In the dynamic and challenging maritime domain, Search and Rescue (SAR) operations are critical for ensuring the safety of life at sea. Adverse weather conditions often hinder traditional SAR efforts, leading to significant delays or cancellation of search missions. This paper introduces an autonomous search system utilizing Unmanned Aerial Vehicles. The system combines decision-making techniques for automatic mission generation and a flexible machine-learning framework that allows for easy training and deployment of models to automatically process data gathered during SAR operations. One of the system’s main features is the ease of use in mission planning, where high-level mission goals can be specified via a user interface in the form of data requests. The paper presents the results of the experimental evaluations of the system and showcases its deployment in actual field-test experimentation.

This paper addresses the problem of vision-based object geolocation using Unmanned Aerial Vehicles in Search and Rescue settings. It focuses on the task of automatically and accurately geolocating objects of different classes, focusing on human bodies, to provide a map of the detected objects as salient locations. Such maps can be used by responders to plan rescue operations or by other robotic platforms where geolocation is necessary, such as with delivery of medical supplies. The proposed solution strategy leverages recent developments in the field of Convolutional Neural Networks for vision-based object detection with a method for fusing detections. Occupancy probabilities of locations in the environment containing objects of specific classes, or lack thereof, are also computed. This is achieved by taking advantage of a novel sensor model for fusing vision-based detections using both positive and negative observations. The method is validated in simulation as well as with real field experiments.

This paper explores the use of LH Interval Calculus, a novel qualitative spatial reasoning formalism, to create a human-readable representation of environments observed by UAVs. The system simplifies data from multiple UAVs collaborating on environment mapping. Real UAV-captured data was used for evaluation. In tests involving two UAVs mapping an outdoor area, LH Calculus proved effective in generating a cohesive high-level description of the environment, contingent on consistent input data.

In the context of collaborative robotics, distributed situation awareness is essential for  supporting collective intelligence in teams of robots and human agents where it can be used for both individual and collective decision support. This is particularly important in applications pertaining to emergency rescue and crisis management. During operational missions, data and knowledge are gathered incrementally and in different ways by heterogeneous robots and humans. We describe this as the creation of Hastily Formed Knowledge Networks (HFKNs). The focus of this paper is the specification and prototyping of a general distributed system architecture that supports the creation of HFKNs by teams of robots and humans. The information collected ranges from low-level sensor data to high-level semantic knowledge, the latter represented in part as RDF Graphs. The framework includes a synchronization protocol and associated algorithms that allow for the automatic distribution and sharing of data and knowledge between agents. This is done through the distributed synchronization of RDF Graphs shared between agents. High-level semantic queries specified in SPARQL can be used by robots and humans alike to acquire both knowledge and data content from team members. The system is empirically validated and complexity results of the proposed algorithms are provided. Additionally, a field robotics case study is described, where a 3D mapping mission has been executed using several UAVs in a collaborative emergency rescue scenario while using the full HFKN Framework.

Reasoning about uncertainty is one of the main cornerstones of Knowledge Representation. Formal representations of uncertainty are numerous and highly varied due to different types of uncertainty intended to be modeled such as vagueness, imprecision and incompleteness. There is a rich body of theoretical results that has been generated for many of these approaches. It is often the case though, that pragmatic tools for reasoning with uncertainty lag behind this rich body of theoretical results. Rough set theory is one such approach for modeling incompleteness and imprecision based on indiscernibility and its generalizations. In this paper, we provide a pragmatic tool for constructively reasoning with generalized rough set approximations that is based on the use of Answer Set Programming (Asp). We provide an interpretation of answer sets as (generalized) approximations of crisp sets (when possible) and show how to use Asp solvers as a tool for reasoning about (generalized) rough set approximations situated in realistic knowledge bases. The paper includes generic Asp templates for doing this and also provides a case study showing how these techniques can be used to generate reducts for incomplete information systems. Complete, ready to run clingo Asp code is provided in the Appendix, for all programs considered. These can be executed for validation purposes in the clingo Asp solver.

A research arena (WARA-PS) for sensing, data fusion, user interaction, planning and control of collaborative autonomous aerial and surface vehicles in public safety applications is presented. The objective is to demonstrate scientific discoveries and to generate new directions for future research on autonomous systems for societal challenges. The enabler is a computational infrastructure with a core system architecture for industrial and academic collaboration. This includes a control and command system together with a framework for planning and executing tasks for unmanned surface vehicles and aerial vehicles. The motivating application for the demonstration is marine search and rescue operations. A state-of-art delegation framework for the mission planning together with three specific applications is also presented. The first one concerns model predictive control for cooperative rendezvous of autonomous unmanned aerial and surface vehicles. The second project is about learning to make safe real-time decisions under uncertainty for autonomous vehicles, and the third one is on robust terrain-aided navigation through sensor fusion and virtual reality tele-operation to support a GPS-free positioning system in marine environments. The research results have been experimentally evaluated and demonstrated to industry and public sector audiences at a marine test facility. It would be most difficult to do experiments on this large scale without the WARA-PS research arena. Furthermore, these demonstrator activities have resulted in effective research dissemination with high public visibility, business impact and new research collaborations between academia and industry.

Aerial robots hold great potential for aiding Search and Rescue (SAR) efforts over large areas, such as during natural disasters. Traditional approaches typically search an area exhaustively, thereby ignoring that the density of victims varies based on predictable factors, such as the terrain, population density and the type of disaster. We present a probabilistic model to automate SAR planning, with explicit minimization of the expected time to discovery. The proposed model is a spatial point process with three interacting spatial fields for i) the point patterns of persons in the area, ii) the probability of detecting persons and iii) the probability of injury. This structure allows inclusion of informative priors from e.g. geographic or cell phone traffic data, while falling back to latent Gaussian processes when priors are missing or inaccurate. To solve this problem in real-time, we propose a combination of fast approximate inference using Integrated Nested Laplace Approximation (INLA), and a novel Monte Carlo tree search tailored to the problem. Experiments using data simulated from real world Geographic Information System (GIS) maps show that the framework outperforms competing approaches, finding many more injured in the crucial first hours.

With the rise of deep reinforcement learning, there has also been a string of successes on continuous control problems using physics simulators. This has lead to some optimism regarding use in autonomous robots and vehicles. However, to successful apply such techniques to the real world requires a firm grasp of their limitations. As recent work has raised questions of how diverse these simulation benchmarks really are, we here instead analyze a popular deep RL approach on toy examples from robot obstacle avoidance. We find that these converge very slowly, if at all, to safe policies. We identify convergence issues on stochastic environments and local minima as problems that warrant more attention for safety-critical control applications.

We consider a general and industrially motivated class of planning problems involving a combination of requirements that can be essential to autonomous robotic systems planning to act in the real world: Support for temporal uncertainty where nature determines the eventual duration of an action, resource consumption with a non-linear relationship to durations, and the need to select appropriate values for control parameters that affect time requirements and resource usage. To this end, an existing planner is extended with support for Simple Temporal Networks with Uncertainty, Timed Initial Literals, and temporal coverage goals. Control parameters are lifted from the main combinatorial planning problem into a constraint satisfaction problem that connects them to resource usage. Constraint processing is then integrated and interleaved with verification of temporal feasibility, using projections for partial temporal awareness in the constraint solver.