Mitchell Cohen

DECAR Group, McGill University

prof_pic.jpg

I am completing my Ph.D in robotic perception at McGill University under the supervision of Professor James Forbes in the DECAR research group. Broadly, my research interests are in the areas of robotic state estimation, simulatenous localization and mapping (SLAM), computer vision, and optimization, with a focus on improving navigation techniques for robots. My current research focuses on the fusion of camera and inertial data to perform SLAM. Specifically, I am interested in exploring how the use of semantic information can be used within visual-inertial SLAM pipelines.

I also recieved a Master’s in Mechanical Engineering in 2020 from McGill University, where I focused on developing novel control and state estimation algorithms for both fixed-wing and multirotor UAVs.

selected publications

  1. IROS
    navlie: A Python Package for State Estimation on Lie Groups
    Charles Champagne Cossette, Mitchell Cohen, Vassili Korotkine, and 3 more authors
    In 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2023
  2. RA-L/IROS
    Know What You Don’t Know: Consistency in Sliding Window Filtering with Unobservable States Applied to Visual-Inertial SLAM
    Daniil Lisus, Mitchell Cohen, and James Richard Forbes
    IEEE Robotics and Automation Letters, 2023
  3. RA-L/IROS
    Finite-Horizon LQR Control of Quadrotors on SE_2 (3)
    Mitchell R Cohen, Khairi Abdulrahim, and James Richard Forbes
    IEEE Robotics and Automation Letters, 2020