MIT LIDS | Laboratory for Information & Decision Systems

Upcoming LIDS Events

LIDS Research Highlights

Camera Control for Learning Nonlinear Target Dynamics via Bayesian Non-Parametric Dirichlet-Process Gaussian-Process (DPGP) Models

Mobile sensors are often deployed to cooperatively perform surveillance of an environment and track objects of interest: for example, intrusion detection throughout a secure facility, and anomaly detection in manufacturing plants. In many such cases it is infeasible to provide accurate sensor coverage of the entire environment, and thus an environment model and associated controller that accounts for sensor field-of-view (FoV) geometry is necessary to determine sensor configurations that minimize uncertainty.

Network control: from theory to practice

The performance and control of communication networks can be analyzed using a beautiful theory based on queue stability. This theory gave us the backpressure algorithm firstly proposed by Tassiulas & Ephremides in 1992 [1], whereby packets flow in the data network according to queue backlog differences (a packet always flows from a highly-backlogged node to a neighboring node with smaller backlog). In the context of the ONR project, Prof. Modiano and his group work towards bridging the gap between this control theory and how real networks work.

Approximate Decentralized Bayesian Inference

Recent trends in the growth of datasets, and the methods by which they are collected, have led to increasing interest in the parallelization of machine learning algorithms. Parallelization results in reductions in both the memory usage and computation time of learning, and allows data to be collected and processed by a network of learning agents rather than by a single central agent.