The body and soul of any research lab is its portfolio of research projects. Our projects are grouped into seven topic areas corresponding to MERL's seven research groups.

Computer Vision

Processing data from across space and time to extract meaning and build representations of objects and events in the world. Detection, classification, and recognition based on machine learning and physical modeling; 3D reconstruction, location, and inference; computational imaging for optimized information capture; Dictionary Learning for signal processing; tracking; and multi-modal sensor integration. Adaptively-sampled distance fields-based methods in various domains ranging from font rendering to NC milling simulation.

Data Analytics

Learning and optimization algorithms that can be applied to electrical power systems, various transportation systems (trains, elevators, cars), heating, ventilation, and air conditioning (HVAC) systems and solutions, and factory automation. The application of these algorithms minimizes costs, increases reliability, improves energy efficiency, and reduces environmental impact of products.

Speech & Audio

Machine learning for estimation and inference problems in speech and audio processing, including end-to-end speech recognition and enhancement, acoustic modeling and analysis, statistical dialog systems, as well as natural language understanding and adaptive multimodal interfaces.

Signal Processing

Acquisition, representation, and processing of signals with an emphasis on wireless/optical communications and associated devices, computational sensing, radar processing and statistical inference. Application areas include: terrestrial and trans-oceanic optical networks, train and automotive connectivity and electronics, energy storage systems, RF power amplifiers, RF sensing systems for security, infrastructure and building monitoring.

Control & Dynamical Systems

If it moves, we control it: Advanced control algorithms, model predictive control, estimation, nonlinear dynamical systems, system-level dynamic modeling and analysis, mechatronic co-design, thermo-fluid system dynamics, with applications to automotive mechatronics, factory automation, elevators, space systems, motors, trains, and HVAC.

Multi-Physical Systems & Devices

Research on multi-physical modeling & simulations as a basis for producing model-based design for devices, systems and controls to achieve optimized performance with high efficiency. Target applications include HVAC systems, factory automation, robotics, electrical motors, power amplifier devices, superconductors, and nano-particles for future magnetic particle imaging.