Max Robotics — Global Service Robot Directory + US Certification

About

Mark Edgington’s research career has centered on advancing the capabilities of legged and mobile robots through innovative motion modeling, sensor systems, and evolutionary learning techniques. His most significant contribution is the development of the Dynamic Gaussian Mixture Model (DGMM), a novel motion model representation that reduces the manual effort required to build accurate motion models for complex robotic systems, as detailed in his 2009 paper (7 citations). Edgington also pioneered multi-ultrasonic-sensor systems for echolocation-based SLAM on open-source platforms like the Kobuki Turtlebot, integrating ROS to create accessible, repeatable testbeds for robotics research. His work on evolving walking patterns for kinematically complex robots using evolution strategies (2008, 4 citations) and on general frameworks for encoding and evolving neural networks (2007, 5 citations) demonstrates a sustained focus on bio-inspired and adaptive control. Additionally, his exploration of sensorimotor coordination for object recognition (2007, 2 citations) highlights a commitment to learning through interaction. Though his citation counts are modest, Edgington’s contributions to open-source robotics infrastructure and foundational motion modeling have provided practical tools and frameworks that support broader advances in autonomous systems.