Scipediacontent: Scipediacontent moved page Draft Content 713904063 to Schwertfeger et al 2018a

2021-02-03T18:07:56Z

Scipediacontent moved page Draft Content 713904063 to Schwertfeger et al 2018a

Scipediacontent: Created page with " == Abstract == In this paper, we demonstrate our work on Gaussian Process Occupancy Mapping (GPOM). We concentrate on the inefficiency of the frame computation of the classi..."

2021-02-03T18:07:53Z

Created page with " == Abstract == In this paper, we demonstrate our work on Gaussian Process Occupancy Mapping (GPOM). We concentrate on the inefficiency of the frame computation of the classi..."

New page

== Abstract ==

In this paper, we demonstrate our work on Gaussian Process Occupancy Mapping (GPOM). We concentrate on the inefficiency of the frame computation of the classical GPOM approaches. In robotics, most of the algorithms are required to run in real time. However, the high cost of computation makes the classical GPOM less useful. In this paper we dont try to optimize the Gaussian Process itself, instead, we focus on the application. By analyzing the time cost of each step of the algorithm, we find a way that to reduce the cost while maintaining a good performance compared to the general GPOM framework. From our experiments, we can find that our model enables GPOM to run online and achieve a relatively better quality than the classical GPOM.

Comment: Accepted to ICARCV2018

== Original document ==

The different versions of the original document can be found in:

* [http://arxiv.org/abs/1811.10156 http://arxiv.org/abs/1811.10156]

* [http://arxiv.org/pdf/1811.10156 http://arxiv.org/pdf/1811.10156]

* [http://xplorestaging.ieee.org/ielx7/8564369/8580630/08581356.pdf?arnumber=8581356 http://xplorestaging.ieee.org/ielx7/8564369/8580630/08581356.pdf?arnumber=8581356],
: [http://dx.doi.org/10.1109/icarcv.2018.8581356 http://dx.doi.org/10.1109/icarcv.2018.8581356]

* [https://dblp.uni-trier.de/db/journals/corr/corr1811.html#abs-1811-10156 https://dblp.uni-trier.de/db/journals/corr/corr1811.html#abs-1811-10156],
: [https://arxiv.org/abs/1811.10156 https://arxiv.org/abs/1811.10156],
: [https://ui.adsabs.harvard.edu/abs/2018arXiv181110156Y/abstract https://ui.adsabs.harvard.edu/abs/2018arXiv181110156Y/abstract],
: [https://robotics.shanghaitech.edu.cn/node/223 https://robotics.shanghaitech.edu.cn/node/223],
: [https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/29121 https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/29121],
: [http://arxiv.org/pdf/1811.10156.pdf http://arxiv.org/pdf/1811.10156.pdf],
: [https://academic.microsoft.com/#/detail/2901918920 https://academic.microsoft.com/#/detail/2901918920]

← Older revision	Revision as of 18:07, 3 February 2021
(No difference)

Schwertfeger et al 2018a - Revision history

Scipediacontent: Scipediacontent moved page Draft Content 713904063 to Schwertfeger et al 2018a

Scipediacontent: Created page with " == Abstract == In this paper, we demonstrate our work on Gaussian Process Occupancy Mapping (GPOM). We concentrate on the inefficiency of the frame computation of the classi..."