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

Building domain-specific accelerators for autonomous unmanned aerial vehicles(UAVs) is challenging due to a lack of systematic methodology for designingonboard compute. Balancing a computing system for a UAV requires consideringboth the cyber (e.g., sensor rate, compute performance) and physical (e.g.,payload weight) characteristics that affect overall performance. Iterating overthe many component choices results in a combinatorial explosion of the numberof possible combinations: from 10s of thousands to billions, depending onimplementation details. Manually selecting combinations of these components istedious and expensive. To navigate the {cyber-physical design space}efficiently, we introduce \emph{AutoPilot}, a framework that automatesfull-system UAV co-design. AutoPilot uses Bayesian optimization to navigate alarge design space and automatically select a combination of autonomy algorithmand hardware accelerator while considering the cross-product effect of othercyber and physical UAV components. We show that the AutoPilot methodologyconsistently outperforms general-purpose hardware selections like Xavier NX andJetson TX2, as well as dedicated hardware accelerators built for autonomousUAVs, across a range of representative scenarios (three different UAV types andthree deployment environments). Designs generated by AutoPilot increase thenumber of missions on average by up to 2.25x, 1.62x, and 1.43x for nano, micro,and mini-UAVs respectively over baselines. Our work demonstrates the need forholistic full-UAV co-design to achieve maximum overall UAV performance and theneed for automated flows to simplify the design process for autonomouscyber-physical systems.

AutoPilot: Automating SoC Design Space Exploration for SWaP Constrained Autonomous UAVs