Max Robotics — Global Service Robot Directory + US Certification

About

Anton Mitrokhin is a pioneering researcher at the intersection of neuromorphic computing, event-based vision, and robotic perception. His work focuses on leveraging novel sensing technologies — particularly event cameras like the Dynamic Vision Sensor (DVS) — to enable robots and autonomous systems to perceive and interact with their environments more efficiently and intelligently. Mitrokhin's most influential contribution, "Learning Sensorimotor Control with Neuromorphic Sensors" (2019, 112 citations), advances the concept of active perception by tightly coupling a robot's sensory inputs with its motor actions using hyperdimensional computing frameworks. This work represents a significant departure from traditional pipelines that treat sensing and actuation as separate processes. Equally impactful is his development of EV-IMO (97 citations), the first event-based dataset and learning pipeline for motion segmentation in indoor scenes, providing the research community with a critical benchmark for evaluating event-driven algorithms. His earlier unsupervised learning approaches for estimating dense optical flow, depth, and egomotion from sparse event data (totaling 60 combined citations) further cemented his reputation as an innovator in low-level event-based vision. Collectively, Mitrokhin's research has meaningfully shaped how the robotics and computer vision communities think about neuromorphic sensing and real-time scene understanding.