An Adversarial Approach to Private Flocking in Mobile Robot Teams
- 17 January 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 5 (2), 1009-1016
- https://doi.org/10.1109/lra.2020.2967331
Abstract
Privacy is an important facet of defence against adversaries. In this letter, we introduce the problem of private flocking. We consider a team of mobile robots flocking in the presence of an adversary, who is able to observe all robots' trajectories, and who is interested in identifying the leader. We present a method that generates private flocking controllers that hide the identity of the leader robot. Our approach towards privacy leverages a data-driven adversarial co-optimization scheme. We design a mechanism that optimizes flocking control parameters, such that leader inference is hindered. As the flocking performance improves, we succes- sively train an adversarial discriminator that tries to infer the identity of the leader robot. To evaluate the performance of our co-optimization scheme, we investigate different classes of reference trajectories. Although it is reasonable to assume that there is an inherent trade-off between flocking performance and privacy, our results demonstrate that we are able to achieve high flocking performance and simultaneously reduce the risk of revealing the leader.Keywords
Funding Information
- Centre for Digital Built Britain (RG96233)
- Engineering and Physical Sciences Research Council (EP/S015493/1)
- Mitacs Globalink Research
- Natural Sciences and Engineering Council of Canada
This publication has 32 references indexed in Scilit:
- A survey of multi-agent formation controlAutomatica, 2015
- Unifying microscopic flocking motion models for virtual, robotic, and biological flock membersAutonomous Robots, 2013
- On the Value of Ignorance: Balancing Tracking and Privacy Using a Two-Bit SensorPublished by Springer Science and Business Media LLC ,2009
- Self-organized flocking in mobile robot swarmsSwarm Intelligence, 2008
- Distributed coordination architecture for multi-robot formation controlRobotics and Autonomous Systems, 2008
- Flocking for Multi-Agent Dynamic Systems: Algorithms and TheoryIEEE Transactions on Automatic Control, 2006
- Modeling and control of formations of nonholonomic mobile robotsIEEE Transactions on Robotics and Automation, 2001
- Control of mobile platforms using a virtual vehicle approachIEEE Transactions on Automatic Control, 2001
- Behavior-based formation control for multirobot teamsIEEE Transactions on Robotics and Automation, 1998
- Flocks, herds and schools: A distributed behavioral modelPublished by Association for Computing Machinery (ACM) ,1987