Classifying Environmental Features From Local Observations of Emergent Swarm Behavior

Megan Emmons; Anthony A. Maciejewski; Charles Anderson; Edwin K. P. Chong

doi:10.1109/JAS.2020.1003129

Volume 7 Issue 3

Apr. 2020

IEEE/CAA Journal of Automatica Sinica

JCR Impact Factor: 15.3, Top 1 (SCI Q1)

CiteScore: 23.5, Top 2% (Q1)
Google Scholar h5-index: 77， TOP 5

Turn off MathJax

Article Contents

Article Navigation > IEEE/CAA Journal of Automatica Sinica > 2020 > 7(3): 674-682

Megan Emmons, Anthony A. Maciejewski, Charles Anderson and Edwin K. P. Chong, "Classifying Environmental Features From Local Observations of Emergent Swarm Behavior," IEEE/CAA J. Autom. Sinica, vol. 7, no. 3, pp. 674-682, May 2020. doi: 10.1109/JAS.2020.1003129

Citation:

Megan Emmons, Anthony A. Maciejewski, Charles Anderson and Edwin K. P. Chong, "Classifying Environmental Features From Local Observations of Emergent Swarm Behavior," IEEE/CAA J. Autom. Sinica, vol. 7, no. 3, pp. 674-682, May 2020. doi: 10.1109/JAS.2020.1003129

Citation:

PDF( 1174 KB)

Classifying Environmental Features From Local Observations of Emergent Swarm Behavior

doi: 10.1109/JAS.2020.1003129

More Information

Author Bio:
Megan Emmons (S’08) is currently a Ph.D. candidate at Colorado State University, USA. She received the B.S. degree from the Colorado School of Mines, USA, in 2010 and M.S. degree from Utah State University, USA, in 2013. Her research interests include control systems and swarm robotics. She is an elected, at-large Member of the IEEE Robotics and Automation Society. Her research interests include robotics and biologically-inspired systems

Anthony A. Maciejewski (F’05) received the B.S., M.S., and the Ph.D. degrees in electrical engineering from The Ohio State University, USA, in 1982, 1984, and 1987, respectively. From 1988 to 2001, he was a Professor of electrical and computer engineering with Purdue University, USA. He is currently a Professor and Department Head of Electrical and Computer Engineering with Colorado State University, USA. His research interests include robotics, high-performance computing, and STEM education. A complete vita is available at: http://www.engr.colostate.edu/~aam

Charles Anderson (SM’15) received the B.S. degree in computer science from the University of Nebraska, USA, in 1978 and the Ph.D. degree in computer science from the University of Massachusetts-Amherst, USA, in 1986. After working as a machine learning Researcher at GTE Labs, he joined the Faculty of the Department of Computer Science at Colorado State University in Fort Collins, USA. He has been a Professor there for 28 years where he holds joint appointment in the Molecular, Cellular, and Integrative Neuroscience Program, the School of Biomedical Engineering, the Graduate Degree Program in Ecology, and the Online Systems Engineering Graduate Program. He teaches and conducts research in machine learning with a focus on deep reinforcement learning. He teaches and conducts research in machine learning algorithms for classification, prediction and control with a focus on reinforcement learning, and brain-computer interfaces

Edwin K. P. Chong (F’04) received the B.E. degree (First Class Honors) from the University of Adelaide, South Australia, in 1987; and the M.A. and Ph.D. degrees in 1989 and 1991, respectively, both from Princeton, where he held an IBM Fellowship. He joined the School of Electrical and Computer Engineering at Purdue University, USA, in 1991, where he was named a University Faculty Scholar in 1999. Since August 2001, he has been a Professor of electrical and computer engineering and of mathematics at Colorado State University, USA. He coauthored the best-selling book, An Introduction to Optimization (4th Edition, Wiley-Interscience, 2013). He is an IEEE Fellow and was President of the IEEE Control Systems Society in 2017. His research interests include optimization, control, estimation, and stochastic systems
Corresponding author: M. Emmons, A. A. Maciejewski, and E. K. P. Chong are with the Department of Electrical and Computer Engineering, Colorado State University, Fort Collins, CO 80523 USA (e-mail: memmons14k@gmail.com; aam@colostate.edu; edwin.chong@colostate.edu)
Received Date: 2020-01-29
Revised Date: 2020-02-19
Accepted Date: 2020-03-06

Available Online: 2020-03-26

Abstract

Abstract

Robots in a swarm are programmed with individual behaviors but then interactions with the environment and other robots produce more complex, emergent swarm behaviors. One discriminating feature of the emergent behavior is the local distribution of robots in any given region. In this work, we show how local observations of the robot distribution can be correlated to the environment being explored and hence the location of openings or obstructions can be inferred. The correlation is achieved here with a simple, single-layer neural network that generates physically intuitive weights and provides a degree of robustness by allowing for variation in the environment and number of robots in the swarm. The robots are simulated assuming random motion with no communication, a minimalist model in robot sophistication, to explore the viability of cooperative sensing. We culminate our work with a demonstration of how the local distribution of robots in an unknown, office-like environment can be used to locate unobstructed exits.
- Biologically inspired robotics,
- environment exploration,
- multi-agent systems,
- swarm robotics

FullText(HTML)

References(26)

References

[1]	I. Navarro and F. Matía, “An introduction to swarm robotics,” Int. Scholarly Research Notices Robotics, vol. 2013, 2012. doi: 10.5402/2013/608164
[2]	R. L. Sturdivant and E. K. P. Chong, “The necessary and sufficient conditions for emergence in systems applied to symbol emergence in robots,” IEEE Trans. Cognitive and Developmental Systems, vol. 10, no. 4, pp. 1035–1042, Dec. 2018. doi: 10.1109/TCDS.2017.2731361
[3]	M. Emmons, A. A. Maciejewski, and E. K. P. Chong, “Modelling emergent swarm behavior using continuum limits for environmental mapping,” in Proc. IEEE Int. Conf. Control and Automation, Jun. 2018, pp. 86–93.
[4]	C. A. C. Parker and H. Zhang, “Cooperative decision-making in decentralized multiple-robot systems: the best-of-n problem,” IEEE/ASME Trans. Mechatronics, vol. 14, no. 2, pp. 240–251, Apr. 2009. doi: 10.1109/TMECH.2009.2014370
[5]	J. T. Ebert, M. Gauci, and R. Nagpal, “Multi feature collective decision making in robot swarms,” in Proc. 17th Int. Conf. Autonomous Agents and Multiagent Systems, Jul. 2018.
[6]	M. Schneider-Fontan and M. J. Mataric, “Territorial multi-robot task division,” IEEE Trans. Robotics and Automation, vol. 14, no. 5, pp. 815–822, Oct. 1998. doi: 10.1109/70.720357
[7]	B. P. Gerkey and M. J. Matarić, “A formal analysis and taxonomy of task allocation in multi-robot systems,” The Int. J. Robotics Research, vol. 23, no. 9, pp. 939–953, 2004. doi: 10.1177/0278364904045564
[8]	M. J. Matarić, G. S. Sukhatme, and E. H. Østergaard, “Multi-robot task allocation in uncertain environments,” Autonomous Robots, vol. 14, no. 2, pp. 255–263, Mar. 2003.
[9]	D. Fox, W. Burgard, H. Kruppa, and S. Thrun, “A probabilistic approach to collaborative multi-robot localization,” Autonomous Robots, vol. 8, no. 3, pp. 325–344, Jun. 2000. doi: 10.1023/A:1008937911390
[10]	A. Prorok, A. Bahr, and A. Martinoli, “Low-cost collaborative localization for large-scale multi-robot systems,” in Proc. IEEE Int. Conf. Robotics and Automation, May 2012, pp. 4236–4241.
[11]	J. Chen, K. H. Low, Y. Yao, and P. Jaillet, “Gaussian process decentralized data fusion and active sensing for spatiotemporal traffic modeling and prediction in mobility-on-demand systems,” IEEE Trans. Automation Science and Engineering, vol. 12, no. 3, pp. 901–921, Jul. 2015. doi: 10.1109/TASE.2015.2422852
[12]	A. Giusti, J. Nagi, L. Gambardella, and G. A. D. Caro, “Cooperative sensing and recognition by a swarm of mobile robots,” in Proc. IEEE/RSJ Int. Conf. Intelligent Robots and Systems, Oct. 2012, pp. 551–558.
[13]	K. H. Low, W. K. Leow, and J. Marcelo H. Ang, “Autonomic mobile sensor network with self-coordinated task allocation and execution,” IEEE Trans. Systems,Man,and Cybernetics,Part C (Applications and Reviews), vol. 36, no. 3, pp. 315–327, May 2006. doi: 10.1109/TSMCC.2006.871590
[14]	S. Bandyopadhyay, S.-J. Chung, and F. Y. Hadaegh, “Probabilistic and distributed control of a large-scale swarm of autonomous agents,” IEEE Trans. Robotics, vol. 33, no. 5, pp. 1103–1123, Oct. 2017. doi: 10.1109/TRO.2017.2705044
[15]	A. Dirafzoon and E. Lobaton, “Topological mapping of unknown environments using an unlocalized robotic swarm,” in Proc. IEEE/RSJ Int. Conf. Intelligent Robots and Systems, pp. 5545–5551, Nov. 2013.
[16]	S. Levine, P. Pastor, A. Krizhevsky, J. Ibarz, and D. Quillen, “Learning hand-eye coordination for robotic grasping with deep learning and largescale data collection,” The Int. J. Robotics Research, vol. 34, no. 4–5, pp. 421–436, 2018.
[17]	J. Morelli, P. Zhu, B. Doerr, R. Linares, and S. Ferrari, “Integrated mapping and path planning for very large-scale robotic (vlsr) systems,” in Proc. Int. Conf. Robotics and Automation, May 2019, pp. 3356–3362.
[18]	L. Hou, F. Fan, J. Fu, and J. Wang, “Time-varying algorithm for swarm robotics,” IEEE/CAA J. Autom. Sinica, vol. 5, no. 1, pp. 217–222, Jan. 2018. doi: 10.1109/JAS.2017.7510685
[19]	S. Berman, V. Kumar, and R. Nagpal, “Design of control policies for spatially inhomogeneous robot swarms with application to commercial pollination,” in Proc. IEEE Int. Conf. Robotics and Automation, May 2011, pp. 378–385.
[20]	K. Elamvazhuthi, H. Kuiper, and S. Berman, “PDE-based optimization for stochastic mapping and coverage strategies using robotic ensembles,” Automatica, vol. 95, pp. 356–367, Sept. 2018. doi: 10.1016/j.automatica.2018.06.007
[21]	L. E. Barnes, M. A. Fields, and K. P. Valavanis, “Swarm formation control utilizing elliptical surfaces and limiting functions,” IEEE Trans. Systems,Man,and Cybernetics,Part B, vol. 39, no. 6, pp. 1434–1445, Dec. 2009. doi: 10.1109/TSMCB.2009.2018139
[22]	F. Mondada, M. Bonani, X. Raemy, J. Pugh, C. Cianci, A. Klaptocz, S. Magnenat, J.-C. Zufferey, D. Floreano, and A. Martinoli, “The e-puck, a robot designed for education in engineering,” in Proc. 9th Conf. Autonomous Robot Systems and Competitions, vol. 1, no. 1, pp. 59–65, 2009. [Online]. Available: http://infoscience.epfl.ch/record/135236
[23]	F. Mondada, E. Franzi, and P. Ienne, “Mobile robot miniaturisation: a tool for investigation in control algorithms,” Experimental Robotics III, vol. 200, pp. 501–513, 2009.
[24]	M. Rubenstein, C. Ahler, and R. Nagpal, “Kilobot: a low cost scalable robot system for collective behaviors,” in Proc. IEEE Int. Conf. Robotics and Automation, May 2012, pp. 3293–3298.
[25]	C. M. Bishop, Pattern Recognition and Machine Learning. Springer, 2013.
[26]	B. Yamauchi, “A frontier-based approach for autonomous exploration,” in Proc. Int. Symp. Computational Intelligence in Robotics and Automation, Jul. 1997, pp. 146–151.

Supplements(0)

Cited By

Proportional views

Proportional views

通讯作者: 陈斌, bchen63@163.com

1.
沈阳化工大学材料科学与工程学院沈阳 110142

Figures(7) / Tables(2)

Get Citation

PDF

XML

Article Metrics

Article views (2106) PDF downloads(74)

Highlights

Demonstrate the locally observed distribution of a robot swarm can be correlated to the location of openings in office-like environments
a) Simulated robots are extremely simple - they are not equipped with any communication abilities and only use random motion to explore the environment
b) Correlation between locally observed robot density and global environmental features can be achieved with a simple, single-layer neural network
c) Only information required to predict environment class is a local observation of the robot density.
Can use the correlation to predict the location of exits in an office-like environment without requiring any communication or path-planning algorithms.
Approach is extremely robust: environments can still be classified at better than random accuracy following a 90% loss in the number of robots functioning
a) Extending the classification process, after a 90% decrease in the number of robots, an office worker can still observe the number of robots around them and move away from the least likely exit location to further increase the classification accuracy of the system.

Classifying Environmental Features From Local Observations of Emergent Swarm Behavior

doi: 10.1109/JAS.2020.1003129

Abstract

References

Proportional views

Catalog

通讯作者: 陈斌, bchen63@163.com

Article Metrics

Highlights

Export File

Citation

Format

Content