Robust autonomous navigation is one of the most important aspects in the acceptance of social robots by elderly users. Traditional model-based navigation techniques provide a stable theoretical and practical foundation for autonomous operation in domestic environments, but fall short in achieving human-like, acceptable behaviour while still being able to robustly navigate cluttered environments. In this work, we propose ClusterNav, a novel learning-based technique for navigation. Our technique consists of teaching the robot how it should move in the environment in a human-like manner, capturing key features of this demonstration in a geometric representation of the environment. This representation is then used to generate new trajectories for execution, allowing the robot move in an acceptable manner. We have tested our technique in a real environment in an elderly care facility, comparing it with the traditional model-based approach. Tests involved both expert and non-expert users teleoperating the robot. Results show that ClusterNav is capable of navigating the environment, achieving better similarity with the reference trajectories and higher execution speed when compared to the model-based approach.

This special issue includes extended versions of selected papers presented in the Intelligent Robotics and Multi-Agent Systems (IRMAS) track of the 34th ACM/SIGAPP Symposium on Applied Computing (S...

The Robotic Darwinian Particle Swarm Optimiza-tion (RDPSO) previously proposed is an evolutionary algorithm that benefits from a natural selection mechanism designed to solve complex tasks (e.g., search and rescue). Yet, the stochastic-ity inherent to this algorithm makes it hard to predict teams' performance under specific situations and, therefore, almost im-possible to synthesize the most rightful configuration (e.g., teamsizes) by means of a trial-and-error approach. This paper gives the first steps towards a predictive model that may be able to capture the RDPSO dynamics and, to some extent, estimate the collective performance of robots. The predictive model pro-posed is represented by a semi-Markov chain being compared to its microscopic counterpart by means of simulation experiments. The results show that the predictive model is able to predict the RDPSO performance with minor discrepancies, presenting itself as a reliable approach to synthesize robotic swarms.

The efficient sharing of information is a commonly overlooked problem in methods proposed for cooperative multi-robot tasks. However, in multi-robot scenarios, especially when the communication network's quality of service is less than desirable, either in bandwidth or reliability, efficient information exchange is a key aspect for the successful deployment of coordinated robotic teams with proper exchange of information.

In this paper, we present a robotic system capable of mapping indoor, cluttered environments and, simultaneously, detecting people and localizing them with respect to the map, in real-time, using solely a Red-Green-Blue and Depth (RGB-D) sensor, the Microsoft Kinect, mounted on top of a mobile robotic platform running Robot Operating System (ROS). The system projects depth measures in a plane for mapping purposes, using a grid-based Simultaneous Localization and Mapping (SLAM) approach, and pre-processes the sensor's point cloud to lower the computational load of people detection, which is performed using a classical technique based on Histogram of Oriented Gradients (HOG) features, and a linear Support Vector Machine (SVM) classifier. Results show the effectiveness of the approach and the potential to use the Kinect in real world scenarios.

Multi-robot patrolling is a problem that has important applications in security and surveillance. However, the optimal task assignment is known to be NP-hard. We consider evenly spacing the robots in a cyclic Traveling Salesman Problem (TSP) tour or partitioning the graph of the environment. The trade-off in performance, overall team travel cost and coordination is analyzed in this paper. We provide both a theoretical analysis and simulation results across multiple environments. The results demonstrate that generally cyclic-based strategies are superior, especially when small teams are used but at the expense of greater team cost, whereas partitioning strategies are especially suitable for larger teams and unbalanced graph topologies. The reported results show that graph topology and team size are fundamental to determine the best choice for a patrol strategy.

The Robotic Darwinian Particle Swarm Optimization (RDPSO) recently introduced in the literature has the ability to dynamically partition the whole population of robots based on simple “punish-reward” rules. Although this evolutionary algorithm enables the reduction of the amount of required information exchange among robots, a further analysis on the communication complexity of the RDPSO needs to be carried out so as to evaluate its scalability. This paper analyses the architecture of the RDPSO communication system, thus describing the dynamics of the communication data packet structure shared between teammates. Moreover, a set of simple communication rules is also proposed in order to reduce the communication overhead within swarms of robots. Experimental results with teams of 15 real robots show that the proposed methodology reduces the communication overhead, thus improving the scalability and applicability of the RDPSO algorithm.

Ensuring a mobile ad-hoc network (MANET) in real and complex environments is an arduous task since the strength of the connection between two robots can rapidly change over time or even disappear. An extension of the Particle Swarm Optimization to multi-robot applications was recently proposed and denoted as Robotic Darwinian PSO (RDPSO). This paper contributes with a further extension of the RDPSO, by integrating a fault-tolerant distributed search in order to prevent communication network splits. To that end, each robot performs packet forwarding according to a paradigm of multi-hop communication, thus maintaining a maximum range or minimum signal quality between its k “best” neighbors. This results in a sum of k virtual forces for each robot to ensure a multi-connected MANET over time. Experimental results with 15 physical robots show that a more fault-tolerant strategy clearly influences the time needed to converge to the final solution but is less susceptible to robot failures.

Despite the focus that multi-robot patrolling has received recently, there is a manifest lack of practical real-world implementations of such systems. Beyond that, the existing ones have been mainly focused on centralized policies to coordinate the team of agents. The present work addresses realistic patrol in indoor environments with teams of arbitrary number of autonomous robots performing a distributed, scalable and fault-tolerant strategy for multi-robot coordination in patrolling missions. Agents decide their actions locally and adapt to the system's needs using distributed communication. The work is validated through experiments in a large indoor real-world environment with a team of autonomous mobile robots.

In most real multi-robot applications, e.g., search-and-rescue, cooperative robots have to fulfill their tasks while driving and communicating among themselves without the aid of a network infrastructure. However, initially deploying autonomously a wireless sensor robot network in a real environment has not taken the proper attention. This paper presents an autonomous and realistic initial deployment strategy, based on a hierarchical approach, in which exploring agents, denoted as scouts, are autonomously deployed through explicit cooperation with supporting agents, denoted as rangers. To evaluate the initial deployment strategy proposed, experimental results with a team of heterogeneous robots are conducted using modified low-cost platforms previously developed by the authors. Preliminary results show the effectiveness of the method and pave the way for a whole series of possible new approaches.

This paper presents a collective foraging algorithm designed to simulate natural selection in a group of swarm robots. The Robotic Darwinian Particle Swarm Optimization (RDPSO) previously proposed is improved using fractional calculus theory and evaluated on real low-cost mobile robots performing a distributed foraging task. This work aims at evaluating this novel exploration strategy, by studying the performance of the algorithm within a population of up to 12 robots, under communication constraints. In order to simulate the maximum allowed communication distance, robots were provided with a list of their teammates' addresses. Experimental results show that only 4 robots are needed to accomplish the proposed mission and, independently on the number of robots, maximum communication distance and fractional coefficient, the optimal solution is achieved in approximately 90% of the experiments.

There are several applications for which it is important to both detect and communicate changes in data models. For instance, in some mobile robotics applications (e.g. surveillance) a robot needs to detect significant changes in the environment (e.g. a layout change) which it may achieve by comparing current data provided by its sensors with previously acquired data (e.g. map) of the environment. This often constitutes an extremely challenging task due to the large amounts of data that must be compared in real-time. This paper proposes a framework to detect, and represent changes through a compact model. The main steps of the procedure are: multi-scale sampling to reduce the computation burden; change detection based on Gaussian mixture models; fitting superquadrics to detected changes; and refinement and optimization using the split and merge paradigm. Experimental results in various real and simulated scenarios demonstrate the approach's feasibility and robustness with large datasets.

The ability to detect perceptions which were never experienced before, i.e. novelty detection, is an important component of autonomous robots working in real environments. It is achieved by comparing current data provided by its sensors with a previously known map of the environment. This often constitutes an extremely challenging task due to the large amounts of data that must be compared in real-time. With respect to previously proposed approaches, this paper detects changes in 3D environment based on probabilistic models, the Gaussian Mixture Model, and a fast and robust combined constraint matching algorithm. The matching allows to represent the scene view as a graph which emerges from the comparison between Mixtures of Gaussians. Finding the largest set of mutually consistent matches is equivalent to find the maximum clique on a graph. The proposed approach has been tested for mobile robotics purposes in real environments and compared to other matching algorithms. Experimental results demonstrate the performance of the proposal.

Finding the longest simple path in a generic undirected graph is a challenging issue that belongs to the NP-Complete class of problems. Four approaches based on genetic algorithms to solve this problem are presented in this article. The first three algorithms proposed use crossover mechanisms between pairs of solutions based on their intersecting regions and the fourth one uses a mutation mechanism on individual solutions, in which the perturbation applied depends on the state of the system. Simulation experiments have been carried out to validate the distinct approaches, which reveal their good performance and provide hints for their application in robotics, packet networks and other fields.

This paper describes an efficient method for retrieving the 3-dimensional shape associated to novelties in the environment of an autonomous robot, which is equipped with a laser range finder. First, changes are detected over the point clouds using a combination of theGaussian mixture model(GMM) and theearth mover's distance(EMD) algorithms. Next, the shape retrieval is achieved using two different algorithms. First, new samplings are generated from each Gaussian function, followed by arandom sampling consensus(RANSAC) algorithm to retrieve geometric primitives. Furthermore, a new algorithm is developed to directly retrieve the shape according to the mathematical space of Gaussian mixture. In this paper, the set of geometric primitives has been limited to the setC = {sphere, cylinder, plane}. The two shape retrieval methods are compared in terms of computational cost and accuracy. Experimental results in various real and simulated scenarios demonstrate the feasibility of the approach.

This article addresses the problem of autonomous map building and exploration of an unknown environment with mobile robots. The proposed method assumes that mobile robots use occupancy grid maps as the main representation model for the built maps and a hill climbing local search algorithm for exploring the environment without any kind of human intervention. It is demonstrated that hill climbing based exploration may recover from local minima and cover completely any environment, if a topological representation of the environment is created incrementally along the mapping and exploration mission. The approach is devised for either a single mobile robot or multiple cooperative mobile robots.

Building cooperatively 3-D maps of unknown environments is one of the application fields of multi-robot systems. This article introduces a distributed architecture, within a probabilistic framework for vision-based 3-D mapping, whereby each robot is committed to cooperate with other robots through information sharing. An entropy-based measure of information utility is defined, which a robot uses for communicating to its teammates the most useful measurements, thus preventing the robot to overwhelm communication resources with redundant information. Experiments with real robots, equipped with stereo-vision, yielded important conclusions about the way robots should cooperate on sharing information.

This article presents an innovative probabilistic approach for building volumetric maps of unknown environments with autonomous mobile robots, which is based on information theory. Each mobile robot uses an entropy gradient-based exploration strategy, with the aim of maximizing information gain when building and improving a 3D map upon measurements yielded by an on-board stereo-vision sensor. The proposed framework was validated through experiments with a real mobile robot equipped with stereo-vision, in order to be further used on cooperative volumetric mapping with teams of mobile robots.