This article introduces a curriculum learning approach to develop a reinforcement learning-based robust stabilizing controller for a Quadrotor that meets predefined performance criteria. The learning objective is to achieve desired positions from random initial conditions while adhering to both transient and steady-state performance specifications. This objective is challenging for conventional one-stage end-to-end reinforcement learning, due to the strong coupling between position and orientation dynamics, the complexity in designing and tuning the reward function, and poor sample efficiency, which necessitates substantial computational resources and leads to extended convergence times. To address these challenges, this work decomposes the learning objective into a three-stage curriculum that incrementally increases task complexity. The curriculum begins with learning to achieve stable hovering from a fixed initial condition, followed by progressively introducing randomization in initial positions, orientations and velocities. A novel additive reward function is proposed, to incorporate transient and steady-state performance specifications. The results demonstrate that the Proximal Policy Optimization (PPO)-based curriculum learning approach, coupled with the proposed reward structure, achieves superior performance compared to a single-stage PPO-trained policy with the same reward function, while significantly reducing computational resource requirements and convergence time. The curriculum-trained policy's performance and robustness are thoroughly validated under random initial conditions and in the presence of disturbances.

As industries increasingly adopt large robotic fleets, there is a pressing need for computationally efficient, practical, and optimal conflict-free path planning for multiple robots. Conflict-Based Search (CBS) is a popular method for multi-agent path finding (MAPF) due to its completeness and optimality; however, it is often impractical for real-world applications, as it is computationally intensive to solve and relies on assumptions about agents and operating environments that are difficult to realize. This article proposes a solution to overcome computational challenges and practicality issues of CBS by utilizing structural-semantic topometric maps. Instead of running CBS over large grid-based maps, the proposed solution runs CBS over a sparse topometric map containing structural-semantic cells representing intersections, pathways, and dead ends. This approach significantly accelerates the MAPF process and reduces the number of conflict resolutions handled by CBS while operating in continuous time. In the proposed method, robots are assigned time ranges to move between topometric regions, departing from the traditional CBS assumption that a robot can move to any connected cell in a single time step. The approach is validated through real-world multi-robot path-finding experiments and benchmarking simulations. The results demonstrate that the proposed MAPF method can be applied to real-world non-holonomic robots and yields significant improvement in computational efficiency compared to traditional CBS methods while improving conflict detection and resolution in cases of corridor symmetries.

In this article, we present a framework for deploying an aerial multi-agent system in large-scale subterranean environments with minimal infrastructure for supporting multi-agent operations. The multi-agent objective is to optimally and reactively allocate and execute inspection tasks in a mine, which are entered by a mine operator onthe-fly. The assignment of currently available tasks to the team of agents is accomplished through an auction-based system, where the agents bid for available tasks, which are used by a central auctioneer to optimally assigns tasks to agents. A mobile Wi-Fi mesh supports inter-agent communication and bi-directional communication between the agents and the task allocator, while the task execution is performed completely infrastructure-free. Given a task to be accomplished, a reliable and modular agent behavior is synthesized by generating behavior trees from a pool of agent capabilities, using a back-chaining approach. The auction system in the proposed framework is reactive and supports addition of new operator-specified tasks on-the-go, at any point through a user-friendly operator interface. The framework has been validated in a real underground mining environment using three aerial agents, with several inspection locations spread in an environment of almost 200 meters. The proposed framework can be utilized for missions involving rapid inspection, gas detection, distributed sensing and mapping etc. in a subterranean environment. The proposed framework and its field deployment contributes towards furthering reliable automation in large-scale subterranean environments to offload both routine and dangerous tasks from human operators to autonomous aerial robots. The use of autonomous robotic platforms in industrial production facilities is on the rise, both to increase profitability and to increase safety for human operators [1]. Specifically, in deep underground mining, where the fundamental risk of accidents is high, the industry is focusing on creating a safer environment for humans by deploying robotic systems to either execute dangerous tasks or verify the safety before authorizing human entry. Through efforts in the mining industry, human workers have already been moved to safer locations in several critical operations via, for instance, teleoperation of heavy machinery.

In this article, we address the problem of designing a scalable control architecture for a safe coordinated operation of a multi-agent system with aerial (UAVs) and ground robots (UGVs) in a confined task space. The proposed method uses Control Barrier Functions (CBFs) to impose constraints associated with (i) collision avoidance between agents, (ii) landing of UAVs on mobile UGVs, and (iii) task space restriction. Further, to account for the rapid increase in the number of constraints for a single agent with the increasing number of agents, the proposed architecture uses a centralized-decentralized Edge cluster, where a centralized node (Watcher) activates the relevant constraints, reducing the need for high onboard processing and network complexity. The distributed nodes run the controller locally to overcome latency and network issues. The proposed Edge architecture is experimentally validated using multiple aerial and ground robots in a confined environment performing a coordinated operation.

This article introduces a novel method for converting 3D voxel maps, commonly utilized by robots for localization and navigation, into 2D occupancy maps that can be used for more computationally efficient large-scale navigation, both in the sense of computation time and memory usage. The main aim is to effectively integrate the distinct mapping advantages of 2D and 3D maps to enable efficient path planning for both unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs). The proposed method uses the free space representation in the UFOMap mapping solution to generate 2D occupancy maps with height and slope information. In the process of 3D to 2D map conversion, the proposed method conducts safety checks and eliminates free spaces in the map with dimensions (in the height axis) lower than the robot's safety margins. This allows an aerial or ground robot to navigate safely, relying primarily on the 2D map generated by the method. Additionally, the method extracts height and slope data from the 3D voxel map. The slope data identifies areas too steep for a ground robot to traverse, marking them as occupied, thus enabling a more accurate representation of the terrain for ground robots. The height data is utilized to convert paths generated using the 2D map into paths in 3D space for both UAVs and UGVs. The effectiveness of the proposed method is evaluated in two different environments.

In this article, we propose a control solution for the safe transfer of a quadrotor UAV between two surface robots positioning itself only using the visual features on the surface robots, which enforces safety constraints for precise landing and visual locking, in the presence of modeling uncertainties and external disturbances. The controller handles the ascending and descending phases of the navigation using a visual locking control barrier function (VCBF) and a parametrizable switching descending CBF (DCBF) respectively, eliminating the need for an external planner. The control scheme has a backstepping approach for the position controller with the CBF filter acting on the position kinematics to produce a filtered virtual velocity control input, which is tracked by an adaptive controller to overcome modeling uncertainties and external disturbances. The experimental validation is carried out with a UAV that navigates from the base to the target using an RGB camera.

The fifth generation (5G) cellular network technology is mature and increasingly utilized in many industrial and robotics applications, while an important functionality is the advanced Quality of Service (QoS) features. Despite the prevalence of 5G QoS discussions in the related literature, there is a notable absence of real-life implementations and studies concerning their application in time-critical robotics scenarios. This article considers the operation of time-critical applications for 5G-enabled unmanned aerial vehicles (UAVs) and how their operation can be improved by the possibility to dynamically switch between QoS data flows with different priorities. As such, we introduce a robotics oriented analysis on the impact of the 5G QoS functionality on the performance of 5G-enabled UAVs. Furthermore, we introduce a novel framework for the dynamic selection of distinct 5G QoS data flows that is autonomously managed by the 5G-enabled UAV. This problem is addressed in a novel feedback loop fashion utilizing a probabilistic finite state machine (PFSM). Finally, the efficacy of the proposed scheme is experimentally validated with a 5G-enabled UAV in a real-world 5G stand-alone (SA) network.

In this article, we propose the novel concept of Belief Scene Graphs, which are utility-driven extensions of partial 3D scene graphs, that enable efficient high-level task planning with partial information. We propose a graph-based learning methodology for the computation of belief (also referred to as expectation) on any given 3D scene graph, which is then used to strategically add new nodes (referred to as blind nodes) that are relevant for a robotic mission. We propose the method of Computation of Expectation based on Correlation Information (CECI), to reasonably approximate real Belief/Expectation, by learning histograms from available training data. A novel Graph Convolutional Neural Network (GCN) model is developed, to learn CECI from a repository of 3D scene graphs. As no database of 3D scene graphs exists for the training of the novel CECI model, we present a novel methodology for generating a 3D scene graph dataset based on semantically annotated real-life 3D spaces. The generated dataset is then utilized to train the proposed CECI model and for extensive validation of the proposed method. We establish the novel concept of \textit{Belief Scene Graphs} (BSG), as a core component to integrate expectations into abstract representations. This new concept is an evolution of the classical 3D scene graph concept and aims to enable high-level reasoning for the task planning and optimization of a variety of robotics missions. The efficacy of the overall framework has been evaluated in an object search scenario, and has also been tested on a real-life experiment to emulate human common sense of unseen-objects.

This article presents a novel approach to identifying and classifying intersections for semantic and topological mapping. More specifically, the proposed novel approach has the merit of generating a semantically meaningful map containing intersections, pathways, dead ends, and pathways leading to unexplored frontiers. Furthermore, the resulting semantic map can be used to generate a sparse topological map representation, that can be utilized by robots for global navigation. The proposed solution also introduces a built-in filtering to handle noises in the environment, to remove openings in the map that the robot cannot pass, and to remove small objects to optimize and simplify the overall mapping results. The efficacy of the proposed semantic and topological mapping method is demonstrated over a map of an indoor structured environment that is built from experimental data. The proposed framework, when compared with similar state-of-the-art topological mapping solutions, is able to produce a map with up to 89% fewer nodes than the next best solution.

In this article, we propose a novel LiDAR and event camera fusion modality for subterranean (SubT) environments for fast and precise object and human detection in a wide variety of adverse lighting conditions, such as low or no light, high-contrast zones and in the presence of blinding light sources. In the proposed approach, information from the event camera and LiDAR are fused to localize a human or an object-of-interest in a robot's local frame. The local detection is then transformed into the inertial frame and used to set references for a Nonlinear Model Predictive Controller (NMPC) for reactive tracking of humans or objects in SubT environments. The proposed novel fusion uses intensity filtering and K-means clustering on the LiDAR point cloud and frequency filtering and connectivity clustering on the events induced in an event camera by the returning LiDAR beams. The centroids of the clusters in the event camera and LiDAR streams are then paired to localize reflective markers present on safety vests and signs in SubT environments. The efficacy of the proposed scheme has been experimentally validated in a real SubT environment (a mine) with a Pioneer 3AT mobile robot. The experimental results show real-time performance for human detection and the NMPC-based controller allows for reactive tracking of a human or object of interest, even in complete darkness.