S2L-SLAM: Sensor Fusion Driven SLAM using Sonar, LiDAR and Deep Neural Networks
Authors:
- 31 October 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Abstract
The use of different modalities improves the perception of the environment in situations where the conventional sensors fail (camera and LiDAR). The inclusion of these modalities, such as sonar or radar, is however difficult as existing methods for the conventional sensors usually do not generalise well on these different environment representations. We experiment with a modality prediction method to keep using the existing methodologies and allow to separate the sensing system from the navigation stack of an autonomous agent. In previous work, we used a convolutional stacked autoencoder to predict LiDAR point cloud data using the data from our 3D in-air acoustic ultrasonic sensor (eRTIS). In this paper, we investigate the usability of the predicted data in off-the-shelf algorithms to safely navigate environments where visual modalities become unreliable and less accurate.Keywords
This publication has 13 references indexed in Scilit:
- See through smoke2020
- A Review of Visual-LiDAR Fusion based Simultaneous Localization and MappingSensors, 2020
- LiDAR and Camera Sensor Fusion for 2D and 3D Object Detection2019
- eRTIS: A Fully Embedded Real Time 3D Imaging Sonar Sensor for Robotic Applications2019
- Drones: Augmenting Our Quality of LifeIEEE Potentials, 2019
- Introducing Industry 4.02016
- Real-time loop closure in 2D LIDAR SLAM2016
- Hector Open Source Modules for Autonomous Mapping and Navigation with Rescue Robots2014
- Are we ready for autonomous driving? The KITTI vision benchmark suite2012
- Improved Techniques for Grid Mapping With Rao-Blackwellized Particle FiltersIEEE Transactions on Robotics, 2007