Riku Murai
I am a PostDoc at Imperial College London, working on distributed many-device optimisation, low-power unconventional sensing, and 3D scene representation for SLAM.
Before that, I was a PhD student jointly supervised by Prof. Paul H. J. Kelly and Prof. Andrew J. Davison, and during my PhD, I was a research scientist intern at Meta, Embodied AI team within FAIR.
Publications
"Gaussian Splatting SLAM" (Highlight)
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024
(*equal contribution)
"Distributing Collaborative Multi-Robot Planning With Gaussian Belief Propagation"
IEEE Robotics and Automation Letters, 2023
"Cain: Automatic Code Generation for A Simultaneous Convolutional Kernels on A Focal-plane Sensor-processors"
Languages and Compilers for Parallel Computing, 2022
An extended version is published in Autonomous Robots, 2022, paper
"PathBench: A Benchmarking Platform for Classical and Learned Path Planning Algorithms" (Best Robotics Paper)
Conference on Robot and Vision, 2021
An extended version is published in Advanced Robotics, 2022, paper
"BIT-VO: Visual Odometry at 300 FPS using Binary Features from the Focal Plane"
Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems (IROS), 2020
An extended version is published in Autonomous Robots, 2023, paper
"AnalogNet: Convolutional Neural Network Inference on Analog Focal Plane Sensor Processors"
arXiv preprint arXiv:2006.01765, 2020