Adaptive Sampling

Being able to estimate and predict information about dynamic processes deepens our understanding of biological, chemical, and physical phenomena in the environment. Often, these dynamic processes exhibit complex, spatio-temporal behaviors. Mobile robots are particularly well-suited to monitor these processes because of their abilities to carry sensors and adapt their sensing locations. Example applications include tracking oil spills in the ocean or pollutant concentrations in air for environmental monitoring, localizing gas leaks for pipeline repair, or tracking forest fire boundaries for search and rescue.  The focus of this work is to develop algorithms that will allow robots and teams of robots to actively, adaptively, and continuously sample and monitor a dynamic spatiotemporal process.

Distributed Tracking of Spatiotemporal Processes with Heterogeneous Multi-Robot Teams

The objective is to develop strategies for a team of heterogeneous mobile robots to adaptively sample and track a dynamic process. We create distributed algorithms, where robots collect sparse sensor measurements, create reduced-order models of the spatiotemporal processes they track, and use these models to estimate field values for areas without sensor measurements of the dynamic process. Heterogeneity in sensing and mobility is encapsulated as multi-scale sensor data or sensing data of varying spatiotemporal fidelity.

A team of four robots tracking dye being dispersed using a submerged grid of counter rotating disks. The dye concentration field was mapped and projected onto the tank using the video from a fluids experiment in an experimental flow tank. Four robots robots then tracked the projected concentration field using our developed distributed algorithm.

Relevant Papers

  • S. Manjanna, M. A. Hsieh, G. Dudek. “Scalable Multi-Robot System for Non-myopic Spatial Sampling,” submitted to Autonomous Robots, Under Review, https://arxiv.org/pdf/2105.10018.
  • T. Salam and M. A. Hsieh. “Heterogeneous robot teams for modeling and prediction of multiscale environmental processes,” submitted to Autonomous Robots, Under Review, https://arxiv.org/pdf/2103.10383.pdf.
  • A. Mansfield, S. Manjanna, D. G. Macharet, and M. A. Hsieh. “Multi-robot Scheduling for Environmental Monitoring as a Team Orienteering Problem,” in the Prof. of the 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2021, pp. 6398-6404, https://doi.org/10.1109/IROS51168.2021.9636854.
  • T. Salam and M. A. Hsieh. “Adaptive Sampling and Reduced Order Modeling of Dynamic Processes by Robot Teams,” in IEEE Robotics and Automation Letters (RA-L), 4(2), Apr 2019, pp. 477-484, https://doi.org/10.1109/LRA.2019.2891475.
  • K. Y. Chee and M. A. Hsieh. “Augmenting Coverage Control with Agent-Environment Dependency for Multi-Robot Systems,” in the Proc. of the 2020 IEEE Symposium on Safety, Security, and Rescue Robotics (SSRR 2020), Nov 2020, Abu Dhabi, UAE (Virtual), https://doi.org/10.1109/SSRR50563.2020.9292628.
  • C8. H. Rovina, T. Salam, Y. Kantaros, and M. A. Hsieh. “Asynchronous Adaptive Sampling and Reduced-Order Modeling of Dynamic Processes by Robot Teams via Intermittently Connected Networks,” in the Prof. of the 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2020), Las Vegas, NV USA (Virtual), https://doi.org/10.1109/IROS45743.2020.9341636.
  • T. Salam, D. Kularatne, E. Forgoston, and M. A. Hsieh. “Adaptive Sampling and Energy Efficient Navigation in Time-Varying Flows,” in Autonomous Underwater Vehicles: Design and Practice, eds. F. Ehlers, The Institution of Engineering and Technology, 2020, eISBN: 978-1-78561-704-1.

Acknowledgement

To come …