Filters








1,654 Hits in 8.6 sec

How to learn accurate grid maps with a humanoid

Cyrill Stachniss, Maren Bennewitz, Giorgio Grisetti, Sven Behnke, Wolfram Burgard
2008 2008 IEEE International Conference on Robotics and Automation  
We describe how an existing approach to the simultaneous localization and mapping (SLAM) problem can be adapted to robustly learn accurate maps with a humanoid equipped with a laser range finder.  ...  In this paper, we investigate the problem of learning accurate grid maps with humanoid robots. We present techniques to deal with some of the above-mentioned difficulties.  ...  Learning Accurate Grid Maps The first experiment is designed to show that our approach is well suited to learn accurate grid maps with a humanoid robot.  ... 
doi:10.1109/robot.2008.4543697 dblp:conf/icra/StachnissBGBB08 fatcat:2wkvjttpdra3jii3noc524bpou

Appearance-based traversability classification in monocular images using iterative ground plane estimation

Daniel Maier, Maren Bennewitz
2012 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems  
As we illustrate in thorough experiments with a real humanoid, the classification results of our approach are highly accurate and the resulting occupancy map enables the robot to reliably avoid obstacles  ...  From this information, the robot can compute a two-dimensional occupancy grid map of the environment and use it for planning collision-free paths.  ...  From the labeled pixels, we learn a traversability map of the robot's surroundings in form of a 2D occupancy grid map in which a collision-free path can be computed.  ... 
doi:10.1109/iros.2012.6386098 dblp:conf/iros/MaierB12 fatcat:uslp3kpk65f5tprowxsg6m7obq

Simultaneous Localization and Mapping Trends and Humanoid Robot Linkages

Farshid Pirahansiah, Siti Norul Huda Sheikh Abdullah, Shahnorbanun Sahran
2013 Asia-Pacific Journal of Information Technology and Multimedia  
This method produces a real-time map of an environment and finds the current position of a robot on that map. This method is generally used to solve the problem of "Where am I?"  ...  This paper also reviews the use of SLAM for humanoid robots and aims to address the issue of the significance of SLAM engine in the future of stereo vision on humanoid robots.  ...  Local and global BA to obtain accurate 3D maps with respect to global coordinate frame 5. Data association between a large map of 3D points and 2D features perceived by a camera 6.  ... 
doi:10.17576/apjitm-2013-0202-03 fatcat:ljujog7chzeopf2ti57azhxeoe

Real-time navigation in 3D environments based on depth camera data

Daniel Maier, Armin Hornung, Maren Bennewitz
2012 2012 12th IEEE-RAS International Conference on Humanoid Robots (Humanoids 2012)  
We thoroughly evaluated our system with a Nao humanoid equipped with an Asus Xtion Pro Live depth camera on top of the humanoid's head and present navigation experiments in a multi-level environment containing  ...  In this paper, we present an integrated approach for robot localization, obstacle mapping, and path planning in 3D environments based on data of an onboard consumerlevel depth camera.  ...  ACKNOWLEDGMENTS The authors would like to thank Mathias Luber for his help in laser-based tracking of the robot's pose for ground truth data during the experiments.  ... 
doi:10.1109/humanoids.2012.6651595 dblp:conf/humanoids/MaierHB12 fatcat:disppo447rhlzewm4rnbguyetq

Self-supervised obstacle detection for humanoid navigation using monocular vision and sparse laser data

Daniel Maier, Maren Bennewitz, Cyrill Stachniss
2011 2011 IEEE International Conference on Robotics and Automation  
As we illustrate in experiments with a real humanoid, our approach enables the robot to reliably avoid obstacles during navigation.  ...  While the robot is walking, it then applies the learned classifiers to the images to decide which areas are traversable.  ...  ACKNOWLEDGMENTS The authors would like to acknowledge Armin Hornung and Christoph Sprunk for their help in the context of humanoid robot navigation and Andreas Ess for fruitful discussions on the topic  ... 
doi:10.1109/icra.2011.5979661 dblp:conf/icra/MaierBS11 fatcat:6xyh2zfnsfbele5g4jtayfp7ta

Supervised footstep planning for humanoid robots in rough terrain tasks using a black box walking controller

Alexander Stumpf, Stefan Kohlbrecher, David C. Conner, Oskar von Stryk
2014 2014 IEEE-RAS International Conference on Humanoid Robots  
This raises the question how navigation problems in complex and unstructured environments can be solved utilizing a given black box walking controller with proper perception and modeling of the environment  ...  A proper height map and surface normal estimation are directly obtained from point cloud data. A search-based planning approach (ARA*) is extended to sequences of footsteps in full 3D space (6 DoF).  ...  The authors would like to thank all members of Team ViGIR for their contribution and support which enabled the realization of this work.  ... 
doi:10.1109/humanoids.2014.7041374 dblp:conf/humanoids/StumpfKCS14 fatcat:exfuyimbwrhalfqkrecjiraoc4

Interactive Object Learning and Recognition with Multiclass Support Vector Machines [chapter]

Ales Ude
2010 Robot Vision  
Lets assume now that the data points were transformed with a nonlinear mapping Φ, which maps the data into a possibly higher dimensional feature space.  ...  This makes it possible to equip a humanoid robot with miniature cameras (lipstick size and (Asfour et al., 2008) , while the right one is part of a humanoid robot designed by SARCOS and ATR (Cheng et  ...  How to reference In order to correctly reference this scholarly work, feel free to copy and paste the following: Ales Ude (2010) .  ... 
doi:10.5772/9307 fatcat:bgaivz2n75carko2ikk7wboice

Synthetic Generation of Passive Infrared Motion Sensor Data Using a Game Engine

Petter Stefansson, Fredrik Karlsson, Magnus Persson, Carl Magnus Olsson
2021 Sensors  
Through this, the relationship between sensor output and spatial position of a motion is discovered to be highly non-linear, which highlights some of the difficulties associated with mapping PIR data to  ...  The developed simulator is also used to study how a PIR sensor's output changes depending on where in a room a motion is carried out.  ...  Since the humanoid model is composed of primitive geometrical objects whereas a real person is not, it is not straightforward to accurately map the measurements of a real person onto the body parts of  ... 
doi:10.3390/s21238078 pmid:34884081 fatcat:lz7u46vnmbgfbpld4i2kziyrd4

Training an Interactive Humanoid Robot Using Multimodal Deep Reinforcement Learning [article]

Heriberto Cuayáhuitl, Guillaume Couly, Clément Olalainty
2016 arXiv   pre-print
We describe a learning approach as a step in this direction, where we teach a humanoid robot how to play the game of noughts and crosses.  ...  Training robots to perceive, act and communicate using multiple modalities still represents a challenging problem, particularly if robots are expected to learn efficiently from small sets of example interactions  ...  ) a policy π : S → A that defines a mapping from states to actions.  ... 
arXiv:1611.08666v1 fatcat:lzodxwog5zdkhcqk4lbqifx65m

First do not fall: learning to exploit a wall with a damaged humanoid robot [article]

Timothée Anne, Eloïse Dalin, Ivan Bergonzani, Serena Ivaldi, Jean-Baptiste Mouret
2022 arXiv   pre-print
We hypothesize that humanoid robots would be mostly used in buildings, which makes them likely to be close to a wall.  ...  This article introduces a method, called D-Reflex, that learns a neural network that chooses this contact position given the wall orientation, the wall distance, and the posture of the robot.  ...  "First do not fall: learning to exploit a wall with a damaged humanoid robot". In Robotics and Automation Letters.  ... 
arXiv:2203.00316v3 fatcat:en2a4o5fqjeqzfzoimkvqsnlry

Monte Carlo Localization for Humanoid Robot Navigation in Complex Indoor Environments

Armin Hornung, Stefan Oßwald, Daniel Maier, Maren Bennewitz
2014 International Journal of Humanoid Robotics  
Accurate and reliable localization is a prerequisite for autonomously performing highlevel tasks with humanoid robots.  ...  We demonstrate the effectiveness of our methods in extensive real-world experiments with a Nao humanoid.  ...  The authors would like to thank Rainer Kümmerle and Slawomir Grzonka for fruitful discussions, and Jörg Müller for assistance with the motion capture system.  ... 
doi:10.1142/s0219843614410023 fatcat:phooukthhrgpxlci2ffgg3wb4i

Emotional manifestations of humanoids of the future

Raphaël C.-W. Phan, Elizabeth Sheppard
2020 Journal of Future Robot Life  
These types of humanoids will have the capability to manifest emotions like any normal human in such a manner that another human will not be able to tell if they are engaging with a human or a humanoid  ...  Underpinning these discussions will be the need to map human expressions to underlying emotions being felt by humans, and the issues associated with doing so will be examined from a psychological perspective  ...  training data can be processed to build machine learning models that are able to recognize patterns and perform accurate predictions.  ... 
doi:10.3233/frl-200007 fatcat:praeui2dtjcgnjor47kzqpvlo4

How to localize humanoids with a single camera?

Pablo F. Alcantarilla, Olivier Stasse, Sebastien Druon, Luis M. Bergasa, Frank Dellaert
2012 Autonomous Robots  
In order to obtain an accurate localization of the robot, we first build an accurate 3D map of the environment.  ...  We demonstrate the robustness and accuracy of our approach by showing several vision-based localization experiments with the HRP-2 humanoid robot.  ...  The authors would also like to thank the Joint French-Japanese Robotics Laboratory (JRL), CNRS/AIST, Tsukuba,Japan.  ... 
doi:10.1007/s10514-012-9312-1 fatcat:gn4gltmchvd3xcie5i4h7nxv5q

Hierarchical learning approach for one-shot action imitation in humanoid robots

Yan Wu, Yiannis Demiris
2010 2010 11th International Conference on Control Automation Robotics & Vision  
Our proposed framework, addressing the "how-to" question in imitation, is based on a oneshot imitation learning algorithm.  ...  We consider the issue of segmenting an action in the learning phase into a logical set of smaller primitives in order to construct a generative model for imitation learning using a hierarchical approach  ...  The authors would also like to express their gratitude towards the participants in the experiments.  ... 
doi:10.1109/icarcv.2010.5707349 dblp:conf/icarcv/WuD10 fatcat:7hg2fpjbvzeihdt6fdves4qvza

Learning the reachable space of a humanoid robot: A bio-inspired approach

Lorenzo Jamone, Lorenzo Natale, Kenji Hashimoto, Giulio Sandini, Atsuo Takanishi
2012 2012 4th IEEE RAS & EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob)  
In this paper we describe how a humanoid robot can learn a representation of its own reachable space from motor experience: a Reachable Space Map.  ...  We provide experimental results in which a simulated humanoid robot learns this map autonomously and we discuss how the map can be used for planning whole-body and bimanual reaching.  ...  Different works show how this solution allows to learn a motor-motor mapping that can be used for reaching control [17] - [19] .  ... 
doi:10.1109/biorob.2012.6290729 fatcat:v2outogqejgy5nbdeqbxvuswkm
« Previous Showing results 1 — 15 out of 1,654 results