Matthew Lisondra

University of Toronto, Toronto Metropolitan University

Papers

Total Citations

H-Index

About

Matthew Lisondra is a rising researcher at the forefront of embodied AI and efficient robotic perception. His work bridges two critical frontiers: integrating large-scale foundation models into physical robots, and developing ultra-low-power vision systems for autonomous navigation. In his highly cited 2026 systematic review, Lisondra provides the first comprehensive synthesis of how Large Language Models, Vision-Language Models, and Vision-Language-Action models are revolutionizing mobile service robotics—a seminal roadmap that has already garnered 3 citations. Complementing this theoretical work, his 2024 paper on BIT-VIO introduces a breakthrough in visual-inertial odometry using Focal-Plane Sensor-Processor Arrays (FPSPs). By executing vision algorithms directly on the image sensor at the pixel level, this system achieves high-frame-rate processing while consuming minimal power—a critical advance for resource-constrained robots. With both papers already shaping the field, Lisondra’s dual expertise in foundation-model integration and efficient on-sensor computation positions him as a key architect of the next generation of intelligent, energy-aware autonomous systems.