Filters








600 Hits in 8.9 sec

VISION-BASED HUMANOID NAVIGATION USING SELF-SUPERVISED OBSTACLE DETECTION

DANIEL MAIER, CYRILL STACHNISS, MAREN BENNEWITZ
2013 International Journal of Humanoid Robotics  
Then, it uses the knowledge about obstacles identified in the laser data to train visual classifiers based on color and texture information in a self-supervised way.  ...  In this article, we present an efficient approach to obstacle detection for humanoid robots based on monocular images and sparse laser data.  ...  Acknowledgments The authors would like to acknowledge Armin Hornung and Christoph Sprunk for their help in the context of mobile robot navigation, Jörg Müller for his help with the motion capture system  ... 
doi:10.1142/s0219843613500163 fatcat:symueubgwja3hfvo4papw4btke

Secure Autonomous Cloud Brained Humanoid Robot Assisting Rescuers in Hazardous Environments

Georgios Angelopoulos, Nikolaos Baras, Minas Dasygenis
2021 Electronics  
Our research proposes a novel, secure and efficient programmable system using a humanoid robot that is able to autonomously move and detect survivors in emergency scenarios, with the potential to communicate  ...  The proposed humanoid robot is powered by the cloud and benefits from the powerful storage, computation, and communication resources of a typical modern data center.  ...  features and a cascade AdaBoost classifier for face detection to achieve efficient and real- time performance for face detection.  ... 
doi:10.3390/electronics10020124 fatcat:35ir7qrdtnegniabjznnl3ikim

Guiding visitors of Web3D worlds through automatically generated tours

Luca Chittaro, Roberto Ranon, Lucio Ieronutti
2003 Proceeding of the eighth international conference on 3D web technology - Web3D '03  
Many Web3D sites do not offer sufficient assistance t o (especially novice) users in navigating the virtual world, find objects/places of interests, and learn how to interact with them.  ...  provides automatic code generation for adding such guided tours to VRML worlds.  ...  We classify areas of the virtual world in two categories: areas that the guide can freely navigate, and areas that it cannot (because they contain obstacles).  ... 
doi:10.1145/636593.636598 dblp:conf/vrml/ChittaroRI03 fatcat:vh2psndqsndg7d3vfgvq34tszy

Guiding visitors of Web3D worlds through automatically generated tours

Luca Chittaro, Roberto Ranon, Lucio Ieronutti
2003 Proceeding of the eighth international conference on 3D web technology - Web3D '03  
Many Web3D sites do not offer sufficient assistance t o (especially novice) users in navigating the virtual world, find objects/places of interests, and learn how to interact with them.  ...  provides automatic code generation for adding such guided tours to VRML worlds.  ...  We classify areas of the virtual world in two categories: areas that the guide can freely navigate, and areas that it cannot (because they contain obstacles).  ... 
doi:10.1145/636596.636598 fatcat:cw344rtptzgybpuidrwn2ttdrm

The Emotionally Intelligent Robot: Improving Social Navigation in Crowded Environments [article]

Aniket Bera and Tanmay Randhavane and Rohan Prinja and Kyra Kapsaskis and Austin Wang and Kurt Gray and Dinesh Manocha
2019 arXiv   pre-print
We present a real-time algorithm for emotion-aware navigation of a robot among pedestrians.  ...  These PAD characteristics are used for long-term path prediction and generating proxemic constraints for each pedestrian.  ...  [3] created a robot for navigating urban environments without GPS data or prior knowledge. Fan et al.  ... 
arXiv:1903.03217v1 fatcat:itkqg5irm5fn3klijh2uwkabku

Computer-Vision Based Object Detection and Recognition for Service Robot in Indoor Environment

Kiran Jot Singh, Divneet Singh Kapoor, Khushal Thakur, Anshul Sharma, Xiao-Zhi Gao
2022 Computers Materials & Continua  
In this paper, we present a viable approach for a real-time computer vision based object detection and recognition for efficient indoor navigation of a mobile robot.  ...  The presented framework can be further utilized for a wide variety of applications involving indoor navigation robots for different services.  ...  Microsoft Kinect returns the depth information about a pair of legs using YOLOv2 to develop an image.  ... 
doi:10.32604/cmc.2022.022989 fatcat:yllwhhltjnemffyyhtvw5lnjum

Efficient architecture for collision detection between heterogeneous data structures application for vision-guided robots

Jesse Himmelstein, Guillaume Ginioux, Etienne Ferre, Alireza Nakhaei, Florent Lamiraux, Jean-Paul Laumond
2008 2008 10th International Conference on Control, Automation, Robotics and Vision  
and memory optimizations needed for high-performance.  ...  In order to enable rapid development of efficient collision detection procedures, we propose an extensible software architecture that allows for cross-queries between data types, while permitting the time  ...  Next, it uses the vision data to classify the 3D grid cells, creating two occupancy grids: one for OBSTACLE cells, and the other for UNKNOWN (free space is defined as the absence of grid cells).  ... 
doi:10.1109/icarcv.2008.4795573 dblp:conf/icarcv/HimmelsteinGFNLL08 fatcat:5sv5r7y5cfhjhh536v5jlx3tzm

Improving robot navigation in structured outdoor environments by identifying vegetation from laser data

Kai M. Wurm, Rainer Kummerle, Cyrill Stachniss, Wolfram Burgard
2009 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems  
The ability to detect vegetation is important for robots operating outdoors, since it enables a robot to navigate more efficiently and safely in such environments.  ...  We furthermore illustrate how the learned classifier can improve the autonomous navigation capabilities of mobile robots.  ...  Without knowledge about the specific terrain, the shortest obstacle-free path would have led the robot across a large area containing grass.  ... 
doi:10.1109/iros.2009.5354530 dblp:conf/iros/WurmKSB09 fatcat:i2d7y46nhbc7jfqme4e5ykfbja

An Optimal Control-Based Formulation to Determine Natural Locomotor Paths for Humanoid Robots

Katja Mombaur, Jean-Paul Laumond, Eiichi Yoshida
2010 Advanced Robotics  
The knowledge of these principles is useful to implement biologically inspired path planning algorithms on a humanoid robot.  ...  We propose a single dynamic model valid for all situations, which includes both non-holonomic and holonomic modes of locomotion, as well as an appropriately designed unified objective function.  ...  Acknowledgements We thank the Simulation & Optimization group at IWR, University of Heidelberg for providing the optimal control package MUSCOD.  ... 
doi:10.1163/016918610x487090 fatcat:gquqwqnkobaxtbtmn4qlnm67sy

A FRAMEWORK FOR LEARNING AND CONTROL IN INTELLIGENT HUMANOID ROBOTS

OLIVER BROCK, ANDREW FAGG, RODERIC GRUPEN, ROBERT PLATT, MICHAEL ROSENSTEIN, JOHN SWEENEY
2005 International Journal of Humanoid Robotics  
We present several pieces of an overall framework in which a robot learns situated policies for control that exploit existing control knowledge and extend its scope.  ...  Future application areas for humanoid robots range from the household, to agriculture, to the military, and to the exploration of space.  ...  We would also like to thank Robert Ambrose, William Bluethmann and Myron Diftler at NASA Johnson Space Center for providing access to Robonaut.  ... 
doi:10.1142/s0219843605000491 fatcat:quucpz6uazfznfcgrr6ywkjltm

Cost-Efficient Global Robot Navigation in Rugged Off-Road Terrain

T. Braun
2011 Künstliche Intelligenz  
, but also cost-efficient, e.g. able to generate navigation paths which optimize a cost measure closely related to terrain traversability.  ...  Abstract This thesis addresses the problem of finding a global robot navigation strategy for rugged off-road terrain which is robust against inaccurate self-localization and scalable to large environments  ...  distance based components: ρ i = ρ class ρ dist (6.15) Combining Class Votes for the Classifier Ensemble Label assignment and confidence estimation for each classifier produces three class labels L  ... 
doi:10.1007/s13218-011-0088-9 fatcat:u4ssainmcvc3jmqdon6gpjg674

A Taxonomy of Vision Systems for Ground Mobile Robots

Jesus Martinez-Gomez, Antonio Fernandez-Caballero, Ismael Garcia-Varea, Luis Rodriguez, Cristina Romero-Gonzalez
2014 International Journal of Advanced Robotic Systems  
, what for?, what with?, how?, and where?  ...  Firstly, a thorough review of the papers is proposed to discuss and classify both past and the most current approaches in the field.  ...  Furthermore, a novel and efficient auto-navigation system based on machine vision for an unknown environment has been developed in [107] .  ... 
doi:10.5772/58900 fatcat:ydrtcuwnbrbhdgjxmw3rhfa7oi

A Reuse-Oriented Development Process for Component-Based Robotic Systems [chapter]

Davide Brugali, Luca Gherardi, A. Biziak, Andrea Luzzana, Alexey Zakharov
2012 Lecture Notes in Computer Science  
study of robust navigation functionality, and to present the software tools that we have developed for supporting the proposed process.  ...  State of the art in robot software development mostly relies on class library reuse and only to a limited extent to component-based design.  ...  The authors would like to thank all the partners of the project for their valuable comments.  ... 
doi:10.1007/978-3-642-34327-8_33 fatcat:zdx5mo5fcvb37jkji5xv3ohk4y

Detection of Landmines Using Nuclear Quadrupole Resonance (NQR): Signal Processing to Aid Classification [chapter]

S. D. Somasundaram, K. Althoefer, J. A. S. Smith, L. D. Seneviratne
2006 Climbing and Walking Robots  
Any dissimilarity (i.e. novelty) to normal behaviours are detected and classified into distinctive classes.  ...  Abstract The paper points out the progress in the exploitation of high fast and precise non-contact velocimetry for robot applications.  ...  Choosing the type of locomotion suitable for an application/environment, biomimesis is an effective paradigm. Natural behaviours are understood and reproduced in robotic systems. What attracts and  ... 
doi:10.1007/3-540-26415-9_100 dblp:conf/clawar/SomasundaramASS05 fatcat:4vu25zlx65dszgbcxkusxozfve

Universal Planning Networks [article]

Aravind Srinivas, Allan Jabri, Pieter Abbeel, Sergey Levine, Chelsea Finn
2018 arXiv   pre-print
A key challenge in complex visuomotor control is learning abstract representations that are effective for specifying goals, planning, and generalization.  ...  We find that the representations learned are not only effective for goal-directed visual imitation via gradient-based trajectory optimization, but can also provide a metric for specifying goals using images  ...  To our knowledge, there has been no prior exposition of torque controlled goal conditioned ant navigation for varying goals around obstacle(s) even when spatial positions of the goal and ant torso are  ... 
arXiv:1804.00645v2 fatcat:lh2f2utiujfrnckabtzyp6m3ke
« Previous Showing results 1 — 15 out of 600 results