Project Description

Multi-Sensor Multi-Object Tracking and Classification (MSMOTC) systems are networks of agents that measure, track, and classify objects in their environment using one or more sensing modalities, such as visual imagery or radar. Through the exchange and fusion of information between agents, a distributed MSMOTC system can expand sensing coverage and improve estimation accuracy compared to any individual agent, while being inherently robust to individual sensor failures and intermittent communication. Despite these advantages, distributed MSMOTC systems must address additional challenges, such as continuously evolving sensing regions and objectives, highly dynamic network topologies, and significant power and bandwidth constraints.

The objective of this project is to establish novel algorithms for distributed MSMOTC that are robust to information double-counting, are achievable in a communication-constrained network, and distribute information intelligently and judiciously in a highly dynamic network topology. A core component of the research will focus on long-horizon planning under uncertainty, in which agents must make decisions based on partial knowledge of their neighbor’s data.

Project Start Date

09/01/2023

Postdoc Qualifications

• Solid mathematical skills and background in relevant areas, such as networks, estimation, optimization, control, signal processing, or machine learning.
• Passion and interest to solve challenging research problems using methodologies from different areas.
• Excellent communication and writing skills (English).
• Ability to thrive in a collaborative environment.

Co-advisors

Keith LeGrand, klegrand@purdue.edu, School of Aeronautics and Astronautics, https://engineering.purdue.edu/AAE/people/ptProfile?resource_id=272261

Shreyas Sundaram, sundara2@purdue.edu, School of Electrical and Computer Engineering, https://engineering.purdue.edu/~sundara2/
Center for Innovation in Control, Optimization, and Networks (ICON): https://engineering.purdue.edu/ICON

Bibliography

A. Buonviri, M. York, K. LeGrand, and J. Meub. Survey of Challenges in Labeled Random Finite Set Distributed Multi-Sensor Multi-Object Tracking, Proceedings of the 2019 IEEE Aerospace Conference, 2019

H. Wei, K. LeGrand, A. Paradise, and S. Ferrari. Real-Time Communication Control in Decentralized Autonomous Sensor Networks, Journal of Aerospace Information Systems, 2022

A. Mitra, J. A. Richards, and S. Sundaram. A new approach to distributed hypothesis testing and non-Bayesian learning: Improved learning rate and Byzantine resilience. IEEE Transactions on Automatic Control, 66(9), 4084-4100, 2020.

A. Mitra, J. A Richards, S. Bagchi, and S. Sundaram. Resilient distributed state estimation with mobile agents: overcoming Byzantine adversaries, communication losses, and intermittent measurements. Autonomous Robots, 43(3), 743-768, 2019

A. Mitra, J. A. Richards, S. Bagchi, and S. Sundaram. Distributed inference with sparse and quantized communication. IEEE Transactions on Signal Processing, 69, 3906-3921, 2021.