During the execution of Multi-Agent Path Finding (MAPF) plans in real-life applications, the MAPF assumption that the fleet's movement is perfectly synchronized does not apply. Since some of the agents may become delayed due to internal or external factors, it is often necessary to use a robust execution method to avoid collisions caused by desynchronization. Robust execution methods - such as the Action Dependency Graph (ADG) - synchronize the execution of risky actions, but often at the expense of increased plan execution cost, because it may require some agents to wait for the delayed agents. In such cases, the execution's cost can be reduced while still preserving safety by finding a new plan either by rescheduling (reordering the agents at crossroads) or the more general replanning capable of finding new paths. However, these operations may be costly, and the new plan may not even lead to lower execution cost than the original plan: for example, the two plans may be the exact same, as some losses may not be recoverable at all. Therefore, we estimate the benefit that can be achieved by single replanning in scenarios with delayed agents given an immediate state of the execution with a fully connected feed-forward neural network. The input to the neural network is a set of newly designed ADG-based features describing the execution's state and the impact of potential delays, and the output is an estimated benefit achievable by replanning. We train and test the network on a new labeled dataset containing 12,000 experiments and show that our proposed method is capable of significantly reducing the impact of recoverable delays.

Inspection systems utilizing unmanned aerial vehicles (UAVs) equipped with thermal cameras are increasingly popular for the maintenance of photovoltaic (PV) power plants. However, automation of the inspection task is a challenging problem as it requires precise navigation to capture images from optimal distances and viewing angles. This paper presents a novel localization pipeline that directly integrates PV module detection with UAV navigation, allowing precise positioning during inspection. The detections are used to identify the power plant structures in the image. These are associated with the power plant model and used to infer the UAV position relative to the inspected PV installation. We define visually recognizable anchor points for the initial association and use object tracking to discern global associations. Additionally, we present three different methods for visual segmentation of PV modules and evaluate their performance in relation to the proposed localization pipeline. The presented methods were verified and evaluated using custom aerial inspection data sets, demonstrating their robustness and applicability for real-time navigation. Additionally, we evaluate the influence of the power plant model precision on the localization methods.

Uniform and variable environments still remain a challenge for stable visual localization and mapping in mobile robot navigation. One of the possible approaches suitable for such environments is appearance-based teach-and-repeat navigation, relying on simplified localization and reactive robot motion control - all without a need for standard mapping. This work brings an innovative solution to such a system based on visual place recognition techniques. Here, the major contributions stand in the employment of a new visual place recognition technique, a novel horizontal shift computation approach, and a multi-platform system design for applications across various types of mobile robots. Secondly, a new public dataset for experimental testing of appearance-based navigation methods is introduced. Moreover, the work also provides real-world experimental testing and performance comparison of the introduced navigation system against other state-of-the-art methods. The results confirm that the new system outperforms existing methods in several testing scenarios, is capable of operation indoors and outdoors, and exhibits robustness to day and night scene variations.

Teach-and-repeat navigation systems employing advanced visual place recognition techniques for localization exhibit key attributes for long-term mobile robot navigation, such as the ability to operate in unstructured and dynamic environments. However, existing solutions based on deep-learning techniques are computationally demanding, limiting their applicability. This work introduces a novel and efficient teach-and-repeat system built on the modern visual place recognition method MixVPR. Real-world testing demonstrated its ability to operate both indoors and outdoors, achieving robustness and navigation precision comparable to other state-of-the-art systems. In addition, its lower hardware requirements make it suitable for a wide range of robotic platforms and practical applications.

The Electric Vehicle Routing Problem (EVRP) extends the classical Vehicle Routing Problem (VRP) to reflect the growing use of electric and hybrid vehicles in logistics. Due to the variety of constraints considered in the literature, comparing approaches across different problem variants remains challenging. A minimalistic variant of the EVRP, known as the Capacitated Green Vehicle Routing Problem (CGVRP), was the focus of the CEC-12 competition held during the 2020 IEEE World Congress on Computational Intelligence. This paper presents the competition-winning approach, based on the Variable Neighborhood Search (VNS) metaheuristic. The method achieves the best results on the full competition dataset and also outperforms a more recent algorithm published afterward.

An accurate and up-to-date model of a photovoltaic (PV) power plant is essential for its optimal operation and maintenance. However, such a model may not be easily available. This work introduces a novel approach for PV power plant mapping based on aerial overview images. It enables the automation of the mapping process while removing the reliance on third-party data. The presented mapping method takes advantage of the structural layout of the power plants to achieve detailed modeling down to the level of individual PV modules. The approach relies on visual segmentation of PV modules in overview images and the inference of structural information in each image, assigning modules to individual benches, rows, and columns. We identify visual keypoints related to the layout and use these to merge detections from multiple images while maintaining their structural integrity. The presented method was experimentally verified and evaluated on two different power plants. The final fusion of 3D positions and semantic structures results in a compact georeferenced model suitable for power plant maintenance.

Re-ranking is the second stage of a visual place recognition task, in which the system chooses the best-matching images from a pre-selected subset of candidates. Model-free approaches compute the image pair similarity based on a spatial comparison of corresponding local visual features, eliminating the need for computationally expensive estimation of a model describing transformation between images. The article focuses on model-free re-ranking based on standard local visual features and their applicability in long-term autonomy systems. It introduces three new model-free re-ranking methods that were designed primarily for deep-learned local visual features. These features evince high robustness to various appearance changes, which stands as a crucial property for use with long-term autonomy systems. All the introduced methods were employed in a new visual place recognition system together with the D2-net feature detector (Dusmanu, 2019) and experimentally tested with diverse, challenging public datasets. The obtained results are on par with current state-of-the-art methods, affirming that model-free approaches are a viable and worthwhile path for long-term visual place recognition.

Widespread demand for mobile robots is pushing the research envelope for the development of new robot driving mechanisms that can handle diverse environments. Bristle-bot-like robot designs, investigated increasingly over the past decade, are based on vibration mechanisms built on flexible legs that enable motion on the ground. However, creating scalable and steerable bristle-bots remains a challenge. Therefore, we developed a new kind of magnetic field-driven bristle-bots with a wireless control and power supply that can be steered and downscaled. Therefore, in our experimental study with a working prototype, we developed a new kind of magnetic field-driven bristle-bot designed for wireless control and power supply. These bristle-bots can thus be steered and downscaled. We verified our concept experimentally using 3D-printed bristle-bots with body-embedded permanent magnets actuated via torque imposed by an external magnetic field. An AC-powered Helmholtz coil generated the bristle-bot's driving field, providing 2D input control, field amplitude, and frequency. A variable number of legs on each side of a bristle-bot's body was used to ensure that each side of these sides has a different frequency response. This asymmetry introduced steerability with a rich set of control commands, including rotations with simultaneous forward and backward locomotion. We also observed side locomotion not yet described in previous studies. The results presented were supported with data from numerous experiments and thorough statistical analysis, indicating promising directions for future bristle-bot development.

Visibility is a fundamental concept in computational geometry, with numerous applications in surveillance, robotics, and games. This software paper presents TřiVis, a C++ library developed by the authors for computing numerous visibility-related queries in highly complex polygonal environments. Adapting the triangular expansion algorithm, TřiVis stands out as a versatile, high-performance, more reliable and easy-to-use alternative to current solutions that is also free of heavy dependencies. Through evaluation on a challenging dataset, TřiVis has been benchmarked against existing visibility libraries. The results demonstrate that TřiVis outperforms the competing solutions by at least an order of magnitude in query times, while exhibiting more reliable runtime behavior. TřiVis is freely available for private, research, and institutional use at https://github.com/janmikulacz/trivis.

When planning missions for autonomous machines in real-world scenarios, such as open-pit mining, painting, or harvesting, it is important to consider how the machines will alter the working environment during their operations. Traditional planning methods treat such changes, like piles built during drilling, as constraints given to the planner that depend on the machine's trajectory. The goal is to find a trajectory that satisfies these constraints. However, our approach formulates the planning problem as finding optimal positions for changes, such as piles, along the machine's trajectory. We propose a heuristic solver and provide extensive experimental evaluations.

The article presents a monocular visual localization system based on fiducial markers for autonomous docking in industrial applications. The design has been tailored for direct use with the docking of a mobile logistic robot under storage racks that requires high robustness, usable accuracy, and easy maintenance at a very low cost. The elaborated solution suggests an innovative calibration tool for determining the positions of used fiducial markers at the docking location, which is based on structure-from-motion reconstruction. Moreover, the paper introduces a localization system calculating the position of the robot relative to the docking location using the Perspective-n-Point Problem solver for the detected markers. The presented approach has been verified for precision and robustness limits in diverse work conditions and quantitatively evaluated in experiments.

Visual classification under uncertainty is a complex computer vision problem. We present a thorough comparison of several variants of convolutional neural network (CNN) classification techniques in the context of ambiguous image data interpretation. We explore possible improvements in classification accuracy achieved by insertion of prior ambiguity information during the annotation process. This enables us to harness known similarities between individual classes and use them as probability distributions for soft ground-truth labels. We also present an approach based on Bayesian CNNs, offering the possibility of further interpretation of classification results in a problem where the neural network model is often considered as a black box. The presented techniques are verified on a practical spot weld inspection problem.

The emerging field of passive macro-scale tile-based self-assembly (TBSA) shows promise in enabling effective manufacturing processes by harnessing TBSA's intrinsic parallelism. However, current TBSA methodologies still do not fulfill their potentials, largely because such assemblies are often prone to errors, and the size of an individual assembly is limited due to insufficient mechanical stability. Moreover, the instability issue worsens as assemblies grow in size. Using a novel type of magnetically-bonded tiles carried by bristle-bot drives, we propose here a framework that reverses this tendency; i.e., as an assembly grows, it becomes more stable. Stability is achieved by introducing two sets of tiles that move in opposite directions, thus zeroing the assembly net force. Using physics-based computational experiments, we compare the performance of the proposed approach with the common orbital shaking method, proving that the proposed system of tiles indeed possesses self-stabilizing characteristics. Our approach enables assemblies containing hundreds of tiles to be built, while the shaking approach is inherently limited to a few tens of tiles. Our results indicate that one of the primary limitations of mechanical, agitation-based TBSA approaches, instability, might be overcome by employing a swarm of free-running, sensorless mobile robots, herein represented by passive tiles at the macroscopic scale.

The tile-based self-assembly is an interesting addition to the additive manufacturing framework. The main idea, utilization of randomness to construct highly ordered structures, puts it apart from the conventional methods. Moreover, it is an interesting (elementary) research topic on its own, since the mechanism is a fundamental driving force in the rise of many natural structures, including living organisms. Although extensively studied mainly in nanotechnology, we perceive a lack of comprehensive studies of the process around a scale of centimeters. Thus, we present an extended experimental study of a chessboard assembly, based on the centimeter-scaled self-assembling system with magnetically bonded tiles. The tiles assemble on a 2D plane while being mechanically excited by an industrial manipulator. Seven significant events that lead to growth or to decay of assemblies are described. Further quantitative analysis confirmed the dependency of assembly progress on the system temperature and suggested lower bounds of an assembly error and upper bounds of assembly sizes for different temperatures.

This paper addresses the problem of multirobot search for a stationary object in ana prioriknown environment. Two variants of the problem are studied given the working environment represented by a graph. The first variant is an extension of the traveling deliveryman problem for multiple vehicles, while the second variant is a generalization of the graph search problem. A novel algorithm is presented to solve both problems, which is based on a combination of greedy randomized adaptive search procedure with variable neighborhood descent. A set of experimental evaluations were conducted over the benchmark instances derived from the TSPLIB library. For both problems, the results obtained show that the proposed approach is comparable to state-of-the-art heuristics. Moreover, for problems of a few hundred vertices, the solution times suggest that the approach is suitable for online decision-making in search and rescue.

Modern logistic solutions for large warehouses consist of a fleet of robots that transfer goods, move racks, and perform other physically difficult and repetitive tasks. The shopfloor is usually enclosed with a safety fence and if a human needs to enter the warehouse all the robots are stopped, as opposed to only the ones in the most immediate vicinity of the human, thus significantly limiting the warehouse efficiency. To tackle this challenge, an integrated safety system is needed with human localization as one of its essential components. In this paper, we propose a novel human localization method for robotized warehouses that is based on a suite of wearable visual sensors installed on a vest worn by humans. The proposed method does not require any modifications of the warehouse environment and relies on the already existing infrastructure. Specifically, we estimate the human location by fusing stereo visual-inertial odometry data and distances to the known absolute poses of the detected ground-markers which robots use for their localization. Fusion is performed by building a pose graph, where we treat estimated human poses relative to markers as graph nodes and odometry estimates as graph edges. We conducted extensive laboratory and warehouse facility experiments, where we tested the reliability and accuracy of the proposed method and compared its performance to a state-of-the-art visual SLAM solution, namely ORB-SLAM2. The results indicate that our method can track absolute position in real-time and has competitive accuracy with respect to ORB-SLAM2, while ensuring higher localization reliability when faced with structural changes in the environment. Furthermore, we provide publicly the experimental datasets to the research community.

The combined efforts of theoretical computer science, biochemistry, and nanotechnology have enabled the design of tile-based systems capable of self-assembling intricate patterns in a massively parallel manner, with low error rates, and applications ranging from DNA computing to microelectronics. However, as the underlying physical and chemical principles do not directly translate from micro to the macroscale, the transition to centimeter-scale systems remains challenging. In this contribution, we propose a framework for designing macroscale passive robots (tiles) capable of targeted self-assembly under uncontrolled external mechanical excitation. Self-assembly at this scale is achieved by using properly designed magneto-mechanical locks (glues) to accomplish jamming-free assembly, a dedicated encoding of glues to guide tile interactions, and consistent formalization of geometrical constraints that ensure the valid assembly. The potential of our framework is demonstrated by the errorless assembly of a chessboard pattern, thereby showing its robustness, three-fold increase in error recovery, and two-fold increase in growth rate, when compared to a fully magnetic approach.

Vision-based navigation is one of the leading tasks in mobile robotics. It, however, introduces additional challenges in long-term autonomy due to its reliance on stable visual features. As such, visual navigation methods are often sensitive to appearance changes and unreliable in environments with low feature density. We present a teach-and-repeat navigation system for unmanned aerial vehicles (UAVs) equipped with a low-end camera. We use a novel visual place recognition methodology based on high-level CNN features to localize a robot on a previously traversed trajectory and to directly calculate heading corrections for navigation. The developed navigation method is fully vision-based and independent of other sensory information, making it universal and easily transferable. The system has been experimentally verified and evaluated with respect to a state-of-the-art ORB2-TaR navigation system. It showed comparable results in terms of its precision and robustness to environmental changes. In addition, the system was able to safely navigate in environments with low feature density and to reliably solve the wake-up robot problem.