Hongyu Li (李鸿宇)


Welcome! I’m an incoming Ph.D. student in Computer Science at Brown University. I work with Prof. Srinath Sridhar at Interactive 3D Vision & Learning Lab.

I completed my Master’s degree at Northeastern University, where I conducted research on topics related to robot perception and navigation with the guidance of Prof. Huaizu Jiang and Prof. Taskin Padir.

During the period of 2022 to 2023, I had the opportunity to intern as a researcher at Honda Research Institute (HRI). Throughout my internships at HRI, my research primarily focused on visuotactile manipulation perception. I had the privilege of being supervised by Dr. Nawid Jamali and Dr. Soshi Iba.

My research interests revolve around the convergence of computer vision, machine learning, and robotics, particularly in the field of robot perception. Perception plays a crucial role in various robotics domains, and I am currently focused on developing accurate and efficient models for environment and object interaction.

I hold a Bachelor’s degree in Computer Science and Economics (dual major) from Rensselaer Polytechnic Institute.


May 15, 2023 I receive a $1,300 RAS travel grant for ICRA 2023.
Apr 17, 2023 I will present our work in progress, StereoNavNet: Learning to Navigate using Stereo Camera with Auxiliary Occupancy Voxels, at CVPR 2023 3D Vision and Robotics in Vancouver :canada:.
Apr 14, 2023 I completed my M.S thesis defense on “Toward Efficient Stereo-based Obstacle Detection Using Deep Neural Network”.
Jan 16, 2023 Our work StereoVoxelNet is accepted to ICRA 2023. See you in London :uk:!
Jul 1, 2022 Our paper is accepted to IROS 2022. Kudos to Unver!

Selected Publications

  1. hie.gif
    StereoVoxelNet: Real-Time Obstacle Detection Based on Occupancy Voxels from a Stereo Camera Using Deep Neural Networks
    Hongyu Li, Zhengang Li, Neset Unver AkmandorHuaizu JiangYanzhi Wang, and Taskin Padir
    In IEEE International Conference on Robotics and Automation (ICRA), 2023
    Presented at IROS 2022 Agile Robotics Workshop in Kyoto, Japan :jp:.
  2. tentabot.gif
    Deep Reinforcement Learning based Robot Navigation in Dynamic Environments using Occupancy Values of Motion Primitives
    Neset Unver AkmandorHongyu LiGary Lvov, Eric Dusel, and Taskin Padir
    In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022