A5039277979- Robotics and Sensor-Based Localization
- Robotic Path Planning Algorithms
- Robotics and Automated Systems
- 3D Surveying and Cultural Heritage
- Video Surveillance and Tracking Methods
- Distributed Control Multi-Agent Systems
- Underwater Vehicles and Communication Systems
- Advanced Vision and Imaging
- Advanced Neural Network Applications
- Advanced Image and Video Retrieval Techniques
- Remote Sensing and LiDAR Applications
- Adaptive Control of Nonlinear Systems
- Power Line Inspection Robots
- Modular Robots and Swarm Intelligence
- UAV Applications and Optimization
- Anomaly Detection Techniques and Applications
- Indoor and Outdoor Localization Technologies
- Industrial Vision Systems and Defect Detection
- Advanced Control Systems Optimization
- Reinforcement Learning in Robotics
- Image Enhancement Techniques
- Advanced Optical Sensing Technologies
- Robot Manipulation and Learning
- Machine Learning and Data Classification
- Planetary Science and Exploration
Luleå University of Technology
2016-2025
Xi'an University of Technology
2022
ORCID
2021
During last decade the scientific research on Unmanned Aerial Vehicless (UAVs) increased spectacularly and led to design of multiple types aerial platforms. The major challenge today is development autonomously operating agents capable completing missions independently human interaction. To this extent, visual sensing techniques have been integrated in control pipeline UAVs order enhance their navigation guidance skills. aim article present a comprehensive literature review vision based...
This paper presents and discusses algorithms, hardware, software architecture developed by the TEAM CoSTAR (Collaborative SubTerranean Autonomous Robots), competing in DARPA Subterranean Challenge. Specifically, it techniques utilized within Tunnel (2019) Urban (2020) competitions, where achieved 2nd 1st place, respectively. We also discuss CoSTAR's demonstrations Martian-analog surface subsurface (lava tubes) exploration. The introduces our autonomy solution, referred to as NeBula...
Abstract This work establishes COMPRA, a compact and reactive autonomy framework for fast deployment of Micro Aerial Vehicles (MAVs) in subterranean Search-and- Rescue (SAR) missions. A COMPRA-enabled MAV is able to autonomously explore previously unknown areas while specific mission criteria are considered e.g. an object interest identified localized, the remaining useful battery life, overall desired exploration duration. The proposed architecture follows low-complexity algorithmic design...
This work presents a field-hardened autonomous multimodal legged-aerial robotic system for subterranean exploration, extending legged robot to be the carrier of an aerial platform capable rapid deployment in search-and-rescue scenarios. The driving force developing such configurations are requirements large-scale and long-term missions, where payload capacity long battery life is combined integrated with agile motion agent. structured around quadruped Boston Dynamics Spot, enhanced custom...
This paper presents and discusses algorithms, hardware, software architecture developed by the TEAM CoSTAR (Collaborative SubTerranean Autonomous Robots), competing in DARPA Subterranean Challenge. Specifically, it techniques utilized within Tunnel (2019) Urban (2020) competitions, where achieved second first place, respectively. We also discuss CoSTAR’s demonstrations Martian-analog surface subsurface (lava tubes) exploration. The introduces our autonomy solution, referred to as NeBula...
Loop closure detection in large-scale and long-term missions can be computationally demanding due to the need identify, verify, process numerous candidate pairs establish edge connections for pose graph optimization. Keyframe sampling mitigates this by reducing number of frames stored processed back-end system. In article, we address gap optimized keyframe combined problem optimization loop detection. Our Minimal Subset Approach (MSA) employs an strategy with two key factors, redundancy...
ABSTRACT This article presents the first ever fully autonomous UAV (Unmanned Aerial Vehicle) mission to perform gas measurements after a real blast in an underground mine. The demonstration was deployed around 40 min took place, and as such realistic levels were measured. We also present multiple field robotics experiments different mines detailing development process. presented novel autonomy stack, denoted Routine Inspection Autonomy (RIA) framework, combines risk‐aware 3D path planning ,...
Loop closure detection in large-scale and long-term missions can be computationally demanding due to the need identify, verify, process numerous candidate pairs establish edge connections for pose graph optimization. Keyframe sampling mitigates this by reducing number of frames stored processed back-end system. In article, we address gap optimized keyframe combined problem optimization loop detection. Our Minimal Subset Approach (MSA) employs an strategy with two key factors, redundancy...
Typical LiDAR SLAM architectures feature a front-end for odometry estimation and back-end refining optimizing the trajectory map, commonly through loop closures. However, closure detection in large-scale missions presents significant computational challenges due to need identify, verify, process numerous candidate pairs pose graph optimization. Keyframe sampling bridges by selecting frames storing processing during global This article proposes an online keyframe approach that constructs...
A reliable odometry source is a prerequisite to enable complex autonomy behaviour in next-generation robots operating extreme environments. In this work, we present high-precision lidar system achieve robust and real-time operation under challenging perceptual conditions. LOCUS (Lidar Odometry for Consistent Uncertain Settings), provides an accurate multi-stage scan matching unit equipped with health-aware sensor integration module seamless fusion of additional sensing modalities. We...
Micro Aerial Vehicles (MAVs) navigation in subterranean environments is gaining attention the field of aerial robotics, however there are still multiple challenges for collision free such harsh environments. This article proposes a novel baseline solution with Nonlinear Model Predictive Control (NMPC). In proposed method, MAV considered as floating object, where velocities on x, y axes and position altitude references NMPC to navigate along tunnel, while avoids by considering kinematics...
This article presents a dataset collected from the subterranean (SubT) environment with current state-of-the-art sensors required for autonomous navigation. The includes sensor measurements RGB, RGB-D, event-based and thermal cameras, 2D 3D lidars, inertial measurement unit (IMU), ultra wideband (UWB) positioning systems which are mounted on mobile robot. overall setup will be referred further in as data collection platform. contains synchronized raw all robot operating system (ROS) message...
In this article, we propose a planning algorithm for coverage of complex structures with network robotic sensing agents, multi-robot surveillance missions as our main motivating application. The sensors are deployed to monitor the external surface 3D structure. controls motion each sensor so that measure collective attained by is nondecreasing, while converge an equilibrium configuration. A modified version also provided introduce collision avoidance properties. effectiveness demonstrated in...
In this article an evaluation of current technology on visual localization systems for underground mining is presented. The proposed study considered to be the first step among others towards enabling vision-based mine inspection using Unmanned Micro Aerial Vehicles (UAVs). Furthermore, aim article, verify applicable and reliable low cost existing methods technologies problem UAV in harsh challenging environments. More specifically field trials were performed one biggest mines Europe, iron...
The aim of this article is to present a novel four-degree-of-freedom aerial manipulator allowing multirotor Unmanned Aerial Vehicle (UAV) physically interact with the environment. proposed design, named CARMA (Compact AeRial MAnipulator), characterized by low disturbances on UAV flight dynamics, extended workspace (with regard its retracted configuration) and fast dynamics (compared dynamics). dynamic model formulated control structure consisting an inverse kinematics algorithm independent...
This article presents a Convolutional Neural Network (CNN) method to enable autonomous navigation of low-cost Micro Aerial Vehicle (MAV) platforms along dark underground mine environments. The proposed CNN component provides online heading rate commands for the MAV by utilising image stream from on-board camera, thus allowing platform follow collision-free path tunnel axis. A novel part developed consists generation data-set used training CNN. More specifically, inspired single haze removal...
The usage of Micro Aerial Vehicles (MAVs) is rapidly emerging in the mining industry to increase overall safety and productivity. However, mine environment especially challenging for MAV's operation due lack illumination, narrow passages, wind gusts, dust, other factors that can affect flying capability. This article presents a method assist navigation MAVs by using from field Deep Learning (DL), while considering low-cost platform without high-end sensor suits. presented DL scheme be...
In this letter, a floating robotic emulation platform is presented with an autonomous maneuverability for virtual demonstration of satellite motion. Such design characterized by its friction-less, levitating, yet planar motion over hyper-smooth surface. The the platform, integrated sensor and actuator units, briefly described, including related component specification along mathematical model, describing dynamic Additionally, article establishes nonlinear optimal control architecture...