Filters








1,689 Hits in 6.2 sec

Robust Topological Feature Extraction for Mapping of Environments using Bio-Inspired Sensor Networks [article]

Alireza Dirafzoon, Edgar Lobaton
2014 arXiv   pre-print
To extract dominant features from sampled data, topological data analysis is used to produce persistence intervals for features, to be used for topological mapping.  ...  In this paper, we exploit minimal sensing information gathered from biologically inspired sensor networks to perform exploration and mapping in an unknown environment.  ...  Contribution: In this paper, we aim to construct topological maps of unknown environments using bio-inspired mobile sensor networks under the constraint of limited sensing information.  ... 
arXiv:1410.4622v1 fatcat:nss2bwrbijfpxhemaz52fxwnn4

Underwater SLAM: Challenges, state of the art, algorithms and a new biologically-inspired approach

Felipe Guth, Luan Silveira, Silvia Botelho, Paulo Drews, Pedro Ballester
2014 5th IEEE RAS/EMBS International Conference on Biomedical Robotics and Biomechatronics  
The unstructured scenario, the extraction of significant features, the imprecision of sensors along with the impossibility of using GPS signals are some of the challenges encountered in underwater environments  ...  Given the limitations of probabilistic approaches, a new alternative based on a bio-inspired model is highlighted.  ...  ACKNOWLEDGMENT The authors gratefully acknowledge the contribution of CAPES, CNPQ and Oil Brazilian Agency (ANP).  ... 
doi:10.1109/biorob.2014.6913908 dblp:conf/biorob/GuthSBDB14 fatcat:2iwpvnjorzagxfbgc3f57yfuge

Towards bio-inspired unsupervised representation learning for indoor aerial navigation [article]

Ni Wang, Ozan Catal, Tim Verbelen, Matthias Hartmann, Bart Dhoedt
2021 arXiv   pre-print
To tackle that problem, this research displays a biologically inspired deep-learning algorithm for simultaneous localization and mapping (SLAM) and its application in a drone navigation system.  ...  The designed algorithm is evaluated on a dataset collected in an indoor warehouse environment, and initial results show the feasibility for robust indoor aerial navigation.  ...  ACKNOWLEDGMENT O.Ç . is funded by a Ph.D. grant of the Flanders Research Foundation (FWO).  ... 
arXiv:2106.09326v1 fatcat:m2fxiwavivgxfonexgy5xa3cee

ViTa-SLAM: A Bio-inspired Visuo-Tactile SLAM for Navigation while Interacting with Aliased Environments [article]

Oliver Struckmeier, Kshitij Tiwari, Mohammed Salman, Martin J. Pearson, Ville Kyrki
2019 arXiv   pre-print
RatSLAM is a rat hippocampus-inspired visual Simultaneous Localization and Mapping (SLAM) framework capable of generating semi-metric topological representations of indoor and outdoor environments.  ...  Compared to the former works, our approach can handle ambiguous scenes in which one sensor alone is not capable of identifying false-positive loop-closures.  ...  CONCLUSION AND FUTURE WORKS This work demonstrated a novel bio-inspired multi-sensory SLAM mechanism for a robot exploring and interacting with 2 Video demonstration available here. an environment that  ... 
arXiv:1906.06422v4 fatcat:hgd7l2lnnzfgra6klgvv4kfnzu

ViTa-SLAM: A Bio-inspired Visuo-Tactile SLAM for Navigation while Interacting with Aliased Environments

Oliver Struckmeier, Kshitij Tiwari, Mohammed Salman, Martin J. Pearson, Ville Kyrki
2019 2019 IEEE International Conference on Cyborg and Bionic Systems (CBS)  
RatSLAM is a rat hippocampus-inspired visual Simultaneous Localization and Mapping (SLAM) framework capable of generating semi-metric topological representations of indoor and outdoor environments.  ...  Compared to the former works, our approach can handle ambiguous scenes in which one sensor alone is not capable of identifying false-positive loop-closures. * The authors have equal contribution.  ...  CONCLUSION AND FUTURE WORKS This work demonstrated a novel bio-inspired multisensory SLAM mechanism for a robot exploring and interacting with an environment that presents ambiguous cues.  ... 
doi:10.1109/cbs46900.2019.9114526 dblp:conf/cbs/StruckmeierTSPK19 fatcat:ke4woczusngflmqbxxskbrs2jy

Bio-inspired homogeneous multi-scale place recognition

Zetao Chen, Stephanie Lowry, Adam Jacobson, Michael E. Hasselmo, Michael Milford
2015 Neural Networks  
recognition performance benefits for navigating robots in large real world environments, especially using more than two homogeneous map scales.  ...  We present methods for training each network to learn and recognize places at a specific spatial scale, and techniques for combining the output from each of these parallel networks.  ...  We briefly review evidence for multi-scale maps in the mammalian brain and note other bio-inspired mapping and navigation systems.  ... 
doi:10.1016/j.neunet.2015.10.002 pmid:26576467 fatcat:kkz7wzh3zzhivbqpdacr4kd3am

Multi-resolution SLAM for Real World Navigation [chapter]

Agostino Martinelli, Adriana Tapus, Kai Olivier Arras, Roland Siegwart
2005 Springer Tracts in Advanced Robotics  
The fingerprint used for topological navigation enables also the re-initialization of the metric localization.  ...  The metric approach, based on the Kalman Filter, uses a new concept to avoid the problem of the drift in odometry. For the topological framework the fingerprint sequence approach is used.  ...  networks, e.g. the work by Hafner [10] uses a neural network to create a topological map of the environment based on images of an omni-directional camera.  ... 
doi:10.1007/11008941_47 fatcat:66o5wv3qtzfnvgd2ee2lxh4tpu

Evaluation of Bio-inspired SLAM algorithm based on a Heterogeneous System CPU-GPU

Rachid Latif, Kaoutar Dahmane, Monir Amraoui, Amine Saddik, Abdelouahed Elouardi, S. Krit
2021 E3S Web of Conferences  
In this work we propose an implementation of the bio-inspired SLAM algorithm RatSLAM based on a heterogeneous system type CPU-GPU.  ...  The evaluation of the algorithm showed that with C/C++ we have an executing time of 170.611 ms with a processing of 5 frames/s and for the implementation on a heterogeneous system we used CUDA as language  ...  The identification of places is reached by using a neural network, RatSLAM able to generating topological representations of outdoor and indoor environments, the RatSLAM algorithm is composed of 4 blocks  ... 
doi:10.1051/e3sconf/202122901023 fatcat:m45zk6scazecnf7vkepkmf3xjy

A Cognitive Model for Humanoid Robot Navigation and Mapping using Alderbaran NAO [article]

Jiawei Xu, Ruisheng Wang, Shigang Yue, Loo Chu Kiong
2014 arXiv   pre-print
Cognitive mapping is assumed as three parts, whose representations were proposed a network of ASRs, an MFIS, and a hierarchy of Place Representations.  ...  The aim of this work is to build a cognitive model for the humanoid robot, especially, we are interested in the navigation and mapping on the humanoid robot.  ...  The robustness of our cognitive model by using vision sensor is the research emphasis. Moreover, we would like to test the theory that this is how humans map their environment.  ... 
arXiv:1405.3095v2 fatcat:xnbgjjzyvreulmfrvqaja7vliq

Human Action Recognition with Hierarchical Growing Neural Gas Learning [chapter]

German Ignacio Parisi, Cornelius Weber, Stefan Wermter
2014 Lecture Notes in Computer Science  
We propose a novel biologically inspired framework for the recognition of human full-body actions. First, we extract body pose and motion features from depth map sequences.  ...  Experiments on a set of 10 human actions show that the use of multi-cue learning leads to substantially increased recognition accuracy over the single-cue approach and the learning of joint pose-motion  ...  The use of skeleton model-based techniques for tracking action features in terms of a set of joints and limbs has shown good results, especially for approaches using depth maps [4] .  ... 
doi:10.1007/978-3-319-11179-7_12 fatcat:kof4ezxmgjgbtdtu7xozqeg7cq

On Swarm Intelligence Inspired Self-Organized Networking: Its Bionic Mechanisms, Designing Principles and Optimization Approaches

Zhongshan Zhang, Keping Long, Jianping Wang, Falko Dressler
2014 IEEE Communications Surveys and Tutorials  
Inspired by swarm intelligence observed in social species, the artificial self-organized networking (SON) systems are expected to exhibit some intelligent features (e.g., flexibility, robustness, decentralized  ...  The existing well-known bio-inspired algorithms such as pulse-coupled oscillators (PCO)based synchronization, ant-and/or bee-inspired cooperation and division of labor, immune systems inspired network  ...  ACKNOWLEDGMENT The authors would like to acknowledge the editor and anonymous reviewers for their critical comments, which greatly improved this paper.  ... 
doi:10.1109/surv.2013.062613.00014 fatcat:gil3a5vbm5abzbrnbsyfagosr4

A Bio-inspired Framework for Highly Efficient Structural Health Monitoring and Vibration Analysis [chapter]

Maria-Giovanna Masciotta, Alberto Barontini, Luís F. Ramos, Paulo Amado-Mendes, Paulo B. Lourenço
2017 Lecture Notes in Civil Engineering  
and lead to new sensing paradigms for optimal network to pology and sensors location.  ...  The scope of this paper is to present a bio-inspired framework for optimal structural health monitoring and vibration analysis.  ...  the scope of the project POCI-01-0145-FED ER-007633.  ... 
doi:10.1007/978-3-319-67443-8_39 fatcat:ecdzgggtx5eetjywtjx2lvd2re

Efficient Feedforward Categorization of Objects and Human Postures with Address-Event Image Sensors

Shoushun Chen, P. Akselrod, Bo Zhao, J. A. Perez-Carrasco, B. Linares-Barranco, E. Culurciello
2012 IEEE Transactions on Pattern Analysis and Machine Intelligence  
An event-based temporal difference image sensor is used to provide input video sequences, while a software module extracts size and position invariant line features inspired by models of the primate visual  ...  The system employs an innovative combination of event-based hardware and bio-inspired software architecture.  ...  We use a temporal difference image sensor named Mo-toTrigger [19] , [36] , combined with a software implementation of a bio-inspired feature extraction unit and a classifier.  ... 
doi:10.1109/tpami.2011.120 pmid:21670481 fatcat:llkekdkxzrb2ppan6lnhv4sygm

Embedded neuromorphic vision for humanoid robots

Chiara Bartolozzi, Francesco Rea, Charles Clercq, Daniel B. Fasnacht, Giacomo Indiveri, Michael Hofstatter, Giorgio Metta
2011 CVPR 2011 WORKSHOPS  
We are developing an embedded vision system for the humanoid robot iCub, inspired by the biology of the mammalian visual system, including concepts such as stimulusdriven, asynchronous signal sensing and  ...  It comprises stimulus-driven sensors, a dedicated embedded processor and an event-based software infrastructure for processing visual stimuli.  ...  it will be used for extracting high-level information about the environment.  ... 
doi:10.1109/cvprw.2011.5981834 dblp:conf/cvpr/BartolozziRCHFI11 fatcat:sdzr4andx5c4vpmphtuqzszcvm

A Hardware-Deployable Neuromorphic Solution for Encoding and Classification of Electronic Nose Data

Anup Vanarse, Adam Osseiran, Alexander Rassau, Peter van der Made
2019 Sensors  
Recent developments in spike-based bio-inspired approaches have delivered solutions for the highly accurate classification of multivariate sensor data with minimized computational and power requirements  ...  Through this investigation, we proposed a spiking neural network (SNN)-based classifier, implemented in a chip-emulation-based development environment, that can be seamlessly deployed on a neuromorphic  ...  Conflicts of Interest: The authors declare no conflict of interest. Sensors 2019, 19, 4831  ... 
doi:10.3390/s19224831 pmid:31698785 pmcid:PMC6891685 fatcat:2ybjtx247ff3bcdwv4z5qqjs3e
« Previous Showing results 1 — 15 out of 1,689 results