no code implementations • 8 Apr 2024 • Mikael Skog, Oleksandr Kotlyar, Vladimír Kubelka, Martin Magnusson
The CNN is trained to distinguish between the background and person classes based on a series of 2D projections of the 4D radar data that include the elevation, azimuth, range, and Doppler velocity dimensions.
no code implementations • 19 Mar 2024 • Shuo Sun, Malcolm Mielle, Achim J. Lilienthal, Martin Magnusson
We propose a dense RGBD SLAM system based on 3D Gaussian Splatting that provides metrically accurate pose tracking and visually realistic reconstruction.
no code implementations • 26 Oct 2023 • Shih-Min Yang, Martin Magnusson, Johannes A. Stork, Todor Stoyanov
We solve this problem by learning a sequence of actions that utilize the environment to change the object's pose.
2 code implementations • IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2021 • Daniel Adolfsson, Martin Magnusson, Anas Alhashimi, Achim J. Lilienthal, Henrik Andreasson
This paper presents the accurate, highly efficient, and learning-free method CFEAR Radarodometry for large-scale radar odometry estimation.
Ranked #1 on Radar odometry on Oxford Radar RobotCar Dataset
1 code implementation • 19 Apr 2020 • Tomasz Piotr Kucner, Stephanie Lowry, Martin Magnusson, Achim J. Lilienthal
Our experiments demonstrate that (1) the application of ROSE for decluttering can substantially improve structural feature retrieval (e. g., walls) in cluttered environments, (2) ROSE can successfully distinguish between clutter and structure in the map even with substantial amount of noise and (3) ROSE can numerically assess the amount of structure in the map.
Robotics Functional Analysis
no code implementations • 4 Mar 2020 • Li Sun, Daniel Adolfsson, Martin Magnusson, Henrik Andreasson, Ingmar Posner, Tom Duckett
More importantly, the Gaussian method (i. e. deep probabilistic localisation) and non-Gaussian method (i. e. MCL) can be integrated naturally via importance sampling.
1 code implementation • 28 Sep 2017 • Malcolm Mielle, Martin Magnusson, Achim J. Lilienthal
We present a method for segmenting maps from different modalities, focusing on robot built maps and hand-drawn sketch maps, and show better results than state of the art for both types.
Robotics
1 code implementation • 16 Feb 2017 • Malcolm Mielle, Martin Magnusson, Henrik Andreasson, Achim J. Lilienthal
Experiments in an office environment show that we can handle up to 70% of wrong correspondences and still get the expected result.
Robotics