This article presents the first ever fully autonomous UAV (Unmanned Aerial Vehicle) mission to perform gas measurements after a real blast in an underground mine. The demonstration mission was deployed around 40 minutes after the blast took place, and as such realistic gas levels were measured. We also present multiple field robotics experiments in different mines detailing the development process. The presented novel autonomy stack, denoted as the Routine Inspection Autonomy (RIA) framework, combines a risk-aware 3D path planning D + ∗ , with 3D LiDAR-based global relocalization on a known map, and it is integrated on a custom hardware and a sensing stack with an onboard gas sensing device. In the presented framework, the autonomous UAV can be deployed in incredibly harsh conditions (dust, significant deformations of the map) shortly after blasting to perform inspections of lingering gases that present a significant safety risk to workers. We also present a change detection framework that can extract and visualize the areas that were changed in the blasting procedure, a critical parameter for planning the extraction of materials, and for updating existing mine maps. As will be demonstrated, the RIA stack can enable robust autonomy in harsh conditions, and provides reliable and safe navigation behavior for autonomous Routine Inspection missions.

This paper presents a complete system architecture for multi-robot coordination for unbalanced task assignments, where a number of robots are supposed to visit and accomplish missions at different locations. The proposed method first clusters tasks into clusters according to the number of robots, then the assignment is done in the form of one-cluster-to-one-robot, followed by solving the traveling salesman problem (TSP) to determine the visiting order of tasks within each cluster. A nonlinear model predictive controller (NMPC) is designed for robots to navigate to their assigned tasks while avoiding colliding with other robots. Several simulations are conducted to evaluate the feasibility of the proposed architecture. Video examples of the simulations can be viewed at https://youtu.be/5C7zTnv2sfo and https://youtu.be/-JtSg5V2fTI?si=7PfzZbleOOsRdzRd. Besides, we compare the cluster-based assignment with a simulated annealing (SA) algorithm, one of the typical solutions for the multiple traveling salesman problem (mTSP), and the result reveals that with a similar optimization effect, the cluster-based assignment demonstrates a notable reduction in computation time. This efficiency becomes increasingly pronounced as the task-to-agent ratio grows.

As the routine operations are starting to become highly automated, it is crucial to develop autonomous solutions that are infrastructure independent. Achieving this is challenging due to the ever-changing landscape of mines, which complicates infrastructure development. In response, this paper introduces a robust framework employing drones to gather data from hard-to-access areas in mines and deliver the data back to the base station for routine monitoring purposes. These tasks include gathering data from operational vehicles (mine trucks, loaders etc.), as well as various sensors (e.g. monitoring rock bolts) and relaying the data to the mine’s base station for monitoring purposes. The proposed framework is based on autonomous navigation using a known point cloud map of the mine, proximity detection via Ultra WideBand (UWB) radios and the data transfer is accomplished through the IEEE 802.15.4 communication standard, operating in the 868 MHz ISM band, with the aim to guarantee long range operation. On the mission level, the drones act as data mules capable of autonomously extracting data from operating vehicles, storing the data onboard and eventually delivering the data to the base station, which is enabled through a Point and Click (PAC) autonomy framework based on global planning, reactive navigation, communication link and behavior management. The efficacy of this framework has been demonstrated through real-world experiments conducted at a test mine in Sweden, validating the overall architecture of the proposed solution.

Exploration and safe navigation in previously unknown GPS-denied obstructed areas are major challenges for autonomous robots when deployed in subterranean environments. In response, this work establishes an Exploration-Planning framework developed for the real-world deployment of Micro Aerial Vehicles (MAVs) in subterranean exploration missions. The fundamental task for an autonomous MAV to navigate in an unknown area, is to decide where to look while navigating such that the MAV will acquire more information about the surrounding. The work presented in this article focuses around 3D exploration of large-scale caves or multi-branched tunnel like structures, while still prioritizing the Look-Ahead and Move-Forward approach for fast navigation in previously unknown areas. In order to achieve such exploration behaviour, the proposed work utilizes a two-layer navigation approach. The first layer deals with computing traversable frontiers to generate the look ahead poses in the constrained field of view, aligned with the MAV’s heading vector that leads to rapid continuous exploration. The proposed frontier distribution based switching goal selection approach allows the MAV to explore various terrains, while still regulating the MAV’s heading vector. The second layer of the proposed scheme deals with global cost based navigation of the MAV to the potential junction in a multi-branched tunnel system leading to a continuous exploration of partially seen areas. The proposed framework is a combination of a novel frontier goal selection approach, risk-aware expandable grid based path planning, nonlinear model predictive control and artificial potential fields based on local reactive navigation, obstacle avoidance, and control for the autonomous deployment of MAVs in extreme environments.

This article establishes the novel D_+^*, , a risk-aware and platform-agnostic heterogeneous global path planner for robotic navigation in complex environments. The proposed planner addresses a fundamental bottleneck of occupancy-based path planners related to their dependency on accurate and dense maps. More specifically, their performance is highly affected by poorly reconstructed or sparse areas (e.g. holes in the walls or ceilings) leading to faulty generated paths outside the physical boundaries of the 3-dimensional space. As it will be presented, D+* addresses this challenge with three novel contributions, integrated into one solution, namely: (a) the proximity risk, (b) the modeling of the unknown space, and (c) the map updates. By adding a risk layer to spaces that are closer to the occupied ones, some holes are filled, and thus the problematic short-cutting through them to the final goal is prevented. The novel established D₊*  also provides safety marginals to the walls and other obstacles, a property that results in paths that do not cut the corners that could potentially disrupt the platform operation. D₊*  has also the capability to model the unknown space as risk-free areas that should keep the paths inside, e.g in a tunnel environment, and thus heavily reducing the risk of larger shortcuts through openings in the walls. D₊* is also introducing a dynamic map handling capability that continuously updates with the latest information acquired during the map building process, allowing the planner to use constant map growth and resolve cases of planning over outdated sparser map reconstructions. The proposed path planner is also capable to plan 2D and 3D paths by only changing the input map to a 2D or 3D map and it is independent of the dynamics of the robotic platform. The efficiency of the proposed scheme is experimentally evaluated in multiple real-life experiments where D₊* is producing successfully proper planned paths, either in 2D in the use case of the Boston dynamics Spot robot or 3D paths in the case of an unmanned areal vehicle in varying and challenging scenarios.

This chapter presents an overview of various exploration schemes with single and multi Aerial Robotic Workers (ARWs) and their applications in Search and Rescue, Environmental Monitoring, and planetary exploration missions, under the assumption that the map is partially known or completely unknown. The presented methods in the chapter are in line with the field deployment of the ARWs in subterranean and planetary exploration missions. The addressed questions will include the operating environment configuration and path planning methods for single and multi-robot exploration. The chapter will also briefly present two exploration strategies in terms of frontier and sampling-based exploration algorithms. More specifically, frontier-based and Rapidly Exploring Random Tree (RRT)-based exploration methodologies with results will be explained in detail.

This chapter presents an overview of various navigation schemes used for ARWs and their application areas. Navigation schemes, in general, answer the question of how to move from the current position to the desired and optimally plan the path between them, which is a necessary step for almost all applications for autonomous flight. This chapter will go over reactive navigation schemes, such as the potential fields and Model Predictive Control with integrated obstacle avoidance, as well as global path-planning methods, such as map-based iterative planners like D^⁎, and planning for complete coverage of infrastructure to perform a visual inspection.

This Chapter presents vision-based perception modules for an Aerial Robotic Worker, as a basic component for the autonomy of the platform. Generally, visual information could be involved in various levels of autonomy, from object tracking to workspace mapping and motion estimation. The major challenge today is the development of autonomously operating aerial agents capable of completing missions independently of human interaction. To this extent, onboard perception should be developed for the aerial platform to perceive its surroundings and estimate its motion, enhancing the overall navigation and guidance skills.

Micro Aerial Vehicles (MAVs) have showcased their potential for enabling the next generation of inspection technologies as a sensor payload carrier operating at various levels of autonomy. Combining their ability to navigate in unstructured areas with the dexterity of robotic arms leads to a new era of Aerial Robotic Workers (ARWs) able to interact with the environment and as such address infrastructure maintenance tasks. The development of perception capabilities that guide the aerial platform at the desired regions of interest and perform the respective manipulation tasks is, among others, a fundamental step towards the envisioned goal. Thus, the aim of this Chapter is to discuss visual guidance systems to assist the aerial platform before applying any physical interaction.

This compilation thesis presents two main contributions in path planning and obstacle avoidance, as well as an integration of the proposed modules with other frameworks to enable resilient robotic missions in complex environments.In general, through different types of robotic missions it is important to have a collision tolerant and reliable system, both regarding potential risks from collisions with dynamic and static obstacles, but also to secure the overall mission success.%Particularly, a common trend in the presented work is safety regarding collisions with dynamic and static obstacles, as well as reliable overall systems that are capable of executing missions.

The work included in this thesis presents the risk-aware path planner D$^*_+$ that is capable of planning traversable paths for both ground and aerial robots. D$^*_+$ is developed on top of D$^*$-lite with a risk layer close to occupied space, modeling the unknown areas as a risk, and is implemented with a dynamic map to enable updates and adjustments to a changing environment.

The risk layer aids in solving two common challenges with path planning for real robots: a) it creates a safety margin that gives free space between the path and obstacles so that robots with the corresponding size can follow the path, and b) it masks smaller holes in walls that occur when building maps from real data.

Using a dynamic map makes it possible to use D$^*_+$ for an exploration mission, it also enables for the re-planning of the path if the environment changes for example, if an obstacle suddenly blocks a path, a new path will be planned. D$^*_+$ have been tested in different real-life experiments with both an Unmanned Areal Vehicle (UAV) and a quadruped-legged robot and shown to produce traversable paths in different application scenarios, such as exploration, return to base, and navigation on known maps.

This thesis also presents an obstacle avoidance architecture for velocity objects, structured around an object detection and tracking scheme that is combined with non-linear model predictive controller (NMPC) to plan the avoidance maneuver. %that uses a Convolutional Neural Network to detect obstacles that are tracked so they can be avoided by a non-linear model predictive controller (NMPC).In this case, the detection is done with the Convoluitonal Neural Network (CNN) You Only Lock Once v4 (YOLO) where the most certain human is tracked with a Kalman filter, and the velocity of the human is estimated.The proposed scheme models the object motion as constant velocity, which is utilized from the NMPC to plan control inputs for the robot to avoid the identified obstacle. A merit of the approach is that the avoidance maneuver does not only consider the current identification position, but also considers the motion prediction of the object. This avoidance framework proved to be capable to avoid non-cooperative obstacles, such as humans moving towards it.Due to the fact that the avoidance is starting when a future collision is predicted, the avoidance maneuver is started early enough to avoid obstacles with a higher velocity than a classic ``static obstacle'' radius approach can handle.

An additional aim of this thesis is to showcase that the proposed contributions can be applied in full robotic missions/frameworks. Thus, this thesis presents a search and rescue mission with a quadruped-legged robot and a UAV on a partially known map to find the location of survivors and other objects of related interest. In this mission, the quadruped-legged robot carries the UAV to the edge of the known map from where it launches the UAV that then explores and detects any survival and other relevant objects.Also, an autonomy solution, based on Boston dynamics' quadruped-legged robot Spot, for enabling a map-based navigation in confined environments has been developed and tested. This Spot solution enables the robot to navigate to a user-selected point, rotate in the desired direction, and instruct the UAV, in the combined search and rescue mission, to take off.