Results 221 to 230 of about 35,641 (264)

Learning landmark triples by experimentation

Robotics and Autonomous Systems, 1997
Abstract This article describes a method for learning a set of landmarks suitable for place navigation. The approach is novel in that it exploits the ability of a robot to learn through active perception in the task environment, similar to the learning by experimentation technique developed for LEX (Mitchell et al., 1990).
Robin R. Murphy, David Hershberger, Glenn Blauvelt   +2 more
openaire   +1 more source

Learning to Localize Little Landmarks

2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016
We interact everyday with tiny objects such as the door handle of a car or the light switch in a room. These little landmarks are barely visible and hard to localize in images. We describe a method to find such landmarks by finding a sequence of latent landmarks, each with a prediction model.
Saurabh Singh 0005, Derek Hoiem, David A. Forsyth   +2 more
openaire   +1 more source

Learning Deep Landmarks for Imbalanced Classification

IEEE Transactions on Neural Networks and Learning Systems, 2020
We introduce a deep imbalanced learning framework called learning DEep Landmarks in laTent spAce (DELTA). Our work is inspired by the shallow imbalanced learning approaches to rebalance imbalanced samples before feeding them to train a discriminative classifier.
Feng Bao 0002, Yue Deng 0001, Youyong Kong, Zhiquan Ren, Jin-Li Suo, Qionghai Dai   +5 more
openaire   +2 more sources

Landmark learning: An illustration of associative search

Biological Cybernetics, 1981
In a previous paper we defined the associative search problem and presented a system capable of solving it under certain conditions. In this paper we interpret a spatial learning problem as an associative search task and describe the behavior of an adaptive network capable of solving it.
BARTO, AG, SUTTON, RS
openaire   +2 more sources

Landmarks in Route Learning by Girls and Boys

Perceptual and Motor Skills, 2000
Previous research on route learning has shown that men learn routes faster and with fewer errors than women. The same patterns have also been found for girls and boys. In this study, 19 children of ages 5 to 6 years, 26 children of ages 7 to 9 years, and 22 children of ages 10 to 12 years were presented a route-learning task. The children were randomly
C D, Beilstein, J F, Wilson
openaire   +2 more sources

Learning visual landmarks for pose estimation

Proceedings 1999 IEEE International Conference on Robotics and Automation (Cat. No.99CH36288C), 2003
We present an approach to vision-based mobile robot localization, even without an a-priori pose estimate. This is accomplished by learning a set of visual features called image-domain landmarks. The landmark learning mechanism is designed to be applicable to a wide range of environments.
Robert Sim, Gregory Dudek
openaire   +1 more source

Learning Combinatorial Information from Alignments of Landmarks

Proceedings 2007 IEEE International Conference on Robotics and Automation, 2007
This paper characterizes the information space of a robot moving in the plane with limited sensing. The robot has a landmark detector, which provides the cyclic order of the landmarks around the robot, and it also has a touch sensor, that indicates when the robot is in contact with the environment boundary.
FREDA, Luigi, Tovar, Benjamín, Lavalle, Steven M.   +2 more
openaire   +1 more source

Honeybees learn the colours of landmarks

Journal of Comparative Physiology A, 1986
1. To discover whether bees learn the colours of landmarks, individually marked foragers were trained to collect sucrose from a small reservoir on the floor of a room. The reservoir was placed at one of two sites each defined by its position relative to one of two different arrays of cylindrical landmarks.
K. Cheng, T. S. Collett, R. Wehner
openaire   +1 more source

Learning spatial prior with automatically labeled landmarks

2008 3rd International Conference on Intelligent System and Knowledge Engineering, 2008
We propose a method of automatically labeling landmarks on target images, which are used for training a constellation model to recognize general object class. First, we randomly sample local features (parts) and generate hierarchical representations of images in a similar way to the ?standard model? of visual cortex.
Jianzhai Wu, Zongtan Zhou, Li Zhou 0003, Dewen Hu   +3 more
openaire   +1 more source

Landmark stability is a prerequisite for spatial but not discrimination learning

Nature, 1993
Neurons sensitive to both place and direction from distinct regions of the hippocampal formation, allometric relationships between spatial learning and hippocampal structure and pronounced impairments in spatial learning after lesions in this area, indicate that the hippocampal formation subserves allocentric spatial learning.
R, Biegler, R G, Morris
openaire   +2 more sources