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

Rapid, accurate and robust detection of looming objects in cluttered movingbackgrounds is a significant and challenging problem for robotic visual systemsto perform collision detection and avoidance tasks. Inspired by the neuralcircuit of elementary motion vision in the mammalian retina, this paperproposes a bioinspired approach-sensitive neural network (ASNN) that containsthree main contributions. Firstly, a direction-selective visual processingmodule is built based on the spatiotemporal energy framework, which canestimate motion direction accurately via only two mutually perpendicularspatiotemporal filtering channels. Secondly, a novel approach-sensitive neuralnetwork is modeled as a push-pull structure formed by ON and OFF pathways,which responds strongly to approaching motion while insensitivity to lateralmotion. Finally, a method of directionally selective inhibition is introduced,which is able to suppress the translational backgrounds effectively. Extensivesynthetic and real robotic experiments show that the proposed model is able tonot only detect collision accurately and robustly in cluttered and dynamicbackgrounds but also extract more collision information like position anddirection, for guiding rapid decision making.

A Bioinspired Approach-Sensitive Neural Network for Collision Detection in Cluttered and Dynamic Backgrounds