Filters








4,956 Hits in 8.1 sec

Quantitative Analysis of Nearest-Neighbors Search in High-Dimensional Sampling-Based Motion Planning [chapter]

Erion Plaku, Lydia E. Kavraki
Springer Tracts in Advanced Robotics  
We quantitatively analyze the performance of exact and approximate nearest-neighbors algorithms on increasingly high-dimensional problems in the context of sampling-based motion planning.  ...  As a result, exact nearest-neighbors algorithms become impractical for sampling-based motion planners when a considerably large number of samples needs to be generated.  ...  Work on this paper by the authors has been supported in part by NSF 0205671, NSF 0308237, ATP 003604-0010-2003, NIH GM078988, and a Sloan Fellowship to LK.  ... 
doi:10.1007/978-3-540-68405-3_1 fatcat:k6rh66mawfholanzf3yjsv6iyi

Nonlinear Dimensionality Reduction using Approximate Nearest Neighbors [chapter]

Erion Plaku, Lydia E. Kavraki
2007 Proceedings of the 2007 SIAM International Conference on Data Mining  
The approximation relies on a distance-based projection of high-dimensional data onto low-dimensional Euclidean spaces.  ...  Nonlinear dimensionality reduction methods often rely on the nearest-neighbors graph to extract low-dimensional embeddings that reliably capture the underlying structure of high-dimensional data.  ...  Potential applications which we are currently addressing include the analysis of molecular motions of proteins and the behavior of motion planning algorithms on high-dimensional problems. .  ... 
doi:10.1137/1.9781611972771.17 dblp:conf/sdm/PlakuK07 fatcat:ferjqsdxjja67krxb6dmmi7ngi

Learning pathological deviations from a normal pattern of myocardial motion [chapter]

N. Duchateau, G. Piella, A. Frangi, M. De Craene
2016 Machine Learning and Medical Imaging  
in! this!new!N[dimensional!space.! ! [Insert!Figure!10.2!here]! ! ' ' ! 9! Tuning'parameters.! The!algorithm!starts!building!a!graph!of!the!training!samples,!by!connecting!nearest!neighbors!  ...  nearest[neighbors!search,! using! the! Euclidean! distance! as! metric.! Then,! the! shortest! path! between! each! pair! of! samples! is! taken! as! surrogate!for!the!geodesic!distance,!and!stored!  ... 
doi:10.1016/b978-0-12-804076-8.00012-8 fatcat:xwlekdonanhnrdjfrj6cfdpxnu

Liveness-Based RRT Algorithm for Autonomous Underwater Vehicles Motion Planning

Yang Li, Fubin Zhang, Demin Xu, Jiguo Dai
2017 Journal of Advanced Transportation  
This paper presents a new version of rapidly exploring random trees (RRT), that is, liveness-based RRT (Li-RRT), to address autonomous underwater vehicles (AUVs) motion problem.  ...  Motion planning is a crucial, basic issue in robotics, which aims at driving vehicles or robots towards to a given destination with various constraints, such as obstacles and limited resource.  ...  Acknowledgments This work was supported by the National Natural Science Foundation of China (NSFC) under Grants 61472325 and 61273333.  ... 
doi:10.1155/2017/7816263 fatcat:rgkw5x32rnfhtk7xvfzvgwlqia

Sampling-based A* algorithm for robot path-planning

Sven Mikael Persson, Inna Sharf
2014 The international journal of robotics research  
This paper presents a generalization of the classic A* algorithm to the domain of sampling-based motion-planning.  ...  Empirical results are presented to assess the proposed method both qualitatively and quantitatively in the context of high-dimensional planning problems.  ...  The authors would like to thank the reviewers of this article for providing very constructive feedback and for upholding the high standards of rigor required for productive scientific discourse.  ... 
doi:10.1177/0278364914547786 fatcat:3mfufmx64vfwzaydu3objkzwn4

Motion Synthesis through Randomized Exploration on Submanifolds of Configuration Space [chapter]

Ioannis Havoutis, Subramanian Ramamoorthy
2010 Lecture Notes in Computer Science  
, which is in turn used to focus the exploration of a sampling based motion planning algorithm.  ...  Solving these problems by general purpose methods such as sampling based motion planning has involved significant computational complexity, and has also required specialised heuristics to handle constraints  ...  Our interest is in incorporating this feature directly into sampling based motion planning.  ... 
doi:10.1007/978-3-642-11876-0_9 fatcat:37dme2sem5e3xl5sbz4fxahsei

Monocular real-time 3D articulated hand pose estimation

Javier Romero, Hedvig Kjellstrom, Danica Kragic
2009 2009 9th IEEE-RAS International Conference on Humanoid Robots  
The method is non-parametric, performing a nearest neighbor search in a large database (100000 entries) of hand pose examples.  ...  An additional contribution is the modeling of constraints based on temporal consistency in hand pose, without explicitly tracking the hand in the high dimensional pose space.  ...  The method is non-parametric, performing a nearest neighbor search in a large database (100000 entries) of hand pose examples.  ... 
doi:10.1109/ichr.2009.5379596 dblp:conf/humanoids/RomeroKK09 fatcat:f62oywjbm5a2hh3pdtdlr3ud5m

Using hand synergies as an optimality criterion for planning human-like motions for mechanical hands

Jan Rosell, Raul Suarez
2014 2014 IEEE-RAS International Conference on Humanoid Robots  
The planning of the motions of these hands is not easy due to the high number of degrees of freedom (DOF) involved.  ...  This paper extends this idea by using an RRT*, that differently from other sampling-based planners, is an asymptotically optimal method.  ...  The authors are with the Institute of Industrial and Control Engineering (IOC), Universitat Politècnica de Catalunya (UPC) -Barcelona Tech, Barcelona, Spain, {jan.rosell, raul.suarez}@upc.edu.  ... 
doi:10.1109/humanoids.2014.7041365 dblp:conf/humanoids/RosellS14 fatcat:jwcwtflajrf4tazbpyacfwkkky

An Empirical Evaluation of the t-SNE Algorithm for Data Visualization in Structural Engineering [article]

Parisa Hajibabaee, Farhad Pourkamali-Anaraki, Mohammad Amin Hariri-Ardebili
2021 arXiv   pre-print
A fundamental task in machine learning involves visualizing high-dimensional data sets that arise in high-impact application domains.  ...  In this paper, the t-Distributed Stochastic Neighbor Embedding (t-SNE) algorithm is used to reduce the dimensions of an earthquake engineering related data set for visualization purposes.  ...  Classification is computed based on a majority vote of the nearest neighbors of each point: a query point is assigned the data class which has the most representatives within the nearest neighbors of the  ... 
arXiv:2109.08795v1 fatcat:d6ave5xj2zbdhclg2rftdjvdqy

Continuous Control Monte Carlo Tree Search Informed by Multiple Experts

Joose Julius Rajamaki, Perttu Hamalainen
2018 IEEE Transactions on Visualization and Computer Graphics  
We present a sampling-based model-predictive controller that comes in the form of a Monte Carlo tree search (MCTS).  ...  While learning, the algorithm runs in near real-time, and after learning the sampling budget can be reduced for real-time operation.  ...  This work was supported by the Academy of Finland (grants 299358 and 305737). Joose Rajamäki additionally thanks Tekniikan edistämissäätiö for their support.  ... 
doi:10.1109/tvcg.2018.2849386 pmid:29994613 fatcat:q3z2gwrpjvbcvetxqjk4gpugwy

A new approach for robot motion planning using rapidly-exploring Randomized Trees

Lukas Krammer, Wolfgang Granzer, Wolfgang Kastner
2011 2011 9th IEEE International Conference on Industrial Informatics  
In the last few years, car-like robots became increasingly important. Thus, motion planning algorithms for this kind of problem are needed more than ever.  ...  This paper introduces a new concept for robot motion planning especially for car-like robots based on Rapidly-exploring Randomized Trees.  ...  At the beginning, the procedure searches for the nearest neighbor of the given random state.  ... 
doi:10.1109/indin.2011.6034885 fatcat:nxd45sprzjfdrf5iczry4phmeq

Computer Aided Planning And Execution Of Craniofacial Surgical Procedures

Cutting, Taylor, Bookstein, Khorramabadi, Haddad, Kalvin, Hiechun Kim, Noz
1992 Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society  
In 1983 we began clinical evaluation of a surgical simulation program based on a threedimensionalization of a cephalogram (Cutting et al. 1986a) .  ...  Numerical printouts specified the movements of each piece. The surgeon could use these "surgical blueprints" in the operating room.  ...  High precision planning is of little use if the surgeon is unable to carry it out.  ... 
doi:10.1109/iembs.1992.594718 fatcat:fnfnv23dbvg2fj6h7yvwi73woe

Computer aided planning and execution of craniofacial surgical procedures

Court Cutting, Russell Taylor, Fred Bookstein, Deljou Khorramabadi, Betsy Haddad, Alan Kalvin, Hiechun Kim, Marilyn Noz
1992 Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society  
In 1983 we began clinical evaluation of a surgical simulation program based on a threedimensionalization of a cephalogram (Cutting et al. 1986a) .  ...  Numerical printouts specified the movements of each piece. The surgeon could use these "surgical blueprints" in the operating room.  ...  High precision planning is of little use if the surgeon is unable to carry it out.  ... 
doi:10.1109/iembs.1992.5761357 fatcat:phpg3jjhybhwvfewt6ywtppjsi

Graph-based trajectory planning through programming by demonstration

Nik A. Melchior, Reid Simmons
2012 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems  
I am also grateful to my master's advisor, Bill Smart, whose enthusiasm and encouragement ignited my interest in robotics. I hope to find opportunities to work with each of them in the future.  ...  I am grateful for for his guidance and shared knowledge in the many areas of robotics that I have been privileged to explore with him.  ...  The first subroutine, NeighborRuns (Algorithm 5.2), searches for runs, or subsequences of the trajectories in which the nearest neighbors roughly correspond.  ... 
doi:10.1109/iros.2012.6386101 dblp:conf/iros/MelchiorS12 fatcat:dz63sk7hr5b5hkbrzlfct2m434

A Data-Driven Framework for Visual Crowd Analysis

Panayiotis Charalambous, Ioannis Karamouzas, Stephen J. Guy, Yiorgos Chrysanthou
2014 Computer graphics forum (Print)  
criteria in a principled fashion using Principle Component Analysis and the notion of Pareto Optimality.  ...  To that end, we introduce a new framework for the visual analysis of crowd simulations.  ...  Xu for helpful discussions on the Pareto Depth Analysis method.  ... 
doi:10.1111/cgf.12472 fatcat:dynnxzj57nfefj466x7e7pltie
« Previous Showing results 1 — 15 out of 4,956 results