4,100 Hits in 5.4 sec

"Programming" by Teaching: Neural Network Control in the Manchester Mobile Robot

Paul Martin, Ulrich Nehmzow
1995 IFAC Proceedings Volumes  
The observed actions are used to train the robot's associative memory, and after a very short training time FortyTwo becomes able to perform the required task autonomously.  ...  An articial neural network, forming the core component of the controller presented here, associates incoming sensor signals with corresponding motor actions.  ...  As a vision preprocessing system, generating sensor information for the arti cial neural network used in the controller, however, optical ow can be used without having solved the correspondence problem  ... 
doi:10.1016/s1474-6670(17)46985-0 fatcat:frhww5zs7jatheljogt6tp724a


Paul Martin, Ulrich Nehmzow
1995 Intelligent Autonomous Vehicles 1995  
The observed actions are used to train the robot's associative memory, and after a very short training time FortyTwo becomes able to perform the required task autonomously.  ...  An articial neural network, forming the core component of the controller presented here, associates incoming sensor signals with corresponding motor actions.  ...  As a vision preprocessing system, generating sensor information for the arti cial neural network used in the controller, however, optical ow can be used without having solved the correspondence problem  ... 
doi:10.1016/b978-0-08-042366-1.50049-x fatcat:ol36fhyfxff5nkgvrebcpdb4eu

Real-time 2D–3D door detection and state classification on a low-power device

João Gaspar Ramôa, Vasco Lopes, Luís A. Alexandre, S. Mogo
2021 SN Applied Sciences  
We use the 3D object classification, PointNet, real-time semantic segmentation algorithms such as, FastFCN, FC-HarDNet, SegNet and BiSeNet, the object detection algorithm, DetectNet and 2D object classification  ...  These methods were also developed to be used in other areas and applications since they are not limited to door detection as other related works are.  ...  To detect doors, 3D cameras or sonar sensors are not required, a simple RGB camera can do the job as in [12] , focusing on real-time, low-cost and low-power systems.  ... 
doi:10.1007/s42452-021-04588-3 pmid:33942027 pmcid:PMC8082488 fatcat:cwcdyclnnjayvjtvfahjop2xpe

Algorithm Development for Minor Damage Identification in Vehicle Bodies Using Adaptive Sensor Data Processing

Sergei Gontscharov, Hauke Baumgärtel, Andre Kneifel, Karl-Ludwig Krieger
2014 Procedia Technology - Elsevier  
Acknowledgements We would like to thank the German Federal Ministry of Education and Research for funding this research project.  ...  Furthermore, we would like to thank our project partners Hella Fahrzeugkomponenten GmbH, Berger Elektronik GmbH and cambio Mobilitätsservice GmbH & Co KG for their contribution in the research project  ...  Through the use of the PRNN classification process of the sensor nodes a high coverage of training data captured from real-time signals is required.  ... 
doi:10.1016/j.protcy.2014.09.019 fatcat:shaoegu7x5g3ninyi3vudpvio4

Multimodal Wireless Sensor Network-Based Ambient Assisted Living in Real Homes with Multiple Residents

Can Tunca, Hande Alemdar, Halil Ertan, Ozlem Incel, Cem Ersoy
2014 Sensors  
Human activity recognition and behavior monitoring in a home setting using wireless sensor networks (WSNs) provide a great potential for ambient assisted living (AAL) applications, ranging from health  ...  We also present the details of the field study we conducted, using the systems deployed in two different real home environments with multiple residents.  ...  In the experiments, we used five different classifiers, namely, kNN, DT, HMM, MLP and time-delay neural network (TDNN).  ... 
doi:10.3390/s140609692 pmid:24887044 pmcid:PMC4118408 fatcat:3pakpqmzt5cqngwm2hcxo4gqsm

Using Educational Robotics to Motivate Complete AI Solutions

Lloyd G. Greenwald, Donovan Artz, Yogi Mehta, Babak Shirmohammadi
2006 The AI Magazine  
Acknowledgements We thank Brian Summers for his efforts in testing the Bayesian network exercises. We thank Zachary Dodds and Jerry Weinberg for their feedback on drafts of this article.  ...  (a) A neural network designed to demonstrate robust obstacle detection and classification using low-cost infrared sensors.  ...  Obstacle Detection with Neural Networks, Bayesian Networks, and the Handy Board A typical task in a robotics class is to program a robot to detect and avoid obstacles.  ... 
doi:10.1609/aimag.v27i1.1865 dblp:journals/aim/GreenwaldAMS06 fatcat:j2ysavafo5ezxiavl3i7lwmmjm

MQTTset, a New Dataset for Machine Learning Techniques on MQTT

Ivan Vaccari, Giovanni Chiola, Maurizio Aiello, Maurizio Mongelli, Enrico Cambiaso
2020 Sensors  
Obtained results demonstrate how MQTTset can be used to train machine learning models to implement detection systems able to protect IoT contexts.  ...  Due to the huge number of connected IoT devices, security of such networks and devices is therefore a critical issue.  ...  and able to validate/identify threats in real time.  ... 
doi:10.3390/s20226578 pmid:33217936 pmcid:PMC7698741 fatcat:ae7tgppfejhytmfakehi6uxhuy

Survey of Visual and Force/Tactile Control of Robots for Physical Interaction in Spain

Gabriel Garcia, Juan Corrales, Jorge Pomares, Fernando Torres
2009 Sensors  
Sensors provide robotic systems with the information required to perceive the changes that happen in unstructured environments and modify their actions accordingly.  ...  strategies: visual servoing control, force control and tactile control.  ...  -06222 and DPI2008-02647 and the grant AP2005-1458.  ... 
doi:10.3390/s91209689 pmid:22303146 pmcid:PMC3267194 fatcat:ejjzr5zjova5vfrdlmiqss7mea

Hallucinating Robots: Inferring Obstacle Distances from Partial Laser Measurements

Jens Lundell, Francesco Verdoja, Ville Kyrki
2018 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)  
Finally, we qualitatively demonstrate in real time on a Care-O-bot 4 that the trained network can successfully infer obstacle distances from partial 2D laser readings.  ...  To learn a mapping from raw 2D laser distances to obstacle distances we frame the problem as a learning task and train a neural network formed as an autoencoder.  ...  In the context of obstacle detection, the use of neural networks has been proposed to infer bounding boxes of pedestrians and vehicles from 3D laser data of typical road scenes [6] , [8] and to track  ... 
doi:10.1109/iros.2018.8594399 dblp:conf/iros/LundellVK18 fatcat:yymztkmn5zfp5audladwovsowq

A Survey of Algorithms and Systems for Evacuating People in Confined Spaces

Huibo Bi, Erol Gelenbe
2019 Electronics  
We present a comprehensive review of research on emergency evacuation and wayfinding, focusing on the algorithmic and system design aspects.  ...  Starting from the history of emergency management research, we identify the emerging challenges concerning system optimisation, evacuee behaviour optimisation and data analysis, and the additional energy  ...  patient. the velocity and the action of evacuees was determined by the social force model and the neural network model, respectively; the neural network had four inputs: the personality of an evacuee,  ... 
doi:10.3390/electronics8060711 fatcat:i6h2fpkyqrhgfpmjahvels5azu

Leveraging Machine Learning and Big Data for Smart Buildings: A Comprehensive Survey [article]

Basheer Qolomany, Ala Al-Fuqaha, Ajay Gupta, Driss Benhaddou, Safaa Alwajidi, Junaid Qadir, Alvis C. Fong
2019 arXiv   pre-print
The massive streaming data generated and captured by smart building appliances and devices contains valuable information that needs to be mined to facilitate timely actions and better decision making.  ...  Changes will occur to the way people live as technology involves into people's lives and information processing is fully integrated into their daily living activities and objects.  ...  The system uses a neural network, assistive software, and a variety of sensors such as illumination sensor, temperature sensor, door sensors, and RFID giving the capacity of controlling the white goods  ... 
arXiv:1904.01460v2 fatcat:rz2gsyurkradlkqvfankw3zue4

Smart Ventilation for Energy Conservation in Buildings

Hwataik Han, Muhammad Hatta, Haolia Rahman
2019 Evergreen  
The real-time ventilation control algorithm is applied successfully without any recursive problems.  ...  Experiments are conducted to control the outdoor airflow rate in real time according to the estimated number of occupants.  ...  Fig. 1 :Fig. 3 :Fig. 2 : 132 Biological neural network (left) and artificial neural network (right) Experimental Concept of a Bayesian inference biological neural network shown in Fig. 4 : 4 Block diagram  ... 
doi:10.5109/2321005 fatcat:7b4p4iqfrbbfhp2xdei3fi72pa

DDDAS for Autonomic Interconnected Systems: The National Energy Infrastructure [chapter]

C. Hoffmann, E. Swain, Y. Xu, T. Downar, L. Tsoukalas, P. Top, M. Senel, M. Bell, E. Coyle, B. Loop, D. Aliprantis, O. Wasynczuk (+1 others)
2007 Lecture Notes in Computer Science  
The most critical element of the nation's energy infrastructure is our electricity generation, transmission, and distribution system known as the "power grid."  ...  model parameters, the results do not provide grid operators with accurate "real time" information that can be used to avoid major blackouts such as were experienced on the East Coast in August of 2003  ...  predictive simulation of the terrestrial electric power grid: faster-than-real-time simulation, distributed dynamic sensing, the development of neural-network-based behavioral models for situations where  ... 
doi:10.1007/978-3-540-72584-8_141 fatcat:vzjwjxr675f77kmm7o25aivbxi

Monitoring of the daily living activities in smart home care

Jan Vanus, Jana Belesova, Radek Martinek, Jan Nedoma, Marcel Fajkus, Petr Bilik, Jan Zidek
2017 Human-Centric Computing and Information Sciences  
With the use of the trained network ANN, we realized a strictly controlled short-term (11 h) experiment without the use of CO2 sensor.  ...  (R) and the length of the measured training time ANN.  ...  Acknowledgements This paper has been elaborated in the framework of the projects SP2017/128 of Student Grant System, VSB-TU Ostrava and "Promotion of Development of NEK activities in the field of energy  ... 
doi:10.1186/s13673-017-0113-6 fatcat:iy2eojxkj5fqlkbrzizufiqmym

Integrating Deep Learning and Augmented Reality to Enhance Situational Awareness in Firefighting Environments [article]

Manish Bhattarai
2021 arXiv   pre-print
First, we used a deep Convolutional Neural Network (CNN) system to classify and identify objects of interest from thermal imagery in real-time.  ...  Finally, we used a low computational unsupervised learning technique called tensor decomposition to perform meaningful feature extraction for anomaly detection in real-time.  ...  40] , and lightweight deep neural networks for real-time object detection (PVANET) [76] ).  ... 
arXiv:2107.11043v2 fatcat:3jm5zawelze7dhx37luja7mly4
« Previous Showing results 1 — 15 out of 4,100 results