Enio Prates Vasconcelos Filho successfully defended his PhD thesis, supervised by Eduardo Tovar, and co-supervised by Anis Koubaa and Luis Almeida, at the Faculty of Engineering of the University of Porto, Portugal.

His thesis entitled "An Evaluation Framework for Safe Cooperative Vehicle Platooning" presents a framework named CopaDrive, aimed at vehicular applications capable of realistically simulating control and communication models. Based on ROS, this framework allows solutions to be developed and validated faster and more efficiently than current models. Its design is composed of the simulation tool, Hardware in the Loop, and the Robotica testbed. Starting from the use case of a Cooperative Vehicle Platooning (Co-VP) system, using this tool, it was possible to present a control solution capable of increasing the size of the platooning, increasing the safety of the maneuvers performed. Furthermore, it was possible to show the efficiency of modifying the message-sending triggers based on the ETSI ITS-G5 communication model.

The PhD examination committee was composed of Prof. Rahul Mangharam, from University of Pennsylvania, USA; Prof. António Casimiro Ferreira da Costa, Departamento de Informática da Faculdade de Ciências da Universidade de Lisboa, Prof. Joaquim José de Castro Ferreira, Escola Superior de Tecnologia e Gestão de Águeda da Universidade de Aveiro and Prof. Paulo José Lopes Machado Portugal, Departamento de Engenharia Eletrotécnica e de Computadores da Faculdade de Engenharia da Universidade do Porto. It was chaired by Prof. José Nuno Moura Marques Fidalgo, Full Professor of the Faculty of Engineering of the University of Porto.

The extended abstract entitled "Shared Resource Contention Aware Schedulability Analysis for Multiprocessor Real-Time Systems" presented by CISTER PhD student Jatin Arora got the "Best Poster Prize" at the PhD Forum of Design, Automation and Test in Europe Conference (DATE) 2023 that took place in Antwerp, Belgium from 17 to 19 April 2023. DATE is a premiere European conference for design, automation & test and this year's edition of DATE attracted more than 900 participants from across the world.

The PhD forum of DATE is a well-known platform for recent PhD graduates/final year PhD students to present their PhD research work to a broader audience.  The PhD forum of DATE 2023 featured 46 researchers/final-year PhD students from prestigious organizations across the world. The PhD forum best poster prize is supported by EDAA, ACM SIGDA, and IEEE CEDA. Besides the best poster prize, Jatin is a recipient of the PhD forum travel grant and full registration sponsorship for DATE 2023 under the Young People Programme (YPP).

The extended abstract co-authored by Jatin Arora, Eduardo Tovar, and Cláudio Maia summarizes the major research challenges addressed during Jatin's PhD studies. This recognition sets a relevant milestone in Jatin's PhD studies.

The Journal Paper entitled "LSTM-characterized Deep Reinforcement Learning for Continuous Flight Control and Resource Allocation in UAV-assisted Sensor Network", authored by Kai Li, Wei Ni, Falko Dressler is published in IEEE Internet of Things Journal.

Unmanned aerial vehicles (UAVs) can be employed to collect sensory data in remote wireless sensor networks (WSN). This is useful in many real-life situations like agriculture monitoring, forest fire prevention and control, smart traffic management, and other similar situations where there is the need to gather information over very large areas but keeping costs and resource usage to the minimum while guaranteeing an adequate quality of service.

Due to UAV's maneuvering, scheduling a sensor device to transmit data can overflow data buffers of the unscheduled ground devices. Moreover, lossy airborne channels can result in packet reception errors at the scheduled sensor.

This paper proposes a new deep reinforcement learning based flight resource allocation framework (DeFRA) to minimize the overall data packet loss in a continuous action space. DeFRA is based on Deep Deterministic Policy Gradient (DDPG), optimally controls instantaneous headings and speeds of the UAV, and selects the ground device for data collection. Furthermore, a state characterization layer, leveraging long short-term memory (LSTM), is developed to predict network dynamics, resulting from time-varying airborne channels and energy arrivals at the ground devices.

To validate the effectiveness of DeFRA, experimental data collected from a real-world UAV testbed and energy harvesting WSN are utilized to train the actions of the UAV. Numerical results demonstrate that the proposed DeFRA achieves a fast convergence while reducing the packet loss by over 15%, as compared to existing deep reinforcement learning solutions.