Results 51 to 60 of about 2,064,870 (170)

Indoor UAV for Nuclear Investigation: Experimental Qualification and Field Feedback

Journal of Field Robotics, EarlyView.
ABSTRACT Indoor Unmanned Aerial Vehicles (UAVs) have recently gained interest for inspection and investigation tasks in hazardous environments. In the nuclear field, indoor UAVs offer promising capabilities to reduce workers' exposure to ionizing radiation while accessing confined or elevated areas.
Jérémy Seyssaud, Marie Cuozzo, Julien Favrichon, Benjamin Catania, Eric Cantrel, Tadec Marraine, Jérôme Boch   +6 more
wiley   +1 more source

Visual Odometry using Convolutional Neural Networks [PDF]

, 2017
Visual odometry is the process of tracking an agent\u27s motion over time using a visual sensor. The visual odometry problem has only been recently solved using traditional, non-machine learning techniques.
Fagan, Thomas, Lim, Steffen, McFall, Kevin, PhD., Graves, Alec   +3 more
core   +1 more source

REVIO: Range- and Event-Based Visual-Inertial Odometry for Bio-Inspired Sensors

Biomimetics, 2022
Visual-inertial odometry is critical for Unmanned Aerial Vehicles (UAVs) and robotics. However, there are problems of motion drift and motion blur in sharp brightness changes and fast-motion scenes.
Yingxun Wang, Bo Shao, Chongchong Zhang, Jiang Zhao, Zhihao Cai   +4 more
doaj   +1 more source

FEWT: Frequency‐Enhanced Wavelet‐Based Transformer for Multimodal Wheeled Bimanual Manipulation

SmartBot, EarlyView.
An embodied mobile bimanual robot learns dexterous manipulation skills through imitation learning with multimodal perception. The integration of vision, proprioception, and tactile sensing establishes a comprehensive perception–action loop, enabling the robot to continuously understand, interact with, and adapt to complex physical environments.
Jiaxin Huang, Hanyu Liu, Yunsheng Ma, Jian Shen, Yilin Zheng, Jiayi Wen, Zhigong Song   +6 more
wiley   +1 more source

Improved Multi-Sensor Fusion Dynamic Odometry Based on Neural Networks

Sensors
High-precision simultaneous localization and mapping (SLAM) in dynamic real-world environments plays a crucial role in autonomous robot navigation, self-driving cars, and drone control. To address this dynamic localization issue, in this paper, a dynamic
Lishu Luo, Fulun Peng, Longhui Dong
doaj   +1 more source

Robust Stereo Visual-Inertial Odometry Using Nonlinear Optimization

Sensors, 2019
The fusion of visual and inertial odometry has matured greatly due to the complementarity of the two sensors. However, the use of high-quality sensors and powerful processors in some applications is difficult due to size and cost limitations, and there ...
Shujun Ma, Xinhui Bai, Yinglei Wang, Rui Fang   +3 more
doaj   +1 more source

Geo2DGS‐SLAM: Geometry‐Driven SLAM With 2D Gaussian Splatting

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Recent advances in SLAM systems based on 3D Gaussian Splatting have enabled dense and photorealistic scene reconstruction. However, 3DGS‐based methods still suffer from limited geometric awareness due to the lack of normal rendering support, view inconsistency and weak depth constraints, ultimately hindering high‐fidelity geometric ...
Weiqing Yan, Tianhao Xie, Liang Liao, Wujie Zhou, Chang Tang   +4 more
wiley   +1 more source

Long-range stereo visual odometry for unmanned aerial vehicles [PDF]

, 2015
This thesis explored the utility of long-range stereo visual odometry for application on Unmanned Aerial Vehicles. Novel parameterisations and initialisation routines were developed for the long-range case of stereo visual odometry and new optimisation ...
Warren, Michael David
core  

Deep Reinforcement Learning Based Autonomous Decision‐Making for Cooperative Uncrewed Aerial Vehicles: A Search and Rescue Real World Application

Journal of Field Robotics, Volume 43, Issue 7, Page 4382-4401, October 2026.
ABSTRACT This paper presents the first end‐to‐end framework that combines guidance, navigation, and centralized task allocation for multiple UAVs performing autonomous search‐and‐rescue (SAR) in GNSS‐denied indoor environments. A twin delayed deep deterministic policy gradient controller is trained with an artificial potential field (APF) reward that ...
Thomas Hickling, Maxwell Hogan, Abdulla Tammam, Nabil Aouf   +3 more
wiley   +1 more source

Implementation and experimental verification of a 3D-to-2D Visual Odometry Algorithm for real-time measurements of a vehicle pose [PDF]

, 2022
This work describes the implementation of a software for real-time vehicle pose reconstruction using stereo visual odometry algorithms. We firstly guess motion by a linear 2D-to-3D method solving a PnP problem embedded within a RANSAC process to remove ...
Soldà, Giulia
core