Self-adaptation can be used in robotics to increase system robust- ness and reliability. This work describes the Metacontrol method for self-adaptation in robotics. Particularly, it details how the MROS (Metacontrol for ROS Systems) framework implements and pack- ages Metacontrol, and it demonstrate how MROS can be applied in a navigation scenario where a mobile robot navigates in a factory floor. Video: https://www.youtube.com/watchvISe9aMskJuE

@en

Known attempts to build autonomous robots rely on complex control architectures, often implemented with the Robot Operating System platform (ROS). The implementation of adaptable architectures is very often ad hoc, quickly gets cumbersome and expensive. Reusable solutions that support complex, runtime reasoning for robot adaptation have been seen in the adoption of ontologies. While the usage of ontologies significantly increases system reuse and maintainability, it requires additional effort from the application developers to translate requirements into formal rules that can be used by an ontological reasoner. In this paper, we present a design tool that facilitates the specification of reconfigurable robot skills. Based on the specified skills, we generate corresponding runtime models for self-adaptation that can be directly deployed to a running robot that uses a reasoning approach based on ontologies. We demonstrate the applicability of the tool in a real robot performing a patrolling mission at a university campus.

@en

Autonomous systems are expected to maintain a dependable operation without human intervention. They are intended to fulfill the mission for which they were deployed, properly handling the disturbances that may affect them. Underwater robots, such as the UX-1 mine explorer developed in the UNEXMIN project, are paradigmatic examples of this need. Underwater robots are affected by both external and internal disturbances that hamper their capability for autonomous operation. Long-term autonomy requires not only the capability of perceiving and properly acting in open environments but also a sufficient degree of robustness and resilience so as to maintain and recover the operational functionality of the system when disturbed by unexpected events. In this article, we analyze the operational conditions for autonomous underwater robots with a special emphasis on the UX-1 miner explorer. We then describe a knowledge-based self-awareness and metacontrol subsystem that enables the autonomous reconfiguration of the robot subsystems to keep mission-oriented capability. This resilience augmenting solution is based on the deep modeling of the functional architecture of the autonomous robot in combination with ontological reasoning to allow self-diagnosis and reconfiguration during operation. This mechanism can transparently use robot functional redundancy to ensure mission satisfaction, even in the presence of faults.

@en

Accurate and reliable localization is crucial to autonomous vehicle navigation and driver assistance systems. This paper presents a novel approach for online vehicle localization in a digital map. Two distinct map matching algorithms are proposed: i) Iterative Closest Point (ICP) based lane level map matching is performed with visual lane tracker and grid map ii) decision-rule based approach is used to perform topological map matching. Results of both the map matching algorithms are fused together with GPS and dead reckoning using Extended Kalman Filter to estimate vehicle's pose relative to the map. The proposed approach has been validated on real life conditions on an equipped vehicle. Detailed analysis of the experimental results show improved localization using the two aforementioned map matching algorithms.

@en

This paper presents an approach for implementing game theoretic decision making in combination with realistic sensory data input so as to allow an autonomous vehicle to perform maneuvers, such as lane change or merge in high traffic scenarios. The main novelty of this work, is the use of realistic sensory data input to obtain the observations as input of an iterative multi-player game in a realistic simulator. The game model allows to anticipate reactions of additional vehicles to the movements of the ego-vehicle without using any specific coordination or vehicle-to-vehicle communication. Moreover, direct information from the simulator, such as position or speed of the vehicles is also avoided.The solution of the game is based on cognitive hierarchy reasoning and it uses Monte Carlo reinforcement learning in order to obtain a near-optimal policy towards a specific goal. Moreover, the game proposed is capable of solving different situations using a single policy. The system has been successfully tested and compared with previous techniques using a realistic hybrid simulator, where the ego-vehicle and its sensors are simulated on a 3D simulator and the additional vehicles' behavior is obtained from a traffic simulator.

@en

This paper presents a game theoretic decision making process for autonomous vehicles. Its goal is to provide a solution for a very challenging task: the merge manoeuvre in high traffic scenarios. Unlike previous approaches, the proposed solution does not rely on vehicle-to-vehicle communication or any specific coordination, moreover, it is capable of anticipating both the actions of other players and their reactions to the autonomous vehicle's movements.

@en

This paper presents a novel tool capable of collecting thermal signatures inside a building by using low-cost IR temperature sensors mounted on-board an aerial platform. The proposed system aims to facilitate the detection of heat loss inside buildings, which is a key aspect for improving energy efficiency in large commercial or industrial buildings. Current detection systems usually require manual labor as well as the use of expensive instrumentation. The proposed system on the other hand, relies on the use of a small unmanned aerial vehicle carrying low-cost thermopile IR sensors. Moreover, the system delivers a fast temperature sensing scheme and it provides coverage to inaccessible areas, thus overcoming the limitations of current mobile platforms which use ground robots. Different experiments were carried out in order to assess the behavior of the sensors as well as to validate the full system. Moreover, the hypothesis that thermopile IR sensors can be used to track temperature signature on-the-fly is validated experimentally with the use of the proposed system over different targets.@en

The constant growth of the population with mobility impairments has led to the development of several gait assistance devices. Among these, smart walkers have emerged to provide physical and cognitive interactions during rehabilitation and assistance therapies, by means of robotic and electronic technologies. In this sense, this paper presents the development and implementation of a human–robot–environment interface on a robotic platform that emulates a smart walker, the AGoRA Walker. The interface includes modules such as a navigation system, a human detection system, a safety rules system, a user interaction system, a social interaction system and a set of autonomous and shared control strategies. The interface was validated through several tests on healthy volunteers with no gait impairments. The platform performance and usability was assessed, finding natural and intuitive interaction over the implemented control strategies.

@en

In this work, we present a decision-making system for automated vehicles driving in highway environments. The task is modeled as a Partially Observable Markov Decision Process, in which the physical states and intentions of surrounding traffic are uncertain. The problem is solved in an online fashion using Monte Carlo tree search. At each decision step, a search tree of beliefs is incrementally built and explored in order to find the current best action for the ego-vehicle. The beliefs represent the predicted state of the world as a response to the actions of the ego-vehicle and are updated using an interaction-and intention-aware probabilistic model. To estimate the long-term consequences of any action, we rely on a lightweight model-based prediction of the scene that assumes risk-averse behavior for all agents. We refer to the proposed decision-making approach as human-like, since it mimics the human abilities of anticipating the intentions of surrounding drivers and of considering the long-term consequences of their actions based on an approximate, common-sense, prediction of the scene. We evaluate the proposed approach in two different navigational tasks: lane change planning and longitudinal control. The results obtained demonstrate the ability of the proposed approach to make foresighted decisions and to leverage the uncertain intention estimations of surrounding drivers.

@en

Robot cooperation is key in Search and Rescue (SaR) tasks. Frequently, these tasks take place in complex scenarios affected by different types of disasters, so an aerial viewpoint is useful for autonomous navigation or human tele-operation. In such cases, an Unmanned Aerial Vehicle (UAV) in cooperation with an Unmanned Ground Vehicle (UGV) can provide valuable insight into the area. To carry out its work successfully, such as multi-robot system requires the autonomous takeoff, tracking, and landing of the UAV on the moving UGV. Furthermore, it needs to be robust and capable of life-long operation. In this paper, we present an autonomous system that enables a UAV to take off autonomously from a moving landing platform, locate it using visual cues, follow it, and robustly land on it. The system relies on a finite state machine, which together with a novel re-localization module allows the system to operate robustly for extended periods of time and to recover from potential failed landing maneuvers. Two approaches for tracking and landing are developed, implemented, and tested. The first variant is based on a novel height-adaptive PID controller that uses the current position of the landing platform as the target. The second one combines this height-adaptive PID controller with a Kalman filter in order to predict the future positions of the platform and provide them as input to the PID controller. This facilitates tracking and, mainly, landing. Both the system as a whole and the re-localization module in particular have been tested extensively in a simulated environment (Gazebo). We also present a qualitative evaluation of the system on the real robotic platforms, demonstrating that our system can also be deployed on real robotic platforms. For the benefit of the community, we make our software open source.@en

This chapter describes a series of works developed in order to integrate ROS-based robots with Unity-based virtual reality interfaces. The main goal of this integration is to develop immersive monitoring and commanding interfaces, able to improve the operator’s situational awareness without increasing its workload. In order to achieve this, the available technologies and resources are analyzed and multiple ROS packages and Unity assets are applied, such as multimaster_fkie, rosbridge_suite, RosBridgeLib and SteamVR. Moreover, three applications are presented: an interface for monitoring a fleet of drones, another interface for commanding a robot manipulator and an integration of multiple ground and aerial robots. Finally, some experiences and lessons learned, useful for future developments, are reported.

@en

One of the active challenges in multi-robot missions is related to managing operator workload and situational awareness. Currently, the operators are trained to use interfaces, but in the near future this can be turned inside out: the interfaces will adapt to operators so as to facilitate their tasks. To this end, the interfaces should manage models of operators and adapt the information to their states and preferences. This work proposes a videogame-based approach to classify operator behavior and predict their actions in order to improve teleoperated multi-robot missions. First, groups of operators are generated according to their strategies by means of clustering algorithms. Second, the operators' strategies are predicted, taking into account their models. Multiple information sources and modeling methods are used to determine the approach that maximizes the mission goal. The results demonstrate that predictions based on previous data from single operators increase the probability of success in teleoperated multi-robot missions by 19%, whereas predictions based on operator clusters increase this probability of success by 28%.@en

This work explores the potential of game theory to solve the task allocation problem in multi-robot missions. The problem considers a swarm with dozens of drones that only know their neighbors, as well as a mission that consists of visiting a series of locations and performing certain activities. Two algorithms have been developed and validated in simulation: one competitive and another cooperative. The first one searches the best Nash equilibrium for each conflict where multiple UAVs compete for multiple tasks. The second one establishes a voting system to translate the individual preferences into a task allocation with social welfare. The results of the simulations show both algorithms work under the limitation of communications and the partial information, but the competitive algorithm generates better allocations than the cooperative one.

@en

This paper presents a study about gait patterns for hexapod robots with extremities called C-legs. The study analyses several modes of gait that different animals use to move through the terrestrial environment, and another new ones that arise when looking at the limitations that present the existing ones. The whole study is reinforced with a series of simulations carried out, where the obtained results are analysed to select the best gait pattern for a specific situation.

@en

The current state of technology permits very accurate 3D reconstructions of real scenes acquiring information through quite different sensors altogether. A high precision modelling that allows simulating any element of the environment on virtual interfaces has also been achieved. This paper illustrates a methodology to correctly model a 3D reconstructed scene, with either a camera RGB-D or a laser, and how to integrate and display it in virtual reality environments based on Unity, as well as a comparison between both results. The main interest regarding this line of research consists in the automation of all the process from the map generation to its visualisation with the VR glasses, although this first approach only managed to get results using several programs manually. The long-term objective would be indeed a real-time immersion in Unity interacting with the scene seen by the camera.

@en

This article presents a new approach to the interception of moving targets in large and complex scenarios. The path planning for interception is based on the Risk-RRT algorithm, which is enhanced by integrating additional information obtained using Fast Marching Method algorithms. Two different techniques based on that method were adapted and integrated within the Risk-RRT, one that obtains the travel distance to the target location and another that estimates the probability of interception at a given point. The proposed approach effectively combines that environmental information with the kinodynamic path planning created by Risk-RRT. The combination of those two algorithms proved to be capable of on-line planning and following an effective interception path, while maintaining the functions of obstacle evasion, handling of uncertainties and reactive navigation.

@en

This article introduces an open source tool for simulating autonomous vehicles in complex, high traffic, scenarios. The proposed approach consists on creating an hybrid simulation, which fully integrates and synchronizes two well known simulators: A microscopic, multi-modal traffic simulator and a complex 3D simulator. The presented software tool allows to simulate an autonomous vehicle, including all its dynamics, sensors and control layers, in a scenario with a very high volume of traffic. The hybrid simulation creates a bi-directional integration, meaning that, in the 3D simulator, the ego-vehicle sees and interacts with the rest of the vehicles, and at the same time, in the traffic simulator, all additional vehicles detect and react to the actions of the ego-vehicle. Two interfaces, one for each simulator, where created to achieve the integration, they ensure the synchronization of the scenario, the state of all vehicles including the ego-vehicle, and the time. The capabilities of the hybrid simulation was tested with different models for the ego-vehicle and almost 300 additional vehicles in a complex merge scenario.

@en

This chapter presents a series of experiences and lessons learned during several implementations and real-world tests of ROS-based Multi-Robot Systems. It also describes, analyses and compares several ROS components relevant for these applications, taking into account the scenarios where they can be used. Also, some general issues of importance of Multi-Robot Systems on real-world, such as software and communications architectures, types of information shared are described in detail. Finally, the difficulties and specific challenges that arose when using a Multi-Robot Systems for any application will be discussed.

@en

This work presents a complete multirobot solution for signal searching tasks in large outdoor scenarios. An evaluation of two different coverage path-planning strategies according to field size and shape is presented. A signal location system developed to simulate mines or chemical source detections is also described. The solution presented is a pioneer in evaluating multimaster robotics operative system architectures with a fleet of robots in real scenarios. This solution minimizes the use of communications bandwidth required for full operation. Finally, field results are provided, and the advantages of the implemented solution are analyzed.@en

This paper presents a pedestrian trajectory prediction technique. Its mail novelty is that it does not require any previous observation or knowledge of pedestrian trajectories, thus making it useful for autonomous surveillance applications. The prediction requires only a set of possible goals, a map of the scenario and the initial position of the pedestrian. Then, it uses two different path planing algorithms to find the possible routes and transforms the similarity between observed and planned routes into probabilities. Finally, it applies a motion model to obtain a time-stamped predicted trajectory. The system has been used in combination with a pedestrian detection and tracking system for real-world tests as well as a simulation software for a large number of executions.@en