Showing papers in "Robotics and Autonomous Systems in 2001"

TL;DR: CDR may provide ways of understanding human beings that go beyond the current level of explanation found in the natural and social sciences and hold promise because they have many degrees of freedom and sense modalities and must face the challenges of scalability that are often side- stepped in simpler domains.

TL;DR: This paper proposes a hierarchical reinforcement learning architecture that realizes practical learning speed in real hardware control tasks and applies it to a three-link, two-joint robot for the task of learning to stand up by trial and error.

TL;DR: Light is shed on the nature of factors affecting the length of paths in the Dubins problem, and is useful for further extensions, e.g. for finding the shortest path between a point and a manifold in the corresponding configuration space.

TL;DR: Reference LSA3-CONF-2000-001 URL: http://humanoids.usc.edu Record created on 2005-11-16, modified on 2017-05-10.

TL;DR: A novel distributed control scheme of multiple robotic vehicles in which all the robotic vehicles are stabilized, which is succeeded in proving mathematically only in the cases where the attractions between the robots are symmetrical.

TL;DR: In this paper, an approach for localization using geometric features from a 360 laser range finder and a monocular vision system is investigated in large-scale experiments and the results were obtained with a fully self-contained system where extensive tests with an overall length of more than 6.4 km and 150,000 localization cycles have been conducted.

TL;DR: Two related examples in which a humanoid robot determines the models and representations that govern its behavior are shown, including a model that captures the dynamics of a haptic exploration of an object with a dextrous robot hand that supports skillful grasping.

TL;DR: A novel approach to the allocation of thruster forces of an autonomous underwater vehicle (AUV) is investigated, and a redundancy resolution scheme is presented that takes into account the presence of excess number of thrusters along with any thruster faults and determines the reference thrusters to produce the desired motion.

TL;DR: In the robot soccer environment, the effectiveness and applicability of modular Q-learning and the uni-vector field method are verified by real experiments using five micro-robots.

TL;DR: This paper describes and compares three different uncertainty calculi techniques to build occupancy grids of an unknown environment using sensory information provided by a ring of ultrasonic range-finders using Bayesian theory, Dempster–Shafer theory of evidence, and fuzzy set theory.

TL;DR: The capability of EM to actually control a real vehicle and to perform trajectory following and obstacle avoidance in real outdoor environments by using simple fuzzy behaviours relying upon low-resolution sensor data is demonstrated.

TL;DR: Design and construction of compact body humanoid robots and various biped locomotion control strategies implemented onto them in the ESYS humanoid project at the Engineering Systems Laboratory are presented.

TL;DR: An extension of the Condensation algorithm is introduced that relies on a single probability distribution to describe the likely states of multiple objects, by introducing an initialization density, so that newly appearing objects can be handled.

TL;DR: This paper focuses on various aspects of coordination in the framework of the RoboCup competitions and presents a behavior-based technique for position selection and the so-called holonic approach from the multi-agent perspective.

TL;DR: A generic framework for combining information from several physically different sensors into a single composite multi-dimensional scene description is described and it is shown that features extracted are more robust than those extracted from a single sensor.

TL;DR: A new method is introduced which works very fast and gives the optimal path in a complex environment and is equipped with the procedures of fast path replanning — very useful in partially known workspaces.

TL;DR: In this paper, skin colour is modelled based on a reflectance model of the skin, the parameters of the camera and light sources, which has applications in adaptive segmentation of skin colour and in the estimation of the current illumination in camera images containing skin colour.

TL;DR: The design of a multi-part mirror catadioptric vision system and its use for self-localization and detection of relevant objects in soccer robots is described.

TL;DR: In the present work, fuzzy logic based implementation of the single-sided reflex is considered and the use of perceptional symmetry allows perception–action mapping with reduced sensor space dimensions.

TL;DR: Experimental results have demonstrated the effectiveness of this method for the segmentation of various hand images as well as general color images with complex backgrounds for gesture-based human–service robot interaction system.

TL;DR: A probabilistic technique for estimating the state of dynamic objects in the environment of a mobile robot to efficiently and accurately identify the most likely state of each object even if the robot is in motion is presented.

TL;DR: An augmented reality tool for collaborative work called the MagicBoard, based on an ordinary white board which has been enhanced by a video-projector and a steerable camera, that largely increases the functionality of a white board and makes it a useful tool in the future office environments.

TL;DR: Three approaches to vision-based self-localization used in the RoboCup middle-size league competition are reviewed and the results they achieve in the robot soccer environment for which they have been designed are described.

TL;DR: In this article, a robust position-tracking method for a mobile robot with seven sonar sensors is presented based on Hough transform and probability grids, which avoids the common problems of feature detection in sonar data such as erroneous lines through separate clusters, corner inference and line artefacts through reflection.

TL;DR: A batch data association method that uses the simultaneous observation of multiple features to determine data associations in a manner decoupled from the vehicle pose estimate and an observation-based dead reckoning procedure that estimates vehicle motion in place of odometry and does not require a kinematic vehicle model are introduced.

TL;DR: A new system of rules that lead to shorter paths than the other methods in the specific case of local minimum detection and avoidance of the sensor-based real-time navigation algorithm are revealed.

TL;DR: A vision guided robotic system for an autonomous disassembly process for used cars in an undefined state and a stereo vision system, a force–torque sensor, a task planning module, and a special unscrewing tool were integrated.

TL;DR: Recognising the critical role of software in tackling a generic problem such as this, the distribution of a proven and carefully designed open-source software framework which is intended for use in a wide range of robot and vision applications is announced.

TL;DR: A new real-time visual system that enables a humanoid robot to learn from and interact with humans and is directly coupled with the motor control system of the humanoid robot DB is described.

TL;DR: A modular, behavior-based control architecture is proposed, which is particularly suited for “Learning from Demonstration” experiments in the spatial domain and first results applying RBF-approximation, growing neural cell structures and probabilistic models for progress estimation, are presented.