The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Robotic soccer provides a rich environment for the development of Reinforcement Learning controllers. The competitive environment imposes strong requirements on performance of the developed controllers. RL offers a valuable alternative for the development of efficient controllers while avoiding the hassle of parameter tuning a hand coded policy. This paper presents the application of a recently proposed...
Existing robot localization methods often rely on particular characteristics of the environment, such as vertical walls. However, these approaches loose generality once the environment does not show that structure, e.g., in domestic environments. This paper addresses the problem of absolute online self-localization in a known map, where the only required structure in the environment is a planar ground...
The Linear inverted pendulum model is widely used in biped walking approaches. This model assumes that the hip height is fixed while the robot walks. In this paper, the hip height movement, or vertical Center of Mass (CoM) trajectory, is used by a robot to achieve a faster and more stable walk. For the first time, the hip height movement is modeled in a formal way and its parameters are learned. The...
Hand gestures are a powerful way for human communication, with lots of potential applications in the area of human computer interaction. Vision-based hand gesture recognition techniques have many proven advantages compared with traditional devices, giving users a simpler and more natural way to communicate with electronic devices. This work proposes a generic system architecture based in computer...
This paper proposes extending Monte Carlo Localization methods with visual information in order to build a long term robot localization system. This system is aimed to work in crowded and non-planar scenarios, where 2D laser rangefinders may not always be enough to match the robot position with the map. Thus, visual place recognition will be used in order to obtain robot position clues that can be...
In this paper we study pose estimation for non-central cameras, using planes. The method proposed uses non-minimal data. Using the homography matrix to represent the transformation between the world and camera coordinate systems, we describe a non-iterative algorithm for pose estimation. In addition, we propose a parameter optimization to refine the pose estimate. We evaluate the proposed solutions...
An approach addressing biped locomotion optimization is here introduced. Concepts from Central Pattern Generators (CPGs) and Dynamic Movement Primitives (DMPs) were combined to easily produce complex trajectories for the joints of a simulated DARwIn-OP. A Reinforcement Learning Algorithm, Policy Learning by Weighting Exploration with the Returns (PoWER), was implemented to improve the robot's locomotion...
This paper proposes a new approach to the boundary value problem of finding a vehicle path from an initial state, defined by a position and velocity vector, to a target position. The presented method explicitly considers magnitude constraints on both the velocity and the acceleration of the vehicle when determining the path. A semi-analytic and computationally efficient algorithm is employed, applicable...
Recognizing a place with a visual glance is the first capacity used by humans to understand where they are. Making this capacity available to robots will make it possible to increase the redundancy of the localization systems available in the robots, and improve semantic localization systems. However, to achieve this capacity it is necessary to build a robust visual place recognition procedure that...
Benchmarking is nowadays an issue on robotic research platforms, due to the fact that it is not easy to reproduce previous experiments and knowing in detail in which real conditions other algorithms have been performed. Having a web-based tool to configure and execute benchmarks opens the door to new opportunities as the design of virtual tele-laboratories that permit the implementation of new algorithms...
This paper describes the development of a low cost robotic platform named MYRABot+, which is able to make the required tasks in order to assist a human in a domestic environment. We also believe that the best way to measure its performance and validate its behavior is taking part in a robotic challenge. This robotic platform explicitly uses low cost components, making it an accessible platform in...
This paper proposes to present and discuss in detail the design of a novel handlebar of a motorized walker to be used as an interface between the user and the motor controller of the wheels. This device enables the user to indicate and command the direction and speed of the walker's motion. This new interface intends to be user-friendly and low cost. Safety considerations are also addressed to detect...
This work presents scenario oriented Color-Depth integration framework for the purpose of robust object segmentation in a real workplace scenario. The workplace is the Library of Bremen University and the objects to be grasped are books located on a shelf. The proposed framework is responsible for segmenting the book to be grasped and extract the features needed for a successful grasping operation...
A multi-robot system is formed when a group of robots interact with the environment as a single system. This system can also be in formation in order to accomplish tasks rather difficult or impossible to achieve with a single robot. A nonlinear model predictive formation control (NMPFC) was used to converge a group of middle sized mobile soccer robots towards a desired target using the concept of...
This paper introduces a fast Traffic Sign Recognition system developed for a robot, participant in the Autonomous Driving Competition in the Portuguese Festival of Robotics. The Autonomous Driving Robot performs detection and classification of traffic signs and traffic lights based on the analysis of images acquired by a camera mounted on its chassis. The proposed algorithm is composed of three processing...
In this paper a formation control algorithm is proposed for teleoperated mobile robot groups. A leader robot is teleoperated directly by the human operator using a primary haptic device. The rest of the mobile robots follow the virtual reference structure attached to the leader. The shape of the structure can be reconfigured by the operator using a secondary haptic device. A method is given for generating...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.