A5043644928- Logic, Reasoning, and Knowledge
- Semantic Web and Ontologies
- AI-based Problem Solving and Planning
- Robotic Path Planning Algorithms
- Robotics and Sensor-Based Localization
- Multi-Agent Systems and Negotiation
- Rough Sets and Fuzzy Logic
- Logic, programming, and type systems
- Advanced Database Systems and Queries
- Constraint Satisfaction and Optimization
- Data Management and Algorithms
- Advanced Algebra and Logic
- Formal Methods in Verification
- UAV Applications and Optimization
- Advanced Vision and Imaging
- Reinforcement Learning in Robotics
- Advanced Image and Video Retrieval Techniques
- 3D Surveying and Cultural Heritage
- Bayesian Modeling and Causal Inference
- Mobile Ad Hoc Networks
- Video Surveillance and Tracking Methods
- Natural Language Processing Techniques
- Modular Robots and Swarm Intelligence
- Target Tracking and Data Fusion in Sensor Networks
- Optimization and Search Problems
Linköping University
2014-2025
Mahasarakham University
2023-2025
Zhuhai Institute of Advanced Technology
2019-2021
Jinan University
2019-2021
University of Manchester
2020
Letterkenny Institute of Technology
2020
University of Warsaw
2000
Recent advances in the field of Unmanned Aerial Vehicles (UAVs) make flying robots suitable platforms for carrying sensors and computer systems capable performing advanced tasks. This paper presents a technique which allows detecting humans at high frame rate on standard hardware onboard an autonomous UAV real-world outdoor environment using thermal color imagery. Detected human positions are geolocated map points interest is built. Such saliency can, example, be used to plan medical supply...
The aim of this paper is to explore the possibility using geo-referenced satellite or aerial images augment an Unmanned Aerial Vehicle (UAV) navigation system in case GPS failure. A vision based which combines inertial sensors, visual odometer and registration a UAV on-board video given image has been developed tested on real flight-test data. experimental results show that it possible extract useful position information from imagery even when flying at low altitude. It shown such can be...
This paper investigates the possibility of augmenting an Unmanned Aerial Vehicle (UAV) navigation system with a passive video camera in order to cope long-term GPS outages. The proposes vision-based architecture which combines inertial sensors, visual odometry, and registration on-board geo-referenced aerial image. vision-aided developed is capable providing high-rate drift-free state estimation for UAV autonomous without system. Due use image-to-map absolute position calculation,...
The goal of the paper is to present foreseen research activity European project "SHERPA" whose activities will start officially on February 1th 2013. SHERPA develop a mixed ground and aerial robotic platform support search rescue in real-world hostile environment, like alpine scenario that specifically targeted project. Looking into technological rescuing scenario, we plan address number topics about cognition control. What makes potentially very rich from scientific viewpoint heterogeneity...
The emerging area of intelligent unmanned aerial vehicle UAV research has shown rapid development in recent years and offers a great number challenges for artificial intelligence. For both military civil applications, there is desire to develop more sophisticated platforms where the emphasis placed on capabilities. Imagine mission scenario supplied with 3D model region containing buildings road structures instructed fly an arbitrary building collect video streams each building's respective...
TALplanner is a forward-chaining planner that utilizes domain-dependent knowledge to control search in the state space generated by action invocation. The knowledge, background plans, and goals are all represented using formulas temporal logic called tal, which has been developed independently as formalism for specifying agent narratives reasoning about them. In Fifth International Artificial Intelligence Planning Scheduling Conference planning competition, exhibited impressive performance,...
An implemented system for achieving high level situation awareness about traffic situations in an urban area is described. It takes as input sequences of color and thermal images which are used to construct maintain qualitative object structures recognize the behavior tracked vehicles real time. The tested both simulation on data collected during test flights. To facilitate signal symbol transformation easy integration streams from sensors with GIS chronicle recognition system, DyKnow, a...
An important use of unmanned aerial vehicles is surveillance distant targets, where sensor information must quickly be transmitted back to a base station. In many cases, high uninterrupted bandwidth requires line-of-sight between sender and transmitter minimize quality degradation. Communication range typically limited, especially when smaller UAVs are used. Both problems can solved by creating relay chains for single target, trees simultaneous multiple targets. this paper, we show how such...
When unmanned aerial vehicles (UAVs) are used for surveillance, information must often be transmitted to a base station in real time. However, limited communication ranges and the common requirement of free line sight may make direct transmissions from distant targets impossible. This problem can solved using relay chains consisting one or more intermediate UAVs. leads positioning such relays given known obstacles, while taking into account possibly mission-specific quality measure. The...
Modern optimization-based approaches to control increasingly allow automatic generation of complex behavior from only a model and an objective. Recent years has seen growing interest in fast solvers also real-time operation on robots, but the computational cost such trajectory optimization remains prohibitive for many applications. In this paper we examine novel deep neural network approximation validate it safe navigation problem with real nano-quadcopter. As risk costly failures is major...
Robots are increasingly expected to move out of the controlled environment research labs and into populated streets workplaces. Collision avoidance in such cluttered dynamic environments is increasing importance as robots gain more autonomy. However, efficient fundamentally difficult since computing safe trajectories may require considering both dynamics uncertainty. While heuristics often used practice, we take a holistic stochastic trajectory optimization perspective that merges collision...
This paper proposes an image matching system using aerial images, captured in flight time, and geo-referenced images to estimate the Unmanned Aerial Vehicle (UAV) position a situation of Global Navigation Satellite System (GNSS) failure. The is based on edge detection posterior automatic registration these edge-images (position estimation UAV). process performed by Artificial Neural Network (ANN), with optimal architecture. A comparison Sobel Canny extraction filters also provided. obtained...
Abstract The technique of forgetting in knowledge representation has been shown to be a powerful and useful engineering tool with widespread application. Yet, very little research done on how different policies forgetting, or use operators, affects the inferential strength original theory. goal this paper is define loss functions for measuring changes based intuitions from model counting probability Properties such measures are studied pragmatic proposed computing using well-known...