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 statistical inference, estimation, computational sensing, radar processing and wireless/optical communications. Application areas include: train and automotive connectivity, Lidar, RF sensing systems for security, vehicular radar, energy storage systems, infrastructure and building monitoring, and wireless and optical communication networks.

Control for Autonomy

Enabling autonomy in automotive, space, robotics, and mechatronics systems by research in control, estimation, motion planning, optimization and dynamics for model-based and data-driven frameworks.

Multi-physics & Dynamics

Applied Physics for multi-physical modeling, design optimization, control and performance monitoring/diagnosis of devices, components and electric systems. Target applications include novel GaN devices, RF circuits, magnetic-based equipment, motors and other electric machines. Other areas of study include fluid dynamics of airflow and traffic dynamical systems with applications focusing on HVAC, wind and weather LiDAR, satellite orbit and traffic control.

Multi-physical Systems

Research multi-physical modeling methodology, develop and use models for simulation, analysis, control, and optimization of large-scale systems that manifest interactions between the thermal, fluid, electrical, and mechanical domains. Target applications include HVAC systems, factory automation and robotics.