The University of Southampton
Telephone:
+442380599255
Email:
D.S.Tarapore@soton.ac.uk

Dr Danesh Tarapore 

Personal homepage

I am an Assistant Professor at the Agents Interaction and Complexity GroupElectronics and Computer Science at the University of Southampton. Prior to Southampton I was a recipient of the prestigious Marie Curie research fellow award and hosted at the University of York. This followed previous research fellow appointments at the UPMC (France), Gulbenkian Institute of Science (Portugal), Institute for Systems and Robotics (Portugal), Swiss Federal Institute of Technology (Switzerland), and University of Lausanne (Switzerland) where I obtained my doctoral degree in Life Science. I have a Masters degree in Computer Science from the Indian Institute of Technology, Bombay.

Through the development and application of theoretical models, agent-based models, multi-scale stochastic simulations, and the physical instantiation of biological models in robots, I have addressed a diverse range of important problems in, task allocation and division of labor in large-scale multiagent systems, immunological maintenance of self-tolerance in the adaptive immune system, and fault-detection and fault-tolerance in both single-robot systems and large-scale robot swarms. Research on resilient robots that I have collaborated on has been featured on the front cover of the Nature magazine and received widespread media coverage. The work was covered by around 40 news outlets (including BBC News, CBC, Washington Post, The Guardian, The New York Times, and BBC Radio), and by over 15 science and technology blogs (including IEEE Spectrum, CNET, Science/AAAS, Phys.org, Tech Times, Wired.co.uk and Robotics Trends). The accompanying videos demonstrating robot damage recovery received over 225k views on YouTube.

Research

Research interests

My research aims to push robot swarms currently operating in carefully controlled laboratory environments out into the real world.

Robot swarms to date are frail systems, unprepared for long-term autonomy. They require hours of learning to adapt their behavior, to recover from faults inevitably sustained during operation. My research aims to remedy this situation by developing an algorithmic framework allowing robots in a swarm to robustly detect faults in each other, and adapt rapidly to unforeseen situations in their environment.

As an early career researcher, I have secured over £400K of research funding. I am currently PI on an EPSRC New Investigator grant to develop data-efficient learning algorithms for rapid behavior adaptation in robot swarms. Am also a Co-PI on a Turing pilot project formulating scalable human-swarm interactions for flexible autonomy.

Publications

Tarapore, Danesh, Lungarella, Max and Gómez, Gabriel (2006) Quantifying patterns of agent--environment interaction. Robotics and Autonomous Systems, 54 (2), 150-158.

Tarapore, Danesh, Christensen, Anders Lyhne, Lima, Pedro U and Carneiro, Jorge (2012) Environment classification in multiagent systems inspired by the adaptive immune system. In Proceedings of the 13th International Conference on the Simulation and Synthesis of Living Systems, Artificial Life. vol. 13, pp. 275-282 .

Tarapore, Danesh, Floreano, Dario and Keller, Laurent (2010) Task-dependent influence of genetic architecture and mating frequency on division of labour in social insect societies. Behavioral Ecology and Sociobiology, 64 (4), 675-684.

Lichocki, Pawel, Tarapore, Danesh, Keller, Laurent and Floreano, Dario (2012) Neural networks as mechanisms to regulate division of labor. The American Naturalist, 179 (3), 391-400.

Tarapore, Danesh, Christensen, Anders Lyhne, Lima, Pedro U and Carneiro, Jorge (2012) Clonal expansion without self-replicating entities. In International Conference on Artificial Immune Systems. pp. 191-204 .

Tarapore, Danesh, Christensen, Anders Lynhe, Lima, Pedro U and Carneiro, Jorge (2013) Abnormality detection in multiagent systems inspired by the adaptive immune system. In Proceedings of the 2013 international conference on Autonomous agents and multi-agent systems. pp. 23-30 .

Tarapore, Danesh and Mouret, J-B (2014) Comparing the evolvability of generative encoding schemes. In Artificial Life 14: Fourteenth International Conference on the Synthesis and Simulation of Living Systems. pp. 55-62 .

Tarapore, Danesh, Christensen, Anders Lyhne and Timmis, Jon (2015) Abnormality detection in robots exhibiting composite swarm behaviours. In Proceedings of the 13th European Conference on Artificial Life (ECAL). MIT Press. pp. 406-413 .

Tarapore, Danesh, Lima, Pedro U., Carneiro, Jorge and Christensen, Anders Lyhne (2015) To err is robotic, to tolerate immunological: fault detection in multirobot systems. Bioinspiration & Biomimetics, 10 (1), [016014]. (doi:10.1088/1748-3190/10/1/016014).

Tarapore, Danesh and Mouret, Jean-Baptiste (2015) Evolvability signatures of generative encodings: Beyond standard performance benchmarks. Information Sciences, 313, 43-61. (doi:10.1016/j.ins.2015.03.046).

Cully, Antoine, Clune, Jeff, Tarapore, Danesh and Mouret, Jean-Baptiste (2015) Robots that can adapt like animals. Nature, 521 (7553), 503-507. (doi:10.1038/nature14422).

Tarapore, Danesh, Clune, Jeff, Cully, Antoine and Mouret, Jean-Baptiste (2016) How do different encodings influence the performance of the MAP-Elites algorithm? In GECCO '16 Proceedings of the 2016 on Genetic and Evolutionary Computation Conference. ACM. pp. 173-180 . (doi:10.1145/2908812.2908875).

Gomez, Gabriel, Lungarella, Max and Tarapore, Danesh (2006) Information-theoretic approach to embodied category learning. In Artificial Life X: Proceedings of the Tenth International Conference on the Simulation and Synthesis of Living Systems. MIT Press. pp. 332-337 .

Tarapore, Danesh, Lungarella, Max and Gómez, Gabriel (2004) Fingerprinting agent-environment interaction via information theory. In The Eighth International Conference on Intelligent Autonomous Systems (IAS-8). pp. 512-520 .

Tarapore, Danesh, Floreano, Dario and Keller, Laurent (2006) Influence of the level of polyandry and genetic architecture on division of labour. Rocha, Luis Mateus, Yaeger, Larry S., Bedau, Mark A., Floreano, Dario, Goldstone, Robert L. and Vespignani, Alessandro (eds.) In Artificial Life X: Proceedings of the Tenth International Conference on the Simulation and Synthesis of Living Systems. MIT Press. pp. 358-364 .

Tarapore, Danesh, Lima, Pedro U, Carneiro, Jorge and Christensen, Anders Lyhne (2014) Optimizing the crossregulation model for scalable abnormality detection. In Artificial Life 14: Proceedings of the Fourteenth International Conference on the Simulation and Synthesis of Living Systems. MIT Press..

Lichocki, Pawel, Tarapore, Danesh, Keller, Laurent and Floreano, Dario (2012) Limitations of response thresholds models of division of labor. Adami, Cristoph, Bryson, David M., Ofria, Charles and Pennock, Robert T. (eds.) In Artificial Life 13: Proceedings of the Thirteenth International Conference on the Simulation and Synthesis of Living Systems. MIT Press. pp. 561-562 .

O’Keeffe, James, Tarapore, Danesh, Millard, Alan G and Timmis, Jon (2017) Towards fault diagnosis in robot swarms: an online behaviour characterisation approach. In Conference Towards Autonomous Robotic Systems. vol. 10454, Springer. pp. 393-407 . (doi:10.1007/978-3-319-64107-2_31).

Tarapore, Danesh, Christensen, Anders Lyhne and Timmis, Jon (2017) Generic, scalable and decentralized fault detection for robot swarms. PLoS ONE, 12 (8), [e0182058]. (doi:10.1371/journal.pone.0182058).

O'Keeffe, James, Tarapore, Danesh, Millard, Alan G. and Timmis, Jon (2017) Fault diagnosis in robot swarms: an adaptive online behaviour characterisation approach. In 2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Proceedings. vol. 2018-January, Institute of Electrical and Electronics Engineers Inc. pp. 1-8 . (doi:10.1109/SSCI.2017.8280891).

O'Keeffe, James, Tarapore, Danesh, Millard, Alan G. and Timmis, Jonathan (2018) Adaptive online fault diagnosis in autonomous robot swarms. Frontiers in Robotics and AI, 5, [131]. (doi:10.3389/frobt.2018.00131).

Tarapore, Danesh, Timmis, Jon and Christensen, Anders Lyhne (2019) Fault detection in a swarm of physical robots based on behavioral outlier detection. IEEE Transactions on Robotics, 35 (6), 1516-1522. (doi:10.1109/TRO.2019.2929015).

Capezzuto, Luca, Tarapore, Danesh and Ramchurn, Sarvapali (2020) Anytime and efficient coalition formation with spatial and temporal constraints. In Proceedings of the European Conference on Multi-Agent Systems (EUMAS) 2020.

Bossens, David, Mouret, Jean-Baptiste and Tarapore, Danesh (2020) Learning behaviour-performance maps with meta-evolution. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO) 2020. 10 pp .

Tarapore, Danesh, Gross, Roderich and Zauner, Klaus-Peter (2020) Sparse robot swarms: Moving swarms to real world applications. Frontiers in Robotics and AI. (doi:10.3389/frobt.2020.00083). (In Press)

Contact

Share this profile FacebookTwitterWeibo