In mid-2015 the European Union changed its response to the increase of migrants crossing the Mediterranean Sea from humanitarian to securitization and deterrence. In 2017 this became visible in the criminalization of search and rescue (SAR) organizations, which had an impact and both intended and unintended consequences. This study focuses on the impact of criminalization on the management of search and rescue NGOs in the Central Mediterranean Sea since 2017 by analysing changes in their recruitment, training and general management, their decision-making process when faced with (the risk of) criminalization and criminalization’s impact on their ability to fulfil their mission. This is done through analysing literature and conducting semi-structured interviews with four people who are active in SAR organizations affected by (the risk of) criminalization. This study finds that it is not generally known that authorities have changed strategies of criminalization. The previous more open form of criminalization partly strengthened one of the organizations as members became more resolute in their commitment to their mission and public support and donations increased by those who opposed the authorities’ strategy. The current strategy consists of mainly administrative hurdles, which are less visible but more difficult to manage for organizations.  Recruitment was impacted as there are fewer potential candidates and vetting increased. Trainings changed to give crew members additional information and enable them to obtain required licenses. In general management more sustainable structures were created for resilience to criminalization. In the decision-making process when faced with (the risk of) criminalization the organizations aim to be democratic, which makes the process more time-consuming and prone to internal conflict. The organizations’ ability to fulfil their missions was impacted by the negative influence of the media on their public image and needing to use resources for legal defence instead of SAR operations. There are currently less frequent SAR operations and it is increasingly difficult for small organizations to run their own ship.

There is a tremendous volume of data being generated in today’s world. As organizations around the globe realize the increased importance of their data as being a valuable asset in gaining a competitive edge in a fast-paced and a dynamic business world, more and more attention is being paid to the quality of the data. Advances in the fields of data mining, predictive modeling, text mining, web mining, business intelligence, health care analytics, etc. all depend on clean, accurate data. That one cannot effectively mine data, which is dirty, comes as no surprise. This research is an exploratory study of different domain data sets, addressing the data quality issues specific to each domain, identifying the challenges faced and arriving at techniques or methodologies for measuring and improving the data quality. The primary focus of the research is on the SAR or Search and Rescue dataset, identifying key issues related to data quality therein and developing an algorithm for improving the data quality. SAR missions which are routinely conducted all over the world show a trend of increasing mission costs. Retrospective studies of historic SAR data not only allow for a detailed analysis and understanding of SAR incidents and patterns, but also form the basis for generating probability maps, analytical data models, etc., which allow for an efficient use of valuable SAR resources and their distribution. One of the challenges with regards to the SAR dataset is that the collection process is not perfect. Often, the LKP or the Last Known Position is not known or cannot be arrived at. The goal is to fully or partially geocode the LKP for as many data points as possible, identify those data points where the LKP cannot be geocoded at all, and further highlight the underlying data quality issues. The SAR Algorithm has been developed, which makes use of partial or incomplete information, cleans and validates the data, and further extracts address information from relevant fields to successfully geocode the data. The algorithm improves the geocoding accuracy and has been validated by a set of approaches.

No description available.

No description available.

No description available.

The intensity and frequency of hurricanes and storms increase due to climate change, leaving destruction in their trail. After a hurricane happens, it is fundamental to respond as quickly as possible, and Search and Rescue operations occur to limit human damage further. The operations take place in hostile environments and extreme situations, where speed and efficiency are essential. Indeed, rescuers must be able to have a shared mental model of the situation and act immediately. This study focuses on visualizing situational awareness in such environments to optimize decision-making.  This study has been conducted in collaboration with Frog design and Sony and is part of the broader project FindMe Tag, a system composed of a wearable device that tracks civilians’ location and biometric data. The tag is connected to an app for civilians to handle which data to share. The data is shared to the rescuers’ dashboard for optimizing Search and Rescue operations, which is the focus of this thesis.  Following a Research through Design approach, this thesis project aims to contribute to the interaction design field by proposing a way to visualize situational awareness during extreme and dynamic situations. The process resulted in a dashboard prototype to support Search and Rescue operations by providing a way to visualize data concerning civilians’ status and rescuers, communicate among teams, and encourage connectedness among civilians.

We introduce a framework that would enable using autonomous aerial vehicles in search and rescue scenarios associated with missing person incidents to assist human searchers. We formulate a lost person behavior model and a human searcher model informed by data collected from past search missions. These models are used to generate a probabilistic heatmap of the lost person's position and anticipated searcher trajectories. We use Gaussian processes with a Gibbs' kernel for data fusion to accurately model a limited field-of-view sensor. Our algorithm thereby computes a set of trajectories for a team of aerial vehicles to autonomously navigate, so as to assist and complement human searchers' efforts. / Master of Science / Our goal is to assist human searchers using autonomous aerial vehicles in search and rescue scenarios associated with missing person incidents. We formulate a lost person behavior model and a human searcher model informed by data collected from past search missions. These models are used to generate a probabilistic heatmap of the lost person’s position and anticipated searcher trajectories. We use Gaussian processes for data fusion with Gibbs’ kernel to accurately model a limited field-of-view sensor. Our algorithm thereby computes a set of trajectories for a team of aerial vehicles to autonomously navigate, so as to assist and complement human searchers’ efforts.

Unfavorable environmental and (or) human displacement may engender the need for Search and Rescue (SAR). Challenges such as inaccessibility, large search areas, and heavy reliance on available responder count, limited equipment and training makes SAR a challenging problem. Additionally, SAR operations also pose significant risk to involved responders. This opens a remarkable opportunity for robotic systems to assist and augment human understanding of the harsh environments. A large body of work exists on the introduction of ground and aerial robots in visual and temporal inspection of search areas with varying levels of autonomy. Unfortunately, limited autonomy is the norm in such systems, due to the limitations presented by on-board UAV resources and networking capabilities. In this work we propose a new multi-agent approach to SAR and introduce a wearable compute cluster in the form factor of a backpack. The backpack allows offloading compute intensive tasks such as Lost Person Behavior Modelling, Path Planning and Deep Neural Network based computer vision applications away from the UAVs and offers significantly high performance computers to execute them. The backpack also provides for a strong networking backbone and task orchestrators which allow for enhanced coordination and resource sharing among all the agents in the system. On the basis of our benchmarking experiments, we observe that the backpack can significantly boost capabilities and success in modern SAR responses. / Master of Science / Unfavorable environmental and (or) human displacement may engender the need for Search and Rescue (SAR). Challenges such as inaccessibility, large search areas, and heavy reliance on available responder count, limited equipment and training makes SAR a challenging problem. Additionally, SAR operations also pose significant risk to involved responders. This opens a remarkable opportunity for robotic systems to assist and augment human understanding of the harsh environments. A large body of work exists on the introduction of ground and aerial robots in visual and temporal inspection of search areas with varying levels of autonomy. Unfortunately, limited autonomy is the norm in such systems, due to the limitations presented by on-board UAV resources and networking capabilities. In this work we propose a new multi-agent approach to SAR and introduce a wearable compute cluster in the form factor of a backpack. The backpack allows offloading compute intensive tasks such as Lost Person Behavior Modelling, Path Planning and Deep Neural Network based computer vision applications away from the UAVs and offers significantly high performance computers to execute them. The backpack also provides for a strong networking backbone and task orchestrators which allow for enhanced coordination and resource sharing among all the agents in the system. On the basis of our benchmarking experiments, we observe that the backpack can significantly boost capabilities and success in modern SAR responses.

M. Tech. Computer System Engineering / Autonomous robots are extensively used equipment in industries and in our daily lives; they assist in manufacturing and production but are used for exploration in dangerous or unknown environments. However for a successful exploration, manufacturing and production, navigation plays an important role. Road detection is a vital factor that assists autonomous robots in perfect navigation. Different methods using camera-vision technique have been developed by various researchers with outstanding results, but their systems are still vulnerable to environmental risks. The frequent weather change in various countries such as South Africa, Nigeria and Zimbabwe where shadow, light intensity and other environmental noises occur on daily basis, can cause autonomous robot to encounter failure in navigation. Therefore, the main research question is: How to enhance the road region detection system to enable an effective and efficient maneuvering of the robot in any weather condition.

In urban search and rescue (USAR) operations, there is a considerable amount of danger faced by rescuers. The use of mobile robots can alleviate this issue. Coordinating the search effort is made more difficult by the communication issues typically faced in these environments, such that communication is often restricted. With small numbers of robots, it is necessary to break communication links in order to explore the entire environment. The robots can be viewed as a broken ad hoc network, relying on opportunistic contact in order to share data. In order to minimise overheads when exchanging data, a novel algorithm for data exchange has been created which maintains the propagation speed of flooding while reducing overheads. Since the rescue workers outside of the structure need to know the location of any victims, the task of finding their locations is two parted: 1) to locate the victims (Search Time), and 2) to get this data outside the structure (Delay Time). Communication with the outside is assumed to be performed by a static robot designated as the Command Station. Since it is unlikely that there will be sufficient robots to provide full communications coverage of the area, robots that discover victims are faced with the difficult decision of whether they should continue searching or return with the victim data. We investigate a variety of search techniques and see how the application of biological foraging models can help to streamline the search process, while we have also implemented an opportunistic network to ensure that data are shared whenever robots come within line of sight of each other or the Command Station. We examine this trade-off between performing a search and communicating the results.