Haris Balta

UAS deployment and data processing during the Balkans flooding

This project paper provides a report on a real relief operation mission, jointly conducted by two European research projects, in response to the massive flooding in the Balkan in spring 2014. Un Unmanned Aerial System was deployed on-site in collaboration with traditional relief workers, to support them with damage assessment, area mapping, visual inspection and re-localizing the many explosive remnants of war which have been moved due to the flooding and landslides. Novel robotic technologies and data processing methodologies were brought from the research labs and directly applied onto the terrain in order to support the relief workers and minimize human suffering.

Training and Support system in the Cloud for improving the situational awareness in Search and Rescue (SAR) operations

In this paper, a Training and Support system for Search and Rescue operations is described. The system is a component of the ICARUS project (http://www.fp7-icarus.eu) which has a goal to develop sensor, robotic and communication technologies for Human Search And Rescue teams. The support system for planning and managing complex SAR operations is implemented as a command and control component that integrates different sources of spatial information, such as maps of the affected area, satellite images and sensor data coming from the unmanned robots, in order to provide a situation snapshot to the rescue team who will make the necessary decisions. Support issues will include planning of frequency resources needed for given areas, prediction of coverage conditions, location of fixed communication relays, etc. The training system is developed for the ICARUS operators controlling UGVs (Unmanned Ground Vehicles), UAVs (Unmanned Aerial Vehicles) and USVs (Unmanned Surface Vehicles) from a unified Remote Control Station (RC2). The Training and Support system is implemented in SaaS model (Software as a Service). Therefore, its functionality is available over the Ethernet. SAR ICARUS teams from different countries can be trained simultaneously on a shared virtual stage. In this paper we will show the multi-robot 3D mapping component (aerial vehicle and ground vehicles). We will demonstrate that these 3D maps can be used for Training purpose. Finally we demonstrate current approach for ICARUS Urban SAR (USAR) and Marine SAR (MSAR) operation training.

Teodor: A Semi-Autonomous Search and Rescue and Demining Robot

In this paper, we present a ground robotic system which is developed to deal with rough outdoor conditions. The platform is to be used as an environmental monitoring robot for 2 main application areas: - Humanitarian demining: The vehicle is equipped with a specialized multi-channel metal detector array. An unmanned aerial system supports it for locating suspected locations of mines, which can then be confirmed by the ground vehicle. - Search and rescue: The vehicle is equipped with human victim detection sensors and a 3D camera enabling it to assess the traversability of the terrain in front of the robot in order to be able to navigate autonomously. The paper discusses both the mechanical design of these platforms as the autonomous perception capabilities on board of these vehicles.

Framework for automated reconstruction of 3D model from multiple 2D aerial images

The paper considers a problem of 3D environment model reconstruction from a set of 2D images acquired by the Unmanned Aerial Vehicle (UAV) in near real-time. The designed framework combines the FAST (Features from Accelerated Segment Test) algorithm and optical flow approach for detection of interest image points and adjacent images reconstruction. The robust estimation of camera locations is performed using the image points tracking. The coordinates of 3D points and the projection matrix are computed simultaneously using Structure-from-Motion (SfM) algorithm, from which the 3D model of environment is generated. The designed framework is tested using real image data and video sequences captured with camera mounted on the UAV. The effectiveness and quality of the proposed framework are verified through analyses of accuracy of the 3D model reconstruction and its time execution.

Unmanned Ground and Aerial Robots Supporting Mine Action Activities

During the Humanitarian‐demining actions, teleoperation of sensors or multi‐sensor heads can enhance‐detection process by allowing more precise scanning, which is use‐ ful for the optimization of the signal processing algorithms. This chapter summarizes the technologies and experiences developed during 16 years through national and/or European‐funded projects, illustrated by some contributions of our own laboratory, located at the Royal Military Academy of Brussels, focusing on the detection of unex‐ ploded devices and the implementation of mobile robotics systems on minefields.

Use of multi-domain robots in search and rescue operations — Contributions of the ICARUS team to the euRathlon 2015 challenge

Today, in our landscape perception exists a gap that needs to be fulfilled. Its important to increase the coverage, temporal and spatial resolution in order to cover this gap, as well as reduce costs with human resources that usually take this kind of tasks. Unmanned Autonomous vehicles with their inherent autonomy and reduced needs of human and communication resources, can provide additional capabilities and a new innovative solution to this problem This paper presents and describes the participation of ICARUS Team at euRathlon 2015 and the importance of this type of events performed with multiple unnamed systems.

Autonomous Guidance for a UAS Along a Staircase

In the quest for fully autonomous unmanned aerial systems (UAS), multiple challenges are faced. For enabling autonomous UAS navigation in indoor environments, one of the major bottlenecks is the capability to autonomously traverse narrow 3D - passages, like staircases. This paper presents a novel integrated system that implements a semi-autonomous navigation system for a quadcopter. The navigation system permits the UAS to detect a staircase using only the images provided by an on-board monocular camera. A 3D model of this staircase is then automatically reconstructed and this model is used to guide the UAS to the top of the detected staircase. For validating the methodology, a proof of concept is created, based on the Parrot AR.Drone 2.0 which is a cheap commercial off-the-shelf quadcopter.

Adaptive behavior-based control for robot navigation: A multi-robot case study

The main focus of the work presented in this paper is to investigate the application of certain biologically-inspired control strategies in the field of autonomous mobile robots, with particular emphasis on multi-robot navigation systems. The control architecture used in this work is based on the behavior-based approach. The main argument in favor of this approach is its impressive and rapid practical success. This powerful methodology has demonstrated simplicity, parallelism, perception-action mapping and real implementation. When a group of autonomous mobile robots needs to achieve a goal operating in complex dynamic environments, such a task involves high computational complexity and a large volume of data needed for continuous monitoring of internal states and the external environment. Most autonomous mobile robots have limited capabilities in computation power or energy sources with limited capability, such as batteries. Therefore, it becomes necessary to build additional mechanisms on top of the control architecture able to efficiently allocate resources for enhancing the performance of an autonomous mobile robot. For this purpose, it is necessary to build an adaptive behavior-based control system focused on sensory adaptation. This adaptive property will assure efficient use of robots limited sensorial and cognitive resources. The proposed adaptive behavior-based control system is then validated through simulation in a multi-robot environment with a task of prey/predator scenario.