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.

The rapid growth of the Unmanned Aerial Vehicle industry has increased the demand for robust control systems for commercial quadcopters, whose dynamic models are often unknown, to ensure reliable performance under adverse conditions. In this context, this paper proposes Deep Neural Network-Based LQR Adaptive Control (DNN-LQR-AC), an Adaptive Control (AC) strategy implemented using the Robot Operating System (ROS) software framework. DNN-LQR-AC relies on a simplified linearized dynamic model and combines an LQR controller with an adaptive term, which is updated in real-time using Deep Neural Networks (DNNs). The proposed solution also features cubic spline-based trajectory generation to provide continuous reference trajectories for the controller. Experimental validation using a Hardware-in-the-Loop approach on a DJI Matrice 100 quadcopter demonstrates that DNN-LQR-AC outperforms PID, LQR, and LQR-AC controllers, achieving superior position control in trajectory tracking under varied wind conditions, highlighting its applicability in real-world scenarios.

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.

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.

This paper describes an overview of a generic framework for collaboration among humans and multiple heterogeneous robotic systems based on the use of a formal characterization of delegation as a speech act. The system used contains a complex set of integrated software modules that include delegation managers for each platform, a task specification language for characterizing distributed tasks, a task planner, a multi-agent scan trajectory generation and region partitioning module, and a system infrastructure used to distributively instantiate any number of robotic systems and user interfaces in a collaborative team. The application focusses on 3D reconstruction in alpine environments intended to be used by alpine rescue teams. Two complex UAV systems used in the experiments are described. A fully autonomous collaborative mission executed in the Italian Alps using the framework is also described.

Visual object tracking performance has improved significantly in recent years. Most trackers are based on either of two paradigms: online learning of an appearance model or the use of a pre-trained object detector. Methods based on online learning provide high accuracy, but are prone to model drift. The model drift occurs when the tracker fails to correctly estimate the tracked object’s position. Methods based on a detector on the other hand typically have good long-term robustness, but reduced accuracy compared to online methods.

Despite the complementarity of the aforementioned approaches, the problem of fusing them into a single framework is largely unexplored. In this paper, we propose a novel fusion between an online tracker and a pre-trained detector for tracking humans from a UAV. The system operates at real-time on a UAV platform. In addition we present a novel dataset for long-term tracking in a UAV setting, that includes scenarios that are typically not well represented in standard visual tracking datasets.

In this work we are investigating reactive avoidance techniques which can be used on board of a small quadcopter and which do not require absolute localisation. We propose a local map representation which can be updated with proprioceptive sensors. The local map is centred around the robot and uses spherical coordinates to represent a point cloud. The local map is updated using a depth sensor, the Inertial Measurement Unit and a registration algorithm. We propose an extension of the Dynamic Window Approach to compute a velocity vector based on the current local map. We propose to use an OctoMap structure to compute a 2-pass A* which provide a path which is converted to a velocity vector. Both approaches are reactive as they only make use of local information. The algorithms were evaluated in a simulator which offers a realistic environment, both in terms of control and sensors. The results obtained were also validated by running the algorithms on a real platform.

Robots are increasingly expected to move out of the controlled environment of research labs and into populated streets and workplaces. Collision avoidance in such cluttered and dynamic environments is of increasing importance as robots gain more autonomy. However, efficient avoidance is fundamentally difficult since computing safe trajectories may require considering both dynamics and uncertainty. While heuristics are often used in practice, we take a holistic stochastic trajectory optimization perspective that merges both collision avoidance and control. We examine dynamic obstacles moving without prior coordination, like pedestrians or vehicles. We find that common stochastic simplifications lead to poor approximations when obstacle behavior is difficult to predict. We instead compute efficient approximations by drawing upon techniques from machine learning. We propose to combine policy search with model-predictive control. This allows us to use recent fast constrained model-predictive control solvers, while gaining the stochastic properties of policy-based methods. We exploit recent advances in Bayesian optimization to efficiently solve the resulting probabilistically-constrained policy optimization problems. Finally, we present a real-time implementation of an obstacle avoiding controller for a quadcopter. We demonstrate the results in simulation as well as with real flight experiments.

Micro unmanned aerial vehicles are becoming increasingly interesting for aiding and collaborating with human agents in myriads of applications, but in particular they are useful for monitoring inaccessible or dangerous areas. In order to interact with and monitor humans, these systems need robust and real-time computer vision subsystems that allow to detect and follow persons.

In this work, we propose a low-level active vision framework to accomplish these challenging tasks. Based on the LinkQuad platform, we present a system study that implements the detection and tracking of people under fully autonomous flight conditions, keeping the vehicle within a certain distance of a person. The framework integrates state-of-the-art methods from visual detection and tracking, Bayesian filtering, and AI-based control. The results from our experiments clearly suggest that the proposed framework performs real-time detection and tracking of persons in complex scenarios