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

Collision detection is one of the most challenging tasks for Unmanned AerialVehicles (UAVs). This is especially true for small or micro UAVs, due to theirlimited computational power. In nature, flying insects with compact and simplevisual systems demonstrate their remarkable ability to navigate and avoidcollision in complex environments. A good example of this is provided bylocusts. They can avoid collisions in a dense swarm through the activity of amotion based visual neuron called the Lobula Giant Movement Detector (LGMD).The defining feature of the LGMD neuron is its preference for looming. As aflying insect's visual neuron, LGMD is considered to be an ideal basis forbuilding UAV's collision detecting system. However, existing LGMD models cannotdistinguish looming clearly from other visual cues such as complex backgroundmovements caused by UAV agile flights. To address this issue, we proposed a newmodel implementing distributed spatial-temporal synaptic interactions, which isinspired by recent findings in locusts' synaptic morphology. We firstintroduced the locally distributed excitation to enhance the excitation causedby visual motion with preferred velocities. Then radially extending temporallatency for inhibition is incorporated to compete with the distributedexcitation and selectively suppress the non-preferred visual motions.Systematic experiments have been conducted to verify the performance of theproposed model for UAV agile flights. The results have demonstrated that thisnew model enhances the looming selectivity in complex flying scenesconsiderably, and has potential to be implemented on embedded collisiondetection systems for small or micro UAVs.

Enhancing LGMD's Looming Selectivity for UAV with Spatial-temporal Distributed Presynaptic Connections