2015 12th Latin American Robotics Symposium and 2015 3rd Brazilian Symposium on Robotics (LARS-SBR)最新文献

{"title":"Using Reinforcement Learning to Improve the Stability of a Humanoid Robot: Walking on Sloped Terrain","authors":"I. J. Silva, D. Perico, T. P. D. Homem, Claudio O. Vilão, Flavio Tonidandel, Reinaldo A. C. Bianchi","doi":"10.1109/LARS-SBR.2015.41","DOIUrl":"https://doi.org/10.1109/LARS-SBR.2015.41","url":null,"abstract":"In order to perform a walk on a real environment, humanoid robots need to adapt themselves to the environment, as humans do. One approach to achieve this goal is to use Machine Learning techniques that allow robots to improve their behavior with time. In this paper, we propose a system that uses Reinforcement Learning to learn the action policy that will make a robot walk in an upright position, in a lightly sloped terrain. To validate this proposal, experiments were made with a humanoid robot - a robot for the RoboCup Humanoid League based on DARwIn-OP. The results showed that the robot was able to walk on sloping floors, going up and down ramps, even in situations where the slope angle changes.","PeriodicalId":360398,"journal":{"name":"2015 12th Latin American Robotics Symposium and 2015 3rd Brazilian Symposium on Robotics (LARS-SBR)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122426482","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"GPU-Services: Real-Time Processing of 3D Point Clouds for Robotic Systems Using GPUs","authors":"Leonardo Christino, Fernando Santos Osório","doi":"10.1109/LARS-SBR.2015.50","DOIUrl":"https://doi.org/10.1109/LARS-SBR.2015.50","url":null,"abstract":"The GPU-Services project fits into the context of research and development of methods for data processing of three-dimensional sensors data applied to mobile robotics. Such methods are called services on this project, which include 3D point clouds pre-processing algorithms, segmentation of the data, separation and identification of planar zones (ground, roads), and detection of elements of interest (edges, obstacles). Due to the large amount of data to be processed in a short time, these services will use parallel processing elements, using the GPU to perform partial or complete processing of these data. The project aims to provide services for an autonomous car, forcing the services to approach a system for real-time processing, which should complete the whole data processing before the next frame came from the sensors (~10 to 20Hz). The sensor data is structured in the form of a cloud of points, allowing for great parallel processing. However, its major difficulty is the high rate of data received from the sensor (around 700,000 points/sec), and this gives the motivation of this project: to use the full potential of sensor and to efficiently use the parallelism of GPU programming. The GPU services are divided into steps, but always seeking the processing speed given by their intrinsic parallelism: The first step is to organize an environment for parallel processing development in conjunction with the system already being used in our autonomous car, The second step is an intelligent extraction and reorganization of the data provided by the sensor (Velodyne multi-layer laser sensor), The third stage is a pre-segmentation of non-planar data, The fourth stage is performing the segmentation of data received from the previous steps in order to find objects, curbs and ground plane, The fifth stage is to develop a methodology that unite the results of previous steps in order to explore the topology of the environment, i.e. Will aim to structure the results into a topological form (identifying pathways and links between pathways, such as curves and intersections) to assist other projects that focus on vehicle control and autonomous navigation systems.","PeriodicalId":360398,"journal":{"name":"2015 12th Latin American Robotics Symposium and 2015 3rd Brazilian Symposium on Robotics (LARS-SBR)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128254798","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Dense Localization of a Monocular Camera Using Keyframes","authors":"A. Díaz, Eduardo Caicedo Bravo, L. Paz, P. Piniés","doi":"10.1109/LARS-SBR.2015.22","DOIUrl":"https://doi.org/10.1109/LARS-SBR.2015.22","url":null,"abstract":"In this paper, we present a low cost localization system that exploits dense image information to continuously track the position of a camera in 6DOF. It leverages of the use of a set of selected \"key frames\" separated in distance from which a depth map is available to create a local 3D point cloud. In this way, we avoid the computational overload caused by common dense sequential approaches. The system uses a 3D-2D technique to calculate an initial pose estimate for the intermediate camera frames. A refinement step stated as a Non Linear Least Squares (NLQs) optimisation is performed by minimising the photo-consistency error. The NLQs cost function is defined by aligning a warped image and an image associated to the closest key frame. The minimum solution is calculated using the Levenberg-Marquardt method. To validate the accuracy of our system, we conducted experiments using data with perfect ground truth. Our assessment shows that our system is able to achieve up to millimeter accuracy. Most of the expensive calculations are carried out by exploiting parallel computing and GPGPU.","PeriodicalId":360398,"journal":{"name":"2015 12th Latin American Robotics Symposium and 2015 3rd Brazilian Symposium on Robotics (LARS-SBR)","volume":"537 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127061580","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Addressing Escorting by Behavior Combining Using Multiple Differential Drive Robots","authors":"M. R. Batista, A. H. M. Pinto, R. Romero","doi":"10.1109/LARS-SBR.2015.55","DOIUrl":"https://doi.org/10.1109/LARS-SBR.2015.55","url":null,"abstract":"Robot escorting is a challenging task that can be applied to protect a target entity, capturing and to manage leader-follower formations. A linear combination of minimum distance maintenance and area coverage as an obstacle avoidance procedure was shown as an effective tool to escort with a simulated omni directional robot, which can deal easily with the constantly changing outputs generated by this method. In this paper, such approach is applied on differential drive robots to identify particularities of dealing with nonholonomic constraints. Two approaches of inter-robot distancing were tested and a perpendicular circling behavior was added. Experiments were performed using the V-REP simulator.","PeriodicalId":360398,"journal":{"name":"2015 12th Latin American Robotics Symposium and 2015 3rd Brazilian Symposium on Robotics (LARS-SBR)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127462884","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Path Planning and Autonomous Navigation using AMCL and AD*","authors":"L. P. N. Matias, T. C. Santos, D. Wolf, J. Souza","doi":"10.1109/LARS-SBR.2015.31","DOIUrl":"https://doi.org/10.1109/LARS-SBR.2015.31","url":null,"abstract":"Path planning and autonomous navigation are some of the most important challenges in mobile robotics. These are difficult tasks because the robot has to accurately and safely perform autonomous maneuverings. This paper presents a methodology to efficiently plan the trajectory of a robot in dynamic and complex environments, which it should traverse autonomously. A planner based in the AD* algorithm is used to plan a less costly trajectory to the destination. The methodology enables the robot to reach the goal using a local planner, which is applied to determine the speed and steering of the robot. Experimental results show that the planner is reliable for simulated and real tasks, as the robot has reached the goal while safely avoided obstacles.","PeriodicalId":360398,"journal":{"name":"2015 12th Latin American Robotics Symposium and 2015 3rd Brazilian Symposium on Robotics (LARS-SBR)","volume":"120 16","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113940229","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Detecting Latent Variables of Interest in Geo-Localized Environments Using an Aerial Robot","authors":"David Saldaña, Ramon S. Melo, E. R. Nascimento, M. Campos","doi":"10.1109/LARS-SBR.2015.56","DOIUrl":"https://doi.org/10.1109/LARS-SBR.2015.56","url":null,"abstract":"In general, monitoring applications require human intervention whenever there is no physical sensors for the variables of interest (e.g. People in danger after a catastrophe). In this paper we describe an inference engine which is used to estimate latent variables that can not be perceived by sampling the physical phenomena directly. Our approach uses information from different types of sensors, and fuses them along with knowledge of experts. The inference engine works with probabilistic first order logic rules based on geo-located sensed data as evidences in order to dynamically create the structure of a Bayesian network. Our experiments, performed by using an aerial robot with a mounted RGB-Camera, show the capability of our method to detect people in danger situations, where the physical variables to being sensed are humans and fire.","PeriodicalId":360398,"journal":{"name":"2015 12th Latin American Robotics Symposium and 2015 3rd Brazilian Symposium on Robotics (LARS-SBR)","volume":"2014 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134035293","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Terrain Classification from UAV Flights Using Monocular Vision","authors":"I. S. G. Campos, E. R. Nascimento, L. Chaimowicz","doi":"10.1109/LARS-SBR.2015.49","DOIUrl":"https://doi.org/10.1109/LARS-SBR.2015.49","url":null,"abstract":"With the popularization of small Unmanned Aerial Vehicles (UAVs) and their usage diversification among various fields, such as aerial mapping applications, it is important to develop better terrain following techniques that rely solely on the vehicle's sensing capabilities. The objective of this paper is to evaluate whether is possible to gather information about terrain inclination and elevation from monocular video captured from such aircrafts. Our approach is biologically inspired by trying to reproduce some insects behaviour with the use of optical flow to infer about the terrain. We built an UAV specifically for this research which uses a gimbal stabilized down-facing camera and flew it at a fixed Above Sea Level (ASL) altitude. After performing preliminary analysis on sparse optical flow data and validating the concept, we moved towards a dense optical flow algorithm and created different descriptors to feed multiple decision trees in order to infer about terrain characteristics. We achieved accuracies of 77.34%, 86.75% and 91.85% depending on the evaluated characteristic, showing that our approach is valid.","PeriodicalId":360398,"journal":{"name":"2015 12th Latin American Robotics Symposium and 2015 3rd Brazilian Symposium on Robotics (LARS-SBR)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133381247","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Foothold Planning and Gait Generation for a Hexapod Robot Traversing Terrains with Forbidden Zones","authors":"M. Rojas, N. Certad, J. Cappelletto, J. Grieco","doi":"10.1109/LARS-SBR.2015.70","DOIUrl":"https://doi.org/10.1109/LARS-SBR.2015.70","url":null,"abstract":"One of the primary advantage of walking machines is their inherent capacity to operate in different terrains. However, it is necessary a locomotion system for planning in advance future footholds, and to modify the robot gait in order to maintain the platform stability. Several locomotion systems have been developed for rectangular hexapod robots, in this work a system for radially a symmetric hexapod robot is presented. It includes a module for planning the next foothold, which takes information from the robot motion and terrain obstacles, and send signals to the global controller with the modifications needed on legs trajectories. These actions demand a new coordination between moving legs, while maintaining stability. The described system was coupled with two gait pattern generators for legs coordination over terrains with forbidden zones. The locomotion system was tested on a circular hexapod robot model using a dynamic simulation software. Results from simulations show that the proposed algorithm worked successfully, with a less than 1% of error.","PeriodicalId":360398,"journal":{"name":"2015 12th Latin American Robotics Symposium and 2015 3rd Brazilian Symposium on Robotics (LARS-SBR)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127946907","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluating the Performance of Two Visual Descriptors Techniques for a Humanoid Robot","authors":"Claudio De Oliveira Vilao Junior, Reinaldo A. C. Bianchi, Luiz Antonio Celiberto Junior","doi":"10.1109/LARS-SBR.2015.43","DOIUrl":"https://doi.org/10.1109/LARS-SBR.2015.43","url":null,"abstract":"A humanoid robot capable of playing soccer needs to know where opponents and team mates are in the soccer field. The robot has to be able to recognize team mates and opponents, inferring information such as distance and estimated location of the other robots. In order to achieve this key requisite, this paper analyze two descriptor algorithms, HAAR and HOG, so that one of them can be used for recognizing humanoid robots with less false positives alarms and with best frame per second rate. They were used with their respective classical classifiers, AdaBoost and SVM. As many different robots are available in RoboCup domain, the descriptor needs to describe features in a way that they can be distinguished from the background at the same time the classification has to have a good generalization capability. Although some limitations appeared in tests, the results were beyond expectations.","PeriodicalId":360398,"journal":{"name":"2015 12th Latin American Robotics Symposium and 2015 3rd Brazilian Symposium on Robotics (LARS-SBR)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124298113","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Rules for Robotic Cooperation Based on Vygotsky and Piaget","authors":"R. Maia, Anderson Abner Souza, L. M. Gonalves","doi":"10.1109/LARS-SBR.2015.71","DOIUrl":"https://doi.org/10.1109/LARS-SBR.2015.71","url":null,"abstract":"We propose the rules for robotic cooperation to be used by a group of robots for solving practical tasks in indoor environments. The formalism is inspired on the theory of social learning models for human beings that is traditionally developed in Psychology and Education fields. Our model can be used for coordination of the group, as for, allowing assimilation and accommodation of knowledge through experience exchange. Besides explaining the theoretical model itself, we formalize the mathematics involved with it in a very simple and straightforward fashion. Some issues are especially investigated such as the realistic representation of the multi-robot environment involving the global mission, the tasks belonging to the mission and the active set of robots. A way for task selection is proposed based on social learning theories and approaches that allow cooperative and efficient execution of tasks by robots. To this end, the rules can be used in different types of missions varying from simple to complex. Experiments and results validate the efficiency of the formalism compared to a traditional empirical model.","PeriodicalId":360398,"journal":{"name":"2015 12th Latin American Robotics Symposium and 2015 3rd Brazilian Symposium on Robotics (LARS-SBR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129773691","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}