In this article, we propose a novel deep reinforcement learning (DRL) approach for controlling multiple unmanned aerial vehicles (UAVs) with the ultimate purpose of tracking first responders (FRs) in challenging 3-D environments presence obstacles and occlusions. We assume that UAVs receive noisy distance measurements from FRs which are two types, i.e., Line Sight (LoS) non-LoS (NLoS) used by UAV agents order to estimate state (i.e., position) FRs. Subsequently, proposed DRL-based controller...

This work proposes a coverage controller that enables an aerial team of distributed autonomous agents to collaboratively generate non-myopic plans over rolling finite horizon, aiming cover specific points on the surface area three-dimensional object interest. The collaborative problem, formulated as model predictive control optimizes agents' motion and camera inputs, while considering inter-agent constraints at reducing redundancy. proposed integrates based light-path propagation techniques...

We propose the Cooperative Aerial Robot Inspection Challenge (CARIC), a simulation-based benchmark for motion planning algorithms in heterogeneous multi-UAV systems. CARIC features UAV teams with complementary sensors, realistic constraints, and evaluation metrics prioritizing inspection quality efficiency. It offers ready-to-use perception-control software stack diverse scenarios to support development of task allocation algorithms. Competitions using were held at IEEE CDC 2023 IROS 2024...

Indoor positioning systems have received a lot of attention recently due to their importance for many location-based services, e.g. indoor navigation and smart buildings. Lightweight solutions based on WiFi inertial sensing gained popularity, but are not fit demanding applications, such as expert museum guides industrial settings, which typically require sub-meter location information. In this paper, we propose novel system, RAVEL (Radio And Vision Enhanced Localization), fuses anonymous...

Drones, including remotely piloted aircraft or unmanned aerial vehicles, have become extremely appealing over the recent years, with a multitude of applications and usages. However, they can potentially present major threats for security public safety, especially when fly across critical infrastructures spaces. This work investigates novel counter-drone solution by proposing multi-agent framework in which team pursuer drones cooperate order to track jam rogue drone. Within proposed...

Coverage path planning with unmanned aerial vehicles (UAVs) is a core task for many services and applications including search rescue, precision agriculture, infrastructure inspection surveillance. This work proposes an integrated guidance gimbal control coverage (CPP) approach, in which the mobility inputs of autonomous UAV agent are jointly controlled optimized to achieve full given object interest, according specified set optimality criteria. The proposed approach uses visibility...

In this work, a novel distributed search-planning framework is proposed, where dynamically varying team of autonomous agents cooperate in order to search multiple objects interest three-dimension (3-D). It assumed that the can enter and exit mission space at any point time, as result number actively participate varies over time. The proposed takes into account agent dynamical sensing model, agents, utilizes model predictive control (MPC) generate cooperative trajectories finite rolling...

To date, the majority of positioning systems have been designed to operate within environments that long-term stable macro-structure with potential small-scale dynamics. These assumptions allow existing produce and utilize maps. However, in highly dynamic industrial settings these are no longer valid task tracking people is more challenging due rapid large-scale changes structure. In this paper we propose a novel system for environments, such as construction sites. The proposed leverages...

In this paper we propose a novel algorithm for tracking people in highly dynamic industrial settings, such as construction sites. We observed both short term and long changes the environment; were allowed to walk different parts of site on days, field view fixed cameras changed over time with addition walls, whereas radio magnetic maps proved unstable movement large structures. To make things worse, uniforms helmets that wear safety them very hard distinguish visually, necessitating use...

In this work a robust and scalable cooperative multi-agent searching tracking framework is proposed. Specifically, we study the problem of multiple moving targets by group autonomous mobile agents with limited sensing capabilities. We assume that actual number present not known priori target births/deaths can occur anywhere inside surveillance region thus efficient search strategies are required to detect track as many possible. To address aforementioned challenges recursively compute...

We propose a novel probabilistically robust controller for the guidance of an unmanned aerial vehicle (UAV) in coverage planning missions, which can simultaneously optimize both UAV's motion, and camera control inputs 3D given object interest. Specifically, problem is formulated this work as optimal with logical constraints to enable UAV agent jointly: a) select series discrete field-of-view states satisfy set constraints, b) its motion according specified mission objective. show how hybrid...

In this paper, we investigate the problem of joint searching and tracking multiple mobile targets by a group agents. The appear disappear at random times inside surveillance region their positions are unknown. agents have limited sensing range receive noisy measurements from targets. A decision control arises, where mode operation (i.e., search or track) as well mobility action for each agent, time instance, must be determined so that collective goal is achieved. We build our approach upon...

The ability to efficiently plan and execute search missions in challenging complex environments during natural man-made disasters is imperative. In many emergency situations, precise navigation between obstacles time-efficient searching around 3D structures essential for finding survivors. this work we propose an integrated assessment planning approach which allows autonomous UAV (unmanned aerial vehicle) agent collision-free trajectories environments. More specifically, the proposed...

Nowadays, unmanned aerial vehicles or UAVs are being used for a wide range of tasks, including infrastructure inspection, automated monitoring and coverage. This paper investigates the problem 3D inspection planning with an autonomous UAV agent which is subject to dynamical sensing constraints. We propose receding horizon control approach generating optimal trajectories enable inspect finite number feature-points scattered on surface cuboid-like structure interest. The formulated as...

In this paper we study the problem of cooperative searching and tracking (SAT) multiple moving targets with a group autonomous mobile agents that exhibit limited sensing capabilities. We assume actual number is not known priori target births/deaths can occur anywhere inside surveillance region. For reason efficient search strategies are required to detect track as many possible. To address aforementioned challenges augment classical Probability Hypothesis Density (PHD) filter ability...

This work proposes a novel distributed control framework in which team of pursuer agents equipped with radio jamming device cooperate order to track and radio-jam rogue target 3D space, the ultimate purpose disrupting its communication navigation circuitry. The evolves space according stochastic dynamical model it can appear disappear from surveillance area at random times. estimate probability existence spatial density set noisy measurements presence clutter. Additionally, proposed allows...

This work proposes a receding horizon coverage control approach which allows multiple autonomous aerial agents to cooperatively in order cover the total surface area of 3D object interest. The cooperative problem is posed this as an optimal problem, jointly optimizes agents' kinematic and camera inputs, while considering coupling constraints amongst team aim at minimizing duplication work. To generate look-ahead trajectories over finite planning horizon, proposed integrates visibility into...

In this paper we are interested in the task of searching and tracking multiple moving targets a bounded surveillance area with group autonomous mobile agents. More specifically, assume that can appear disappear at random times inside region their positions unknown. The agents have limited sensing range, due to sensor imperfections they receive noisy measurements from targets. work utilize theory finite sets (RFS) capture uncertainty time-varying number states propose decision control...

This work investigates the problem of simultaneous tracking and jamming a rogue drone in 3D space with team cooperative unmanned aerial vehicles (UAVs). We propose decentralized estimation, decision control framework which UAVs cooperate order to a) optimally choose their mobility actions that result accurate target b) select desired transmit power levels cause uninterrupted radio thus ultimately disrupt operation drone. The proposed allows reconfigure themselves such (CSTJ) objective is...

This work introduces a cooperative inspection system designed to efficiently control and coordinate team of distributed heterogeneous UAV agents for the 3D structures in cluttered, unknown spaces. Our proposed approach employs two-stage innovative methodology. Initially, it leverages complementary sensing capabilities robots cooperatively map environment. It then generates optimized, collision-free paths, thereby ensuring comprehensive coverage structure's surface area. The effectiveness our...

Fault-tolerant coverage control involves determining a trajectory that enables an autonomous agent to cover specific points of interest, even in the presence actuation and/or sensing faults. In this work, encounters inputs are erroneous; specifically, its nominal controls perturbed by stochastic disturbances, potentially disrupting intended operation. Existing techniques have focused on deterministically bounded disturbances or relied assumption Gaussian whereas non-Gaussian been primarily...