Search

As robotic systems spread, cybersecurity emerges as major concern. Currently most research autonomous systems are built using the ROS framework, along with other commercial software. ROS is a distributed framework where nodes publish information that other nodes consume. This model simplifies data communication but poses a major threat because a malicious process could easily interfere the communications, read private messages or even supersede nodes. In this paper we propose that ROS communications should be encrypted. We also measure how encryption affects its performance.We have used 3DES cyphering algorithm and we have evaluated the performance of the system, both from the computing and the communications point of view. Preliminary results show that symmetric ciphers using private keys impose significant delays

—Using information from RGBD sensors requires huge amount of processing. To use these sensors improves the robustness of algorithms for object perception, self-localization and, in general, all the capabilities to be performed by a robot to improve its autonomy. In most cases, these algorithms are not computationally feasible using single-thread implementations. This paper describes two multi thread strategies proposed for self localize a mobile robot in a known environment using information from a RGBD sensor. The experiments will show the benefits obtained when different numbers of threads are compared, using different approaches: a pool of threads and creation/destruction scheme. The work has been carried out on a Kobuki mobile robot in the environment of the RoCKiN competition, similar to RoboCup@home

This article exposes the localization issues faced during the implementation of a humanoid goalkeeper to take part in the RoboCup SPL standardized soccer robot competition. For this task, we have used BICA, a state-driven, component-based architecture created by our counterparts in the URJC, to allow a much easier behavior design process. The use of BICA let us choose different self-localization methods in configuration time, and the possibility of using none in running time if some type of error appears

Visual attention is a natural tool which allows animals to locate relevant objects or areas in a given scene, discarding the rest of elements present and thus reducing the amount of information to deal with. In this paper we present the design an implementation of a visual attention mechanism based on a saliency map and its implementation in the Nao humanoid. This control mechanism is applied to solve one of the challenges proposed in the RoboCup competition named ”any-ball”. The results obtained are analysed and future works derived from that analysis are presented

The main goal of the project described in this paper is to create a security system using autonomous surveillance robots that use SODAR-like detection system sensors, working with acoustic signals in air environment and navigation base on Geographic Information System and Markov's models. The surveillance system based on SONAR provides great information from the environment, even lets you see behind objects (rebounds effects) whose manipulation offers a great added value to surveillance The guide system will implement in one hand a local navigation module directed to avoid obstacles based on classical techniques and using the new SODAR sensor. On the other hand a global navigation module will be implemented using preset trajectories and gradient techniques and an auto-location system. One of the greatest challenges obtained is the definition of the VIGICOPVar variable that defines, depending on the environment and safety parameters, the probability of intrusion. Surveillance experts of GRUPO NORTE (multinational company with security expertise of more than 38 years) have worked In the definition and validation of the model. The monitoring robots will be controlled in a centralized way from an alarm center from where you can manage all information relating to intrusion detected. VIGICOP is the low cost surveillance robot which provides new/full information interactive surveillance information

Attention mechanism can be used both for reducing the amount of perceptual information to be processed and for restricting all available actions to only those useful for a given scenario. Information reduction improves performance and action restriction allows for a more precise interaction with our environment. In this paper we present the design of an attention control mechanism based on a saliency map and its implementation in the SPL's Nao robot. The results obtained are analysed and future works derived from that analysis are presented

This paper addresses the problem of determining the current 3D location of a moving object and robustly tracking it from a sequence of camera images. The approach presented here uses a particle filter and does not perform any explicit triangulation. Only the color of the object to be tracked is required, but not any precisemotion model. The observation model we have developed avoids the color filtering of the entire image. That and the Monte Carlotechniques inside the particle filter provide real time performance.Experiments with two real cameras are presented and lessons learned are commented. The approach scales easily to more than two cameras and new sensor cues., {"references":["D. Gorodnichy, S. Malik and G. Roth, Affordable 3D face tracking using\nprojective vision, Proc. of Int. Conf. on Vision Interface, pp. 383-390,\nCalgary (Canada) May 2002.","A.J. Davison, Y. Gonzalez-Cid and N. Kita, Real-time 3D SLAM\nwith wide-angle vision, 5th IFAC/EURON Symposium on Intelligent\nAutonomous Vehicles, July 2004.","D. Margaritis and S. Thrun, Learning to locate an object in 3D space\nfrom a sequence of images. Proc. of Int. Conf. on Machine Learning, pp.\n332-340, 1998.","D. Fox, W. Burgard, F. Dellaert and S. Thrun, Monte Carlo localization:\nefficient position estimation for mobile robots, In Proc. of 16th. AAAI\nNat. Conf. on Artificial Intelligenge, pp. 343-349, Orlando (USA), July\n1999","S. Arulampalam, S. Maskell, N. Gordon and T. Clapp, A tutorial on\nparticle filters for on-line non-linear/non-gaussian bayesian tracking,\nIEEE Transactions on Signal Processing, vol. 50, no. 2, pp. 174-188,\n2002.","A.M. Boumaza and J. Louchet, Mobile robot sensor fusion using flies\nIn G├╝nter Raidl et.al. editors, Applications of Evolutionary Computing,\nEvo Workshops 2003, Lecture Notes in Computer Science, vol. 2611, pp.\n357-367, Springer, 2003.","Jean Louchet, Using an individual evolution strategy for stereovision,\nGenetic Programming and Evolvable Machines, vol. 2, pp. 101-109, 2001","M. Isard and A. Blake, CONDENSATION- conditional density propagation\nfor visual tracking, Int. Journal of Computer Vision, vol. 20, no. 1,\npp. 5-28, 1998.","P. Perez, J. Vermaak and A. Blake, Data fusion for visual tracking with\nparticles, Proceedings of IEEE, vol. 92, no. 3, pp. 495-513, March 2004.\n[10] D. Mackay, Introduction to Monte Carlo methods, In M. Jordan editor,\nLearning in graphical models, pp. 175-204, MIT Press, 1999\n[11] A. J. Davison, Real-time simultaneous localisation and mapping with\na single camera, IEEE Int. Conf. on Computer Vision, ICCV-2003, pp.\n1403-1410, Nice (France), October 2003.\n[12] R.T. Collins, Multi-image focus of attention for rapid site model construction,\nIEEE Int. Conf. on Computer Vision and Pattern Recognition,\n1997, pp. 575-581, San Juan, Puerto Rico, June 1007."]}

P. 307-320 Mobile robots need to be able to communicate among themselves, as well as with hosts participating in the task that they are all involved in. Wired networks are obviously not suitable for mobile robots. Current wireless networks based on a fixed infrastructure (GSM, WiFi, etc.) to route packets may not be suitable because this infrastructure does not cover every place and the requirements of its resources. The best choice for mobile robots are Ad-Hoc networks, which are wireless and do not need a fixed infrastructure. This article describes PERA, a complete communications library including link, net, and transport layers for mobile robots with reduced communications capacity. The network layer is based on a well-known ad-hoc routing protocol adapted to limited devices. This protocol has been implemented and tested on EyeBot mobile robots. Robots using PERA can send messages to other robots or hosts that are not directly reachable through their radio antenna range, by routing messages through intermediate mobile robots also running PERA. The design, implementation, testing and lessons learned in the development of PERA are presented in this article SI

P. 125-132 Manual systems require the user/programmer to directly enter the desired behaviour of the robot, usually using a graphical or text-based programming language, as shown in Fig. 1. Text-based systems are either controller-specific languages, generic procedural languages, or behavioural languages, which typically differ by the flexibility and method of expression of the system. Graphical languages [BKS02, BI01] use a graph, flow-chart or diagram based graphical interface to programming, sacrificing some flexibility and expressiveness for ease of use. The user/programmer has little or no direct control over the robot code in an automatic programming system, which may acquire the program by learning, programming by demonstration (PbD), or by instruction, as indicated in Fig. 2. Often automatic systems are used “online,” with a running robot, although a simulation can also be used. In this sidebar we will focus on the characteristics of commercial programming environments. Simple robots can be programmed directly using their own operating systems. More sophisticated robots include SDKs to simplify the programming of their robots. Mobile robots programming environments vs. industrial manipulators are also presented

Communications are the basis for the collaborative activities in the TeamChaos 4-legged team. In this paper we present the communications architecture developed both to let teammates communicate, and to easy the debugging of robot behaviors from external computers. Details of its implementation on the aiBo robots are also given. Using this infrastructure we describe a protocol for role exchange named Switch! that we have created. We also describe the use of both the communication architecture, and the Switch! protocol in the passing challenge of the 2006 edition of the RoboCup

Mobile robots need to represent obstacles in their surroundings, even moving ones, to make right movement decisions. For higher autonomy the robot should automatically build such representation from its sensory input. This paper compares the dynamic character of several gridmap building techniques: probabilistic, fuzzy, theory of evidence and histogramic. Two criteria are defined to rank such dynamism in the representation: time to show a new obstacle and time to show a new hole. The update rules for first three such techniques hold associative property which confers them static character, inconvenient for dynamic environments. Major contribution of this paper is the introduction of two new approaches are presented to improve the perception of mobile obstacles: one uses a differential equation to update the map and another uses majority voting in a limited memory per cell. Their dynamisms are also evaluated and the results presented.

This paper presents a visual based localization mechanism for a legged robot in indoor office environments. Our proposal is a probabilistic approach which uses partially observable Markov decision processes. We use a precompiled topological map where natural landmarks like doors or ceiling lights are recognized by the robot using its on-board camera. Experiments have been conducted using the AIBO Sony robotic dog showing that it is able to deal with noisy sensors like vision and to approximate world models representing indoor office environments. The major contributions of this work is the use of an active vision as the main input and localization in not-engineered environments

JDE is an ethology inspired architecture for designing applications both in autonomous and teleoperated robots. In this paper we will outline the JDE architecture, present some tools included in the JDE suite and show several examples of different applications built using it. Experiments carried out using this suite will be described and the obtained results discussed. We will make emphasis on the Graphical User Interfaces of the examples, like those in Fig. 1. JDE suite provides a exible way to build such interfaces and controls the execution time devoted to them in the applications. The GUIs provide visual objects to graphically command the actuators and to display the sensor data, like laser, sonar, encoders readings or images from robot cameras. Using them, JDE lets us operate and monitor different mobile robots where monitorization or tele-operation is required. The GUIs also allow the visualization of internal states and structures of the control program, and so they are a useful tool for debugging. JDE suite includes two socket servers (oculo and otos) which provide sensors readings and motor commands. These servers can be used both locally or remotely, which makes them really convenient for tele-operation and tele-supervision. They de ne a standard mes- sage protocol which eases the development of new applications and their portability across dfferent robot platforms

Software is one of the major components of robots; in fact, it is the main bottleneck for the proliferation of robotics in our everyday lives. In the last years the field of robotics has been an emerging application area of the libre (free/open source) software phenomenon. Libre software tools have been traditionally popular among the robotics research and teaching community. Even companies whose main business model is to sell robots have found convenient to share the software in order to promote a community around their products. In this paper we analyze the situation of libre software in these three subareas: industry, teaching and research. In particular, we describe commercial robots like the Cye and the Pioneer, a software platform like Orocos as a examples of industrial world applications, the libre tools around the LEGO Mindstorms in the case of teaching, and the Robocup competition and the Player/Stage platform in research area. All these cases show that libre software can act as a catalyst in the robotics industry which is still a sector in its early research and industrial stages

Current ad-hoc network protocols are designed for host similar to those used in fixed networks. Those protocols are not adequate for some applications of ad-hoc networks, where used resources are very scarce. One example is the size of the network addresses, which may be a critical issue, specially whit the use of IPv6 in DRS. This is due to the fact that this protocol uses souece ruoting, so each datagram must carry the sddresses of all the machines in its path. In this paper a new protocol named ADSR is proposed the solve this problem. This new protocol is a modified version of DSR based on using abbreviated addresses. The abreviation procedure can lead to two different nodes having the same address, what we will named "collision"

This paper describes a method to estimate the position of a mobile robot in an indoor scenario using the odometric calculus and the WiFi energy received from the wireless infrastructure. This energy will be measured by wireless network card on-board a mobile robot, and it will be used as another regular sensor to improve position estimation. The Bayes rule will be used to accumulate localization probability as the robot moves on. In this paper several experiments in a university building are shown. The two major contributions of the presented work are that the self-localization error achieved is bounded, and that no significant degradation is observed when the theoretical WiFi energy at each point is taken from radio propagation model instead of an a priori experimental intensity map of the environment

Libre software projects offer abundant information about themselves in publicly available storages (source code snapshots, CVS repositories, etc), which are a good source of quantitative data about the project itself, and the software it produces. The retrieval (and partially the analysis) of all those data can be automated, following a simple methodology aimed at characterizing the evolution of the project. Since the base information is public, and the tools used are libre and readily available, other groups can easily reproduce and review the results. Since the characterization offers some insight on the details of the project, it can be used as the basis for qualitative analysis (including correlations and comparative studies). In some cases, this methodology could also be used for proprietary software (although usually losing the benefits of peer review). This approach is shown, as an example, applied to MONO, a libre software project implementing parts of the .NET framework

This article describes two vision-based behaviors designed for an autonomous robot. These behaviors have been designed and implemented using schemas according to an architecture named DSH (Dynamic Schema Hierarchies), which is also briefly described. The reactive behaviors implemented have been tested in our robotic soccer players, running in EyeBot commercial platforms. The developed behaviors provide the robot with the follow ball, and the follow border capabilities, using only the local camera and the robot on-board low processing power. The design of the control schemas, the algorithms used to analyze the images in perceptual schemas and relevant implementation issues are also described in this paper

When facing the problem of teaching the basis of robot control programming to computer science students, apart from the syllabus of the course, some other requirements have to be taken into account. For instance, which are the most appropriate robotic platforms, and which are the best programming tools for teaching it. In this paper we describe the platforms and programming environments chosen for different senior and graduate robotic courses at Rey Juan Carlos University, focusing on the reasons under our choices. We also point out the practical assignments demanded on the courses. Finally, we will present the results along four years, the feedback from our students, and the lessons we have learned

Robots are just starting to appear in peopled environments but in order to be accepted by humans, they should obey basic people’s social rules. In particular, they have to be able to move around without disturbing people. This means that they have to obey the social rules that manage the movement of people, for example following virtual lanes when moving through corridors, not crossing in front of moving people, etc. In this paper some of these aspects are explained, as well as the implementation of preliminaries works to implement the proposed solutions are described. So, a slight modification to the Lane-Curvature Method is presented to improve the behavior of a mobile robot when crossing people in a corridor. Other works needed to test this modifications in the robot Amelia of the Reliable Autonomous Systems Lab, as the implementation of a fuzzy controller, are also described in this paper

P. 76-80 During 1991 and 1992, the landscape of libre software, and of software development in general, was ready for a change. In two D different communities, two very exciting events were taking place: 386BSD, a libre derivative of the BSD code, was born, and Linus Torvalds distributed the first versions of the Linux kernel. Soon after, the software community had two libre operating systems at its disposal (for some basic references to online information on libre products and distribu- tion, see the “Online Resources” and “Terminology” sidebars) SI

Different models have been proposed to build systems that adapt to the user reducing the complexity in the information browsing process, saving user time and offering personalised interfaces. The work described in this paper, named \wz, is an example of adaptive system specially built for accessing digital libraries. A fuzzy decision mechanism is used to implement the adaptation of both the user interface and the information searching process. This paper describes how this system has been designed and implemented, focusing on its fuzzy-based components. Finally, it also briefly discusses the advantages of using fuzzy logic to implement adaptability of the user interface and the searching process.

P. 33-41 This paper concerns the learning of basic behaviors in an autonomous robot. It presents a method to adapt basic reactive behaviors using a genetic algorithm. Behaviors are implemented as fuzzy controllers and the genetic algorithm is used to evolve their rules. These rules will be formulated in a fuzzy way using prefixed linguistic labels. In order to test the rules obtained in each generation of the genetic evolution process, a real robot has been used. Numerical results from the evolution rate of the different experiments, as well as an example of the fuzzy rules obtained, are presented and discussed SI

This paper presents a model for the control of autonomous robots that allows cooperation among them. The control structure is based on a general purpose multi-agent architecture using a hybrid approach made up by two levels. One level is composed of reactive skills capable of achieving simple actions by their own. The other one uses an agenda used as an opportunistic planning mechanism to compound, activate and coordinate the basic skills. This agenda handles actions both from the internal goals of the robot or from other robots. This two level approach allows the integration of real-time response of reactive systems needed for robot low-level behavior, with a classical high level planning component that permits a goal oriented behavior. The paper describes the architecture itself, and its use in three different domains, including real robots, as well as the issues arising from its adaptation to the RoboCup simulator domain

This paper presents an architecture for the control of autonomous systems that allows cooperation among them This paper focuses on the description of the upper layers of the model The control structure is based on a general purpose multi agent architecture based on a two levels approach One level is composed of reactive skills capable of achieving simple actions by their own The other one is an agenda used as an opportunistic planning mechanism to compound activate and coordinate the basic skills This agenda handles actions both from the internal goals of the robot or from other robots

This paper presents an architecture for the control of simulated robots for the RoboCup that allows explicit cooperation among them. The structure of the software agents controlling the robots is based on a general porpuse multiagent architecture based on a two level approach. One level is composed of reactive skills capable of archieving simple actions by their own. The other is based on a agenda used as an opportinistic planning mechanism to compound, activate and coordinate the basic skills. This agenda handles actions both from the internals goals of the robot or from other robots. This paper describes the work already accomplished, as well as the issues arising from the implementation of the architecture

In this paper a fuzzy interaction among robots in a group is presented as an alternative solution to the classical protocols used in architectures for the cooperation of robots. In order to achieve this goal, the integration of previous works carried out on fuzzy behaviors and on cooperative architectures at the Intelligent Agents Lab. (LAI) has been used. This cooperation/coordination protocol is necessary to successfully control a group of autonomous robots. The protocol will take into account the fuzzy controllers used in the design of the robots. Three different fuzzy protocols have been considered and tested, both in a simulator and in real robots. The results of the experiments carried out and the conclusions obtained are presented.