Selected Publications

The motivation behind this thesis is to further investigate different approaches for image-based localization. Similarly to PoseNet, we formulate the problem as pose regression and further improve upon it by introducing quaternion algebra for proper attitude representation. In addition, we combine two recently developed approaches: (1) a multi-task loss function that learns the optimal weighting between position and orientation regression tasks, (2) a CNN followed by a spatial LSTM network for better structured feature correlation. Furthermore, we only finetune a small portion of the pretrained CNN feature extractor. Lastly, we extend the problem to videos and employ seq-to-seq regression model based on LSTMs. We evaluate the models on the 7Scenes dataset and introduce a new Airframe dataset, where localization is performed with respect to an object that changes position and orientation in the environment. We achieve at least competitive, but sometimes outperforming results, while requiring considerably less computational power for training the models.
Master Thesis, 2018

Using multiple UAVs as a collaborative swarm is considerably more effective for target tracking, reconnaissance, and surveillance missions because of their capacity to tackle complex problems synergistically. In this paper, we consider the problem of optimizing three objectives for a swarm of UAVs: (1) target detection and tracking, (2) map coverage, and (3) network connectivity. Our approach, Dual-Pheromone Clustering Hybrid Approach (DPCHA), incorporates a multi-hop clustering and a dual-pheromone ant-colony model to optimize these three objectives. Clustering keeps stable overlay networks, while attractive and repulsive pheromones mark areas of detected targets and visited areas. Extensive simulations show that DPCHA produces significant improvements in the assessment of coverage fairness, cluster stability, and connection volatility. Results show an approximately 50% improvement in map coverage compared to the pure dual-pheromone approach.
Best Paper Award at CYBCONF, 2017

Poaching is an illegal activity that remains out of control in many countries. Based on the 2014 report of the United Nations and Interpol, the illegal trade of global wildlife and natural resources amounts to nearly $ 213 billion every year, which is even helping to fund armed conflicts. Poaching activities around the world are further pushing many animal species on the brink of extinction. Unfortunately, the traditional methods to fight against poachers are not enough, hence the new demands for more efficient approaches. In this context, the use of new technologies on sensors and algorithms, as well as aerial platforms is crucial to face the high increase of poaching activities in the last few years. Our work is focused on the use of vision sensors on UAVs for the detection and tracking of animals and poachers, as well as the use of such sensors to control quadrotors during autonomous vehicle following and autonomous landing.
Sensors, 2015

Wireless ad hoc networks consists of autonomous hosts which have equal status within a network. Unlike managed wireless networks, ad hoc networks are decentralized. Each host can participate in routing by forwarding packets. Decentralized nature of ad hoc networks makes them more reliable than managed wireless networks, because failure of one host does not cause failure of the whole network. This feature makes them also more suitable for some kinds of applications, like sensoric networks. Message delivery protocols are fundamental for applications that use the network, especially when it comes to sending messages to host that is not directly accessible. Assuming that hosts can be spread over a large area and distance between any pair of adjacent hosts can be large, temporary failures of links and network topology changes should be taken into account. This makes delivery guarantee a hard problem. Another problem is to provide self-organising network. Joining to network should be as simple as possible and maintaining topology should happen in automatic way. In context of the above observations, in this thesis we propose new communication protocols that provide self-organizing networks and try to ensure delivery of messages between any pair of hosts in a network. Moreover, we provide sample implementation of these protocols.
Bachelor Thesis, 2015

Recent Posts

Our CryptoLUX team has won the first place at the LuxBlockHackathon. We developed a decentralized asset exchange platform with Privacy and Know-Your-Customer regulations compliance on the Ethereum network. You can read the whole story at the university website.

CONTINUE READING

Automation & Robotics Research Group from SnT, University of Luxembourg qualified to the final round of the 2016 DJI Challenge. We had to detect and avoid obstacles, follow a small moving car at 20km/h and land on it. You can see our video for the 3rd (and final) round below:

CONTINUE READING

Projects

robot_activity

ROS package which implements node lifecycle

DJI-SDK-utils

Collection of packages and tools for using DJI UAVS in ROS

extract-and-sync

extract-and-sync is a ROS tool, which extracts images from ROSBAG and syncs them with a given TF transformation

FinContracts - Financial contracts on the Blockchain

node.js package for interacting with Fincontracts deployed on the Ethereum blockchain.