English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Autonomous agents require self-localization to navigate in unknownenvironments. They can use Visual Odometry (VO) to estimate self-motion andlocalize themselves using visual sensors. This motion-estimation strategy isnot compromised by drift as inertial sensors or slippage as wheel encoders.However, VO with conventional cameras is computationally demanding, limitingits application in systems with strict low-latency, -memory, and -energyrequirements. Using event-based cameras and neuromorphic computing hardwareoffers a promising low-power solution to the VO problem. However, conventionalalgorithms for VO are not readily convertible to neuromorphic hardware. In thiswork, we present a VO algorithm built entirely of neuronal building blockssuitable for neuromorphic implementation. The building blocks are groups ofneurons representing vectors in the computational framework of Vector SymbolicArchitecture (VSA) which was proposed as an abstraction layer to programneuromorphic hardware. The VO network we propose generates and stores a workingmemory of the presented visual environment. It updates this working memorywhile at the same time estimating the changing location and orientation of thecamera. We demonstrate how VSA can be leveraged as a computing paradigm forneuromorphic robotics. Moreover, our results represent an important steptowards using neuromorphic computing hardware for fast and power-efficient VOand the related task of simultaneous localization and mapping (SLAM). Wevalidate this approach experimentally in a simple robotic task and with anevent-based dataset, demonstrating state-of-the-art performance in thesesettings.

Neuromorphic Visual Odometry with Resonator Networks