{"id":321,"date":"2024-08-21T01:07:42","date_gmt":"2024-08-21T01:07:42","guid":{"rendered":"https:\/\/neuromorphicrobotics.com\/?p=321"},"modified":"2025-06-30T09:17:49","modified_gmt":"2025-06-30T09:17:49","slug":"how-to-implement-visual-odometry-with-neuromorphic-resonator-networks","status":"publish","type":"post","link":"https:\/\/braininspiredrobotics.com\/?p=321","title":{"rendered":"How to implement visual odometry with neuromorphic resonator networks?"},"content":{"rendered":"<p style=\"text-align: justify;\">Alpha Renner, Lazar Supic, Andreea Danielescu, Giacomo Indiveri, E. Paxon Frady, Friedrich T. Sommer &amp; Yulia Sandamirskaya. <a href=\"https:\/\/www.nature.com\/articles\/s42256-024-00846-2\"><strong>Visual odometry with neuromorphic resonator networks<\/strong><\/a>. Nature Machine Intelligence, 6, 653\u2013663 (2024). https:\/\/doi.org\/10.1038\/s42256-024-00846-2<\/p>\n<p style=\"text-align: justify;\">Abstract<br \/>\n&#8220;Visual odometry (VO) is a method used to estimate self-motion of a mobile robot using visual sensors. Unlike odometry based on integrating differential measurements that can accumulate errors, such as inertial sensors or wheel encoders, VO is not compromised by drift. However, <strong><span style=\"color: #ff0000;\">image-based VO is computationally demanding, limiting its application in use cases with low-latency, low-memory and low-energy requirements<\/span><\/strong>. Neuromorphic hardware offers low-power solutions to many vision and artificial intelligence problems, but<strong><span style=\"color: #ff0000;\"> designing such solutions is complicated and often has to be assembled from scratch<\/span><\/strong>. Here we propose the use of vector symbolic architecture (VSA) as an abstraction layer to design algorithms compatible with neuromorphic hardware. Building from a VSA model for scene analysis, described in our companion paper, <strong><span style=\"color: #ff0000;\">we present a modular neuromorphic algorithm that achieves state-of-the-art performance on two-dimensional VO tasks<\/span><\/strong>. Specifically, the proposed algorithm<strong><span style=\"color: #ff0000;\"> stores and updates a working memory of the presented visual environment<\/span><\/strong>. Based on this working memory, <strong><span style=\"color: #ff0000;\">a resonator network estimates the changing location and orientation of the camera<\/span><\/strong>. We experimentally validate the <strong><span style=\"color: #ff0000;\">neuromorphic VSA-based approach to VO<\/span> <\/strong>with two benchmarks: one based on an event-camera dataset and the other in a dynamic scene with a robotic task.&#8221;<\/p>\n<p style=\"text-align: justify;\">Alpha Renner, Lazar Supic, Andreea Danielescu, Giacomo Indiveri, E. Paxon Frady, Friedrich T. Sommer &amp; Yulia Sandamirskaya. <a href=\"https:\/\/www.nature.com\/articles\/s42256-024-00846-2\"><strong>Visual odometry with neuromorphic resonator networks<\/strong><\/a>. Nature Machine Intelligence, 6, 653\u2013663 (2024). https:\/\/doi.org\/10.1038\/s42256-024-00846-2<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Alpha Renner, Lazar Supic, Andreea Danielescu, Giacomo Indiveri, E. Paxon Frady, Friedrich T. Sommer &amp; Yulia Sandamirskaya. Visual odometry with neuromorphic resonator networks. Nature Machine Intelligence, 6, 653\u2013663 (2024). https:\/\/doi.org\/10.1038\/s42256-024-00846-2 Abstract &#8220;Visual odometry (VO) is a method used to estimate self-motion of a mobile robot using visual sensors. Unlike odometry based on integrating differential measurements [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[74,6,7],"tags":[81,50,49],"class_list":["post-321","post","type-post","status-publish","format-standard","hentry","category-brain-inspired-robotics","category-neuromorphic-intelligence","category-neuromorphic-robotics","tag-neuromorphic","tag-resonator-networks","tag-visual-odometry"],"_links":{"self":[{"href":"https:\/\/braininspiredrobotics.com\/index.php?rest_route=\/wp\/v2\/posts\/321","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/braininspiredrobotics.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/braininspiredrobotics.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/braininspiredrobotics.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/braininspiredrobotics.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=321"}],"version-history":[{"count":1,"href":"https:\/\/braininspiredrobotics.com\/index.php?rest_route=\/wp\/v2\/posts\/321\/revisions"}],"predecessor-version":[{"id":322,"href":"https:\/\/braininspiredrobotics.com\/index.php?rest_route=\/wp\/v2\/posts\/321\/revisions\/322"}],"wp:attachment":[{"href":"https:\/\/braininspiredrobotics.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=321"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/braininspiredrobotics.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=321"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/braininspiredrobotics.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=321"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}