
Publication date	2016
Pages	21-30
ISBN (Electronic)	978-1-5090-3534-2
DOIs	https://doi.org/10.1109/SASO.2016.8
Publication status	Published - 2016
Externally published	Yes
Event	International Conference on Self-Adaptive and Self-Organizing Systems - Augsburg, Germany Duration: 12 Sept 2016 → 16 Sept 2016 Conference number: 10

Conference

Conference	International Conference on Self-Adaptive and Self-Organizing Systems
Number	10
Country/Territory	Germany
City	Augsburg
Period	12/09/2016 → 16/09/2016

Keywords

biohybrid robotics
plant-robot interaction
evolutionary robotics
image-based plant dynamics modeling
sim-to-real transfer

Access to Document

10.1109/SASO.2016.8

FloraRobotica: Societies of Symbiotic Robot-plant Bio-Hybrids as social Architectural Artifacts
Støy, K. (PI), Veenstra, F. (CoI), Zahadat, P. (CoI), Nielsen, S. A. (CoI), Blichfeldt, T. (CoI), Schmidt, M. (CoI) & Risi, S. (PI)
European Commission
01/04/2015 → 31/03/2019
Project: Research

Cite this

@inproceedings{1535b59f4e67498a8696bc08a370825d,

title = "An Evolutionary Robotics Approach to the Control of Plant Growth and Motion: Modeling Plants and Crossing the Reality Gap",

abstract = "The self-organizing bio-hybrid collaboration ofrobots and natural plants allows for a variety of interestingapplications. As an example we investigate how robots can beused to control the growth and motion of a natural plant, using LEDs to provide stimuli. We follow an evolutionaryrobotics approach where task performance is determined bymonitoring the plant's reaction. First, we do initial plantexperiments with simple, predetermined controllers. Then weuse image sampling data as a model of the dynamics ofthe plant tip xy position. Second, we use this approach toevolve robot controllers in simulation. The task is to makethe plant approach three predetermined, distinct points in anxy-plane. Finally, we test the evolved controllers in real plantexperiments and find that we cross the reality gap successfully. We shortly describe how we have extended from plant tipto many points on the plant, for a model of the plant stemdynamics. Future work will extend to two-axes image samplingfor a 3-d approach.",

keywords = "biohybrid robotics, plant-robot interaction, evolutionary robotics, image-based plant dynamics modeling, sim-to-real transfer",

author = "Mostafa Wahby and Hofstadler, \{Daniel Nicolas\} and Heinrich, \{Mary Katherine\} and Payam Zahadat and Heiko Hamann",

year = "2016",

doi = "10.1109/SASO.2016.8",

language = "English",

pages = "21--30",

booktitle = "2016 IEEE 10th International Conference on Self-Adaptive and Self-Organizing Systems",

publisher = "IEEE",

address = "United States",

note = "International Conference on Self-Adaptive and Self-Organizing Systems, SASO ; Conference date: 12-09-2016 Through 16-09-2016",

}

Wahby, M, Hofstadler, DN, Heinrich, MK, Zahadat, P & Hamann, H 2016, An Evolutionary Robotics Approach to the Control of Plant Growth and Motion: Modeling Plants and Crossing the Reality Gap. in 2016 IEEE 10th International Conference on Self-Adaptive and Self-Organizing Systems . IEEE, pp. 21-30, International Conference on Self-Adaptive and Self-Organizing Systems, Augsburg, Germany, 12/09/2016. https://doi.org/10.1109/SASO.2016.8

An Evolutionary Robotics Approach to the Control of Plant Growth and Motion: Modeling Plants and Crossing the Reality Gap. / Wahby, Mostafa; Hofstadler, Daniel Nicolas; Heinrich, Mary Katherine et al.
2016 IEEE 10th International Conference on Self-Adaptive and Self-Organizing Systems . IEEE, 2016. p. 21-30.

Research output: Conference Article in Proceeding or Book/Report chapter › Article in proceedings › Research › peer-review

TY - GEN

T1 - An Evolutionary Robotics Approach to the Control of Plant Growth and Motion: Modeling Plants and Crossing the Reality Gap

AU - Wahby, Mostafa

AU - Hofstadler, Daniel Nicolas

AU - Heinrich, Mary Katherine

AU - Zahadat, Payam

AU - Hamann, Heiko

N1 - Conference code: 10

PY - 2016

Y1 - 2016

N2 - The self-organizing bio-hybrid collaboration ofrobots and natural plants allows for a variety of interestingapplications. As an example we investigate how robots can beused to control the growth and motion of a natural plant, using LEDs to provide stimuli. We follow an evolutionaryrobotics approach where task performance is determined bymonitoring the plant's reaction. First, we do initial plantexperiments with simple, predetermined controllers. Then weuse image sampling data as a model of the dynamics ofthe plant tip xy position. Second, we use this approach toevolve robot controllers in simulation. The task is to makethe plant approach three predetermined, distinct points in anxy-plane. Finally, we test the evolved controllers in real plantexperiments and find that we cross the reality gap successfully. We shortly describe how we have extended from plant tipto many points on the plant, for a model of the plant stemdynamics. Future work will extend to two-axes image samplingfor a 3-d approach.

AB - The self-organizing bio-hybrid collaboration ofrobots and natural plants allows for a variety of interestingapplications. As an example we investigate how robots can beused to control the growth and motion of a natural plant, using LEDs to provide stimuli. We follow an evolutionaryrobotics approach where task performance is determined bymonitoring the plant's reaction. First, we do initial plantexperiments with simple, predetermined controllers. Then weuse image sampling data as a model of the dynamics ofthe plant tip xy position. Second, we use this approach toevolve robot controllers in simulation. The task is to makethe plant approach three predetermined, distinct points in anxy-plane. Finally, we test the evolved controllers in real plantexperiments and find that we cross the reality gap successfully. We shortly describe how we have extended from plant tipto many points on the plant, for a model of the plant stemdynamics. Future work will extend to two-axes image samplingfor a 3-d approach.

KW - biohybrid robotics

KW - plant-robot interaction

KW - evolutionary robotics

KW - image-based plant dynamics modeling

KW - sim-to-real transfer

U2 - 10.1109/SASO.2016.8

DO - 10.1109/SASO.2016.8

M3 - Article in proceedings

SP - 21

EP - 30

BT - 2016 IEEE 10th International Conference on Self-Adaptive and Self-Organizing Systems

PB - IEEE

T2 - International Conference on Self-Adaptive and Self-Organizing Systems

Y2 - 12 September 2016 through 16 September 2016

ER -

An Evolutionary Robotics Approach to the Control of Plant Growth and Motion: Modeling Plants and Crossing the Reality Gap

Abstract

Conference

Keywords

Access to Document

Fingerprint

Projects

FloraRobotica: Societies of Symbiotic Robot-plant Bio-Hybrids as social Architectural Artifacts

Cite this