The Beobot Platform for Embedded Real-Time Neuromorphic Vision

The Beobot Platform for Embedded Real-Time Neuromorphic Vision. Itti, L. In Dietterich, T. G., Becker, S., & Ghahramani, Z., editors, Advances in Neural Information Processing Systems, Vol. 15, Hardware Demo Track, Cambridge, MA, 2003. MIT Press.
abstract bibtex

We demonstrate a new mobile robotics platform designed for the implementation and testing of neuromorphic vision algorithms in unconstrained outdoors environments. It is being developed by a team of undergraduate students with graduate supervision and help. Its distinctive features include significant computational power (four 1.4GHz CPUs with gigabit interconnect), high-speed four-wheel-drive chassis, standard Linux operating system, and a comprehensive toolkit of C++ vision classes. The robot is designed with two major goals in mind: real-time operation of sophisticated neuromorphic vision algorithms, and off-the-shelf components to ensure rapid technological evolvability. A preliminary embedded neuromorphic vision architecture that includes attentional, gist/layout, object recognition, and high-level decision subsystems is showcased (see http://iLab.usc.edu/beobots/ for additional information).

@inproceedings{ Itti03nips,
  title = {The Beobot Platform for Embedded Real-Time Neuromorphic Vision},
  author = {L. Itti},
  abstract = {We demonstrate a new mobile robotics platform designed for the
implementation and testing of neuromorphic vision algorithms in
unconstrained outdoors environments. It is being developed by a team
of undergraduate students with graduate supervision and help. Its
distinctive features include significant computational power (four
1.4GHz CPUs with gigabit interconnect), high-speed four-wheel-drive
chassis, standard Linux operating system, and a comprehensive toolkit
of C++ vision classes. The robot is designed with two major goals in
mind: real-time operation of sophisticated neuromorphic vision
algorithms, and off-the-shelf components to ensure rapid technological
evolvability.  A preliminary embedded neuromorphic vision architecture
that includes attentional, gist/layout, object recognition, and
high-level decision subsystems is showcased (see
http://iLab.usc.edu/beobots/ for additional information).},
  year = {2003},
  publisher = { MIT Press },
  editor = {T. G. Dietterich and S. Becker and Z. Ghahramani},
  address = { Cambridge, MA },
  booktitle = { Advances in Neural Information Processing Systems, Vol.
                        15, Hardware Demo Track },
  type = { mod;bu;bb;sc;cv },
  keywords = { Robotics ; Neuromorphic Engineering ; Computational Modeling ;
Visual Processing ; Visual Attention },
  file = { http://iLab.usc.edu/publications/doc/Itti03nips.pdf },
  review = {abs/conf}
}

Downloads: 0

{"_id":{"_str":"5298a1a19eb585cc26000958"},"__v":0,"authorIDs":[],"author_short":["Itti, L."],"bibbaseid":"itti-thebeobotplatformforembeddedrealtimeneuromorphicvision-2003","bibdata":{"html":"<div class=\"bibbase_paper\"> \n\n\n<span class=\"bibbase_paper_titleauthoryear\">\n\t<span class=\"bibbase_paper_title\"><a name=\"Itti03nips\"> </a>The Beobot Platform for Embedded Real-Time Neuromorphic Vision.</span>\n\t<span class=\"bibbase_paper_author\">\nItti, L.</span>\n\t\n</span>\n\n\n\nIn\nDietterich, T. G.; Becker, S.; and Ghahramani, Z., editor, <i>Advances in Neural Information Processing Systems, Vol. 15, Hardware Demo Track</i>, Cambridge, MA, 2003.\n\n\nMIT Press.\n\n\n\n\n<br class=\"bibbase_paper_content\"/>\n\n<span class=\"bibbase_paper_content\">\n \n \n \n <a href=\"javascript:showBib('Itti03nips')\"\n class=\"bibbase link\">\n \n\t\n\t\n\t\n BibTeX\n <i class=\"fa fa-caret-down\"></i></a>\n \n \n  \n <a class=\"bibbase_abstract_link bibbase link\"\n href=\"javascript:showAbstract('Itti03nips')\">\n Abstract\n <i class=\"fa fa-caret-down\"></i></a>\n \n \n \n\n \n \n \n</span>\n\n<div class=\"well well-small bibbase\" id=\"bib_Itti03nips\"\n style=\"display:none\">\n <pre>@inproceedings{ Itti03nips,\n title = {The Beobot Platform for Embedded Real-Time Neuromorphic Vision},\n author = {L. Itti},\n abstract = {We demonstrate a new mobile robotics platform designed for the\nimplementation and testing of neuromorphic vision algorithms in\nunconstrained outdoors environments. It is being developed by a team\nof undergraduate students with graduate supervision and help. Its\ndistinctive features include significant computational power (four\n1.4GHz CPUs with gigabit interconnect), high-speed four-wheel-drive\nchassis, standard Linux operating system, and a comprehensive toolkit\nof C++ vision classes. The robot is designed with two major goals in\nmind: real-time operation of sophisticated neuromorphic vision\nalgorithms, and off-the-shelf components to ensure rapid technological\nevolvability. A preliminary embedded neuromorphic vision architecture\nthat includes attentional, gist/layout, object recognition, and\nhigh-level decision subsystems is showcased (see\nhttp://iLab.usc.edu/beobots/ for additional information).},\n year = {2003},\n publisher = { MIT Press },\n editor = {T. G. Dietterich and S. Becker and Z. Ghahramani},\n address = { Cambridge, MA },\n booktitle = { Advances in Neural Information Processing Systems, Vol.\n 15, Hardware Demo Track },\n type = { mod;bu;bb;sc;cv },\n keywords = { Robotics ; Neuromorphic Engineering ; Computational Modeling ;\nVisual Processing ; Visual Attention },\n file = { http://iLab.usc.edu/publications/doc/Itti03nips.pdf },\n review = {abs/conf}\n}</pre>\n</div>\n\n\n<div class=\"well well-small bibbase\" id=\"abstract_Itti03nips\"\n style=\"display:none\">\n We demonstrate a new mobile robotics platform designed for the implementation and testing of neuromorphic vision algorithms in unconstrained outdoors environments. It is being developed by a team of undergraduate students with graduate supervision and help. Its distinctive features include significant computational power (four 1.4GHz CPUs with gigabit interconnect), high-speed four-wheel-drive chassis, standard Linux operating system, and a comprehensive toolkit of C++ vision classes. The robot is designed with two major goals in mind: real-time operation of sophisticated neuromorphic vision algorithms, and off-the-shelf components to ensure rapid technological evolvability. A preliminary embedded neuromorphic vision architecture that includes attentional, gist/layout, object recognition, and high-level decision subsystems is showcased (see http://iLab.usc.edu/beobots/ for additional information).\n</div>\n\n\n</div>\n","downloads":0,"keyword":["Robotics ; Neuromorphic Engineering ; Computational Modeling ; Visual Processing ; Visual Attention"],"bibbaseid":"itti-thebeobotplatformforembeddedrealtimeneuromorphicvision-2003","role":"author","year":"2003","type":"mod;bu;bb;sc;cv","title":"The Beobot Platform for Embedded Real-Time Neuromorphic Vision","review":"abs/conf","publisher":"MIT Press","keywords":"Robotics ; Neuromorphic Engineering ; Computational Modeling ; Visual Processing ; Visual Attention","key":"Itti03nips","id":"Itti03nips","file":"http://iLab.usc.edu/publications/doc/Itti03nips.pdf","editor_short":["Dietterich, T.<nbsp>G.","Becker, S.","Ghahramani, Z."],"editor":["Dietterich, T. G.","Becker, S.","Ghahramani, Z."],"booktitle":"Advances in Neural Information Processing Systems, Vol. 15, Hardware Demo Track","bibtype":"inproceedings","bibtex":"@inproceedings{ Itti03nips,\n title = {The Beobot Platform for Embedded Real-Time Neuromorphic Vision},\n author = {L. Itti},\n abstract = {We demonstrate a new mobile robotics platform designed for the\nimplementation and testing of neuromorphic vision algorithms in\nunconstrained outdoors environments. It is being developed by a team\nof undergraduate students with graduate supervision and help. Its\ndistinctive features include significant computational power (four\n1.4GHz CPUs with gigabit interconnect), high-speed four-wheel-drive\nchassis, standard Linux operating system, and a comprehensive toolkit\nof C++ vision classes. The robot is designed with two major goals in\nmind: real-time operation of sophisticated neuromorphic vision\nalgorithms, and off-the-shelf components to ensure rapid technological\nevolvability. A preliminary embedded neuromorphic vision architecture\nthat includes attentional, gist/layout, object recognition, and\nhigh-level decision subsystems is showcased (see\nhttp://iLab.usc.edu/beobots/ for additional information).},\n year = {2003},\n publisher = { MIT Press },\n editor = {T. G. Dietterich and S. Becker and Z. Ghahramani},\n address = { Cambridge, MA },\n booktitle = { Advances in Neural Information Processing Systems, Vol.\n 15, Hardware Demo Track },\n type = { mod;bu;bb;sc;cv },\n keywords = { Robotics ; Neuromorphic Engineering ; Computational Modeling ;\nVisual Processing ; Visual Attention },\n file = { http://iLab.usc.edu/publications/doc/Itti03nips.pdf },\n review = {abs/conf}\n}","author_short":["Itti, L."],"author":["Itti, L."],"address":"Cambridge, MA","abstract":"We demonstrate a new mobile robotics platform designed for the implementation and testing of neuromorphic vision algorithms in unconstrained outdoors environments. It is being developed by a team of undergraduate students with graduate supervision and help. Its distinctive features include significant computational power (four 1.4GHz CPUs with gigabit interconnect), high-speed four-wheel-drive chassis, standard Linux operating system, and a comprehensive toolkit of C++ vision classes. The robot is designed with two major goals in mind: real-time operation of sophisticated neuromorphic vision algorithms, and off-the-shelf components to ensure rapid technological evolvability. A preliminary embedded neuromorphic vision architecture that includes attentional, gist/layout, object recognition, and high-level decision subsystems is showcased (see http://iLab.usc.edu/beobots/ for additional information)."},"bibtype":"inproceedings","biburl":"http://ilab.usc.edu/publications/src/ilab.bib","downloads":0,"search_terms":["beobot","platform","embedded","real","time","neuromorphic","vision","itti"],"title":"The Beobot Platform for Embedded Real-Time Neuromorphic Vision","year":2003,"dataSources":["wedBDxEpNXNCLZ2sZ"]}