Developing a robotic application requires thorough testing of the complete system to ensure its reliability. However, depending on the target environment, real-life testing can be difficult to carry out, which favors simulations. Also, some techniques like those based on machine learning, may require large varieties of sensor data, which can be gathered in simulation with ease, whereas doing the same in real environments can pose a great challenge.This work presents a flexible approach to the procedural generation of tunnel networks suitable for underground robotics simulations. The method starts with a graph representation of an underground environment, and applies a custom meshing strategy to generate tunnels that follow the graph structure. This mesh can then be imported into the desired simulation software. The ease of use of this method allows for the testing of robotic applications in an arbitrary number of different environments in completely automated workflows.

IEEE 802.11 suite of protocols is the de facto standard for wireless local area networks, extending to a wide breadth of application domains. One such domain is robotics and teams of cooperating mobile agents. This is a challenging domain due to ad-hoc links and highly dynamic topology. Improving the use of the Radio-Frequency channel requires some level of coordination of transmissions in time and space. However, achieving this level of coordination requires that the network interface cards (NICs) behave in a predictable manner, at least following the Medium Access Control (MAC) protocol. In this preliminary work we report early intriguing observations with existing NICs that are lenient to interpretations of the standard MAC resulting in different ways to handle interference in the medium. Some NICs do not seem to respect an interference zone as commonly defined and silently impose very different buffering/delay trade-offs, with consequences for overlay protocols, particularly TDMA.

Underground environments are some of the most challenging for autonomous navigation. The long, featureless corridors, loose and slippery soils, bad illumination and unavailability of global localization make many traditional approaches struggle. In this work, a topological-based navigation system is presented that enables autonomous navigation of a ground robot in mine-like environments relying exclusively on a high-level topological representation of the tunnel network. The topological representation is used to generate high-level topological instructions used by the agent to navigate through corridors and intersections. A convolutional neural network (CNN) is used to detect all the galleries accessible to a robot from its current position. The use of a CNN proves to be a reliable approach to this problem, capable of detecting the galleries correctly in a wide variety of situations. The CNN is also able to detect galleries even in the presence of obstacles, which motivates the development of a reactive navigation system that can effectively exploit the predictions of the gallery detection.

Distributed scalable algorithms are sought in many multi-robot contexts. In this work we address the dynamic optimal linear assignment problem, exemplified as a target tracking mission in which mobile robots visually track mobile targets in a one-to-one capacity. We adapt our previous work on formation achievement by means of a distributed simplex variant, which results in a conceptually simple consensus solution, asynchronous in nature and requiring only local broadcast communications. This approach seamlessly tackles dynamic changes in both costs and network topology. Improvements designed to accelerate the global convergence in the face of dynamically evolving task rewards are described and evaluated with simulations that highlight the efficiency and scalability of the proposal. Experiments with a team of three Turtlebot robots are finally shown to validate the applicability of the algorithm.

The performance of any cooperative task that involves two or more robots will be determined by their capacity to recognize common information of the environment. Vision sensors are very effective for this particular goal, but the cost of transmitting the visual information represents a real issue, even more if communication must be performed in narrow bandwidth networks and/or over a multi-hop path. Visual vocabularies provide a dimensionality reduction that has been effectively used in computer vision to reduce the computational load of performing searches in large volumes of data. In this paper we propose to exploit the same technique to decrease the volume of information that is exchanged in the network. This way, robots do not need to send the full descriptors associated to the features they observe, but only the word indices of the corresponding features in the vocabulary. Experiments with a wide variety of vocabularies are used to evaluate the quality of the association given by the algorithm. Finally, real experiments in a wireless network with a limited bandwidth are reported, showing the advantages of the proposed method compared to the communication of full images or feature descriptors.

Supporting real-time traffic in a wireless network is a challenging task due to the high probability of errors and to the interference that can be provoked by other networks in the same area. There may be situations in which alien traffic is present by default and communication systems have to deal with difficulty by adapting their characteristics to provide the highest possible level of timing guarantees and performance. In this paper we propose a technique to make real-time protocols tolerant to alien traffic and able to provide soft real-time behavior even in the presence of high traffic loads, using a variable timeout window that allows belated acknowledgments to be accepted also.

Support for real-time traffic and multi-hop is a basic requirement in certain applications as, for example, cooperative robot team missions. Normally, point-to-point communication is sufficient to allow such a collaboration. However, there exist situations in which multicast and/or broadcast capabilities, even with real-time requirements, allow a better usage of the available bandwidth leaving more time for unicast communications. This is the case, for example, in which a server generates real-time traffic that has to be delivered to a subset (that can be the whole set) of the nodes of the network. In this paper we present a solution to incorporate the capability of sending multicast messages in token-passing real-time wireless protocols. The solution has been implemented and tested as an extension of RT-WMP (a real-time wireless multi-hop protocol with priority management support). In addition, using these new characteristics, another type of unicast/multicast protocol is proposed, analyzed, evaluated and compared with the plain RT-WMP.

Ad-hoc networks usually support best-effort traffic and occasionally some kind of quality of service (QoS). However, there are some applications, which generally involve cooperative control, with hard real-time traffic requirements where strict deadlines must be met. To meet deadlines, the communication network has to support the timely delivery of inter-task messages. This is the case, for example, of applications involving cooperative robot teams, such as those used for rescue tasks in hostile environments, emergencies or disaster recovery, where a wired backbone is in-feasible or economically unviable. In this paper, we present RT-WMP, a novel protocol that allows wireless real-time traffic in relatively small mobile ad-hoc networks using the low-cost commercial 802.11 technology. The protocol is based on a token-passing approach and message exchange is priority based. Moreover, support for frequent topology changes is provided through the sharing of a matrix that describes link quality amongst the members of the network.