13,578 Hits in 3.0 sec

Sparse Graphical Memory for Robust Planning [article]

Scott Emmons, Ajay Jain, Michael Laskin, Thanard Kurutach, Pieter Abbeel, Deepak Pathak
2020 arXiv   pre-print
We introduce Sparse Graphical Memory (SGM), a new data structure that stores states and feasible transitions in a sparse memory.  ...  Recent works have attempted to combine the strengths of deep learning and classical planning; however, dominant methods in this domain are still quite brittle and scale poorly with the size of the environment  ...  In particular, we see scaling sparse graphical memory to challenging manipulation tasks as a key outstanding challenge for future work.  ... 
arXiv:2003.06417v3 fatcat:guy5tpcv5bhd7o3gga5dwipybm

Wide area localization on mobile phones

Clemens Arth, Daniel Wagner, Manfred Klopschitz, Arnold Irschara, Dieter Schmalstieg
2009 2009 8th IEEE International Symposium on Mixed and Augmented Reality  
We present a fast and memory efficient method for localizing a mobile user's 6DOF pose from a single camera image. Our approach registers a view with respect to a sparse 3D point reconstruction.  ...  Our method is resource efficient, usually requiring only a few megabytes of memory, thereby making it feasible to run on low-end devices such as mobile phones.  ...  ACKNOWLEDGEMENTS This work was partially sponsored by the Christian Doppler Laboratory for Handheld Augmented Reality and the Austrian Science Foundation FWF under contract Y193 and W1209-N15.  ... 
doi:10.1109/ismar.2009.5336494 dblp:conf/ismar/ArthWKIS09 fatcat:wrhrrivez5fnbc575drvrvmhk4

miniSAM: A Flexible Factor Graph Non-linear Least Squares Optimization Framework [article]

Jing Dong, Zhaoyang Lv
2019 arXiv   pre-print
from motion (SfM), motion planning, and control.  ...  list of sparse linear solvers, including CUDA enabled sparse linear solvers.  ...  The benchmarking is performed on a computer with Intel Core i7-6850K CPU, 128 GB memory, and a NVIDIA TITAN X GPU with 12GB graphic memory. The results are shown in Table.  ... 
arXiv:1909.00903v1 fatcat:x3nhzopuivhmzgvu7e6g3evlb4

Efficient Probabilistic Latent Semantic Indexing using Graphics Processing Unit

Eli Koffi Kouassi, Toshiyuki Amagasa, Hiroyuki Kitagawa
2011 Procedia Computer Science  
We compare the results to the most recent parallel execution of PLSI which combines a method of parallelization by OpenMP with the Message Passing Interface (MPI) for distributed memory parallelization  ...  By dealing with the sparseness of the data, we could not only process more documents and words using GPU, but we could also keep more data on the device memory so that we can avoid massive data copy transfer  ...  Acknowledgement The authors gratefully acknowledge the funding support of Grant-in-Aid for Scientific Research on Priority Areas by MEXT (#21013004).  ... 
doi:10.1016/j.procs.2011.04.040 fatcat:jxavxqszonawtpqdsdp6xebfje

An efficient level set toolkit for visual effects

Ken Museth
2009 SIGGRAPH 2009: Talks on - SIGGRAPH '09  
surfaces), and require specific access patterns (i.e. memory-sequential) for fast data accesst.  ...  The same was true for many of our fundamental level set tools, like the fast and robust scan-converter of self-intersecting polygonal meshes. These are exactly the topics of the current presentation.  ... 
doi:10.1145/1597990.1597995 dblp:conf/siggraph/Museth09 fatcat:gjnvlfnpxbfs7npniv5wrvwrsm

Parallel and efficient Boolean on polygonal solids

Hanli Zhao, Charlie C. L. Wang, Yong Chen, Xiaogang Jin
2011 The Visual Computer  
Secondly, robust depth peeling is investigated to overcome the bottleneck of layer-complexity. Thirdly, an out-of-core tiling technique is presented to overcome the limitation of memory.  ...  Real-time feedback is provided by streaming the proposed pipeline on the many-core graphics hardware.  ...  600MB of the graphics memory.  ... 
doi:10.1007/s00371-011-0571-1 fatcat:codadsonpfgvxl3pd7mx2xl7ju

FPGA-based acceleration of MRI registration: an enabling technique for improving MRI-guided cardiac therapy

Ka-Wai Kwok, Gary CT Chow, Thomas CP Chau, Yue Chen, Shelley H Zhang, Wayne Luk, Ehud J Schmidt, Zion T Tse
2014 Journal of Cardiovascular Magnetic Resonance  
High-contrast and resolution cMRIs can be obtained preoperatively as a EP roadmap for surgical planning of RFA, whilst real-time MRI (rt-MRI) can be used to guide catheterization and update the cMRI model  ...  With the use of Field-programmable Gate Array (FPGA), we hypothesized that novel data structure and architecture of memory access can allow robust registration based on comparison of image intensity patterns  ... 
doi:10.1186/1532-429x-16-s1-w11 pmcid:PMC4044607 fatcat:hznqto5xdrhptjcxoom6xxlbsq

Robust Simulation of Sparsely Sampled Thin Features in SPH-Based Free Surface Flows

Xiaowei He, Huamin Wang, Fengjun Zhang, Hongan Wang, Guoping Wang, Kun Zhou
2014 ACM Transactions on Graphics  
However, sparsely sampled thin features are difficult to simulate in SPH-based free surface flows, due to a number of robustness and stability issues.  ...  Robust simulation of sparsely sampled thin features in SPH-based free surface flows. ACM Trans. Graph. 34, 1, Article 7 (November 2014) 9 pages.  ...  ACKNOWLEDGMENTS The authors would like to thank the anonymous reviewers for their constructive comments and Mingming He for modeling, rendering and video making.  ... 
doi:10.1145/2682630 fatcat:no564vnhine2jncdpuuepc3lw4

Using Runtime Systems Tools to Implement Efficient Preconditioners for Heterogeneous Architectures

Adrien Roussel, Jean-Marc Gratien, Thierry Gautier, S. de Chaisemartin
2016 Oil & Gas Science and Technology  
for developer with the use of runtime systems.  ...  The choice of a robust preconditioner strongly impact the performance of the overall simulation.  ...  As there is many zero entries which are not necessary to keep in memory, we need a specific structure for sparse matrices which store only non-zero values.  ... 
doi:10.2516/ogst/2016020 fatcat:vxx6rbkflnhhrcemgu32zeebge

Onboard dynamic RGB‐D simultaneous localization and mapping for mobile robot navigation

Bruce Canovas, Amaury Nègre, Michèle Rombaut
2021 ETRI Journal  
[10] tightly joins sparse visual odometry and wheel-encoder integration in an optimization framework for robustness in dynamic environments.  ...  In addition, the maps they produce are often unsuitable for path planning.  ... 
doi:10.4218/etrij.2021-0061 fatcat:533437je5bfrjigf3qxvbusbfi

GPU computing in medical physics: A review

Guillem Pratx, Lei Xing
2011 Medical Physics (Lancaster)  
The graphics processing unit (GPU) has emerged as a competitive platform for computing massively parallel problems.  ...  GPU computing as well as the main performance optimization techniques, and survey existing applications in three areas of medical physics, namely image reconstruction, dose calculation and treatment plan  ...  Computer dose calculations are routinely relied upon for planning the delivery of RT.  ... 
doi:10.1118/1.3578605 pmid:21776805 fatcat:rx4alver4fbkjn7x6athn6he7i

Layered Depth-Normal Images: a Sparse Implicit Representation of Solid Models [article]

Charlie C. L. Wang, Yong Chen
2010 arXiv   pre-print
The layered depth-normal images for a solid model, whose boundary is presented by a polygonal mesh, can be generated efficiently with help of the graphics hardware accelerated sampling.  ...  Also, as will be seen later, the required memory for storing LDNIs in an acceptable resolution is much smaller than the current memory of graphics 13 card.  ...  memory is O(w 2 ) with the sampling resolution w for most practical models.  ... 
arXiv:1009.0794v1 fatcat:smrpttx4n5hf5kov5n2vnhvkza

Multi-GPU configuration of 4D intensity modulated radiation therapy inverse planning using global optimization

Aaron Hagan, Amit Sawant, Michael Folkerts, Arezoo Modiri
2018 Physics in Medicine and Biology  
We report on the design, implementation and characterization of a multi-graphic processing unit (GPU) computational platform for higher-order optimization in radiotherapy treatment planning.  ...  For evaluation, we created a 4D-IMRT treatment plan for one lung cancer patient and analyzed computation speed while varying several parameters (number of respiratory phases, GPUs, PSO particles, and data  ...  Each GK210 has 12 GB of memory, totaling 96 GB of GPU memory for our whole system.  ... 
doi:10.1088/1361-6560/aa9c96 pmid:29176059 pmcid:PMC5796762 fatcat:zv6ucwot45ajvbf7cu47pn6z5u

aGrUM: A Graphical Universal Model Framework [chapter]

Christophe Gonzales, Lionel Torti, Pierre-Henri Wuillemin
2017 Lecture Notes in Computer Science  
Afterwards, we plan to improve aGrUM's performance with integration of GPU support and memory optimization.  ...  In addition, for a high level of efficiency, CPTs can be encoded using different representations (arrays, sparse matrices, algebraic decision diagrams, etc.).  ... 
doi:10.1007/978-3-319-60045-1_20 fatcat:xj74v2uuqvbq7poe5ldym6bwaq

Sparse roadmap spanners for asymptotically near-optimal motion planning

Andrew Dobson, Kostas E. Bekris
2014 The international journal of robotics research  
Simulations for rigid body motion planning show that algorithms for constructing sparse roadmap spanners indeed provide small data structures and result in faster query resolution.  ...  An extension of SPARS is also presented, termed SPARS2, which removes the dependency on building a dense graph for constructing the sparse roadmap spanner and for which it is shown that the same desirable  ...  Defn. 2 (Robust Feasibility) An instance of the path planning problem (C free , q init , q goal ) is robustly feasible, if a cl-robust path exists that solves it, for some clearance cl > 0.  ... 
doi:10.1177/0278364913498292 fatcat:m6tyndodd5fjrfgs7lfwvs6iji
« Previous Showing results 1 — 15 out of 13,578 results