Riku Murai

I'm 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

Image of SAFER-Splat: Safety with Control Barrier Functions in Online Gaussian Splatting Maps
Image of PixRO: Pixel-Distributed Rotational Odometry with Gaussian Belief Propagation
Image of Gaussian Splatting SLAM
Gaussian Splatting SLAM (Highlight & Best Demo Award)
Conference on Computer Vision and Pattern Recognition (CVPR), 2024
(*equal contribution)
Image of Distributed Simultaneous Localisation and Auto-Calibration using Gaussian Belief Propagation
Image of A Robot Web for Distributed Many-Device Localisation
Image of Distributing Collaborative Multi-Robot Planning With Gaussian Belief Propagation
Image of Cain: Automatic Code Generation for A Simultaneous Convolutional Kernels on A Focal-plane Sensor-processors
Image of PathBench: A Benchmarking Platform for Classical and Learned Path Planning Algorithms
Image of BIT-VO: Visual Odometry at 300 FPS using Binary Features from the Focal Plane
BIT-VO: Visual Odometry at 300 FPS using Binary Features from the Focal Plane
Conference on Intelligent Robots and Systems (IROS), 2020
Image of AnalogNet: Convolutional Neural Network Inference on Analog Focal Plane Sensor Processors