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

Aerial autonomous machines (Drones) has a plethora of promising applicationsand use cases. While the popularity of these autonomous machines continues togrow, there are many challenges, such as endurance and agility, that couldhinder the practical deployment of these machines. The closed-loop controlfrequency must be high to achieve high agility. However, given theresource-constrained nature of the aerial robot, achieving high control loopfrequency is hugely challenging and requires careful co-design of algorithm andonboard computer. Such an effort requires infrastructures that bridge variousdomains, namely robotics, machine learning, and system architecture design. Tothat end, we present AutoSoC, a framework for co-designing algorithms as wellas hardware accelerator systems for end-to-end learning-based aerial autonomousmachines. We demonstrate the efficacy of the framework by training an obstacleavoidance algorithm for aerial robots to navigate in a densely clutteredenvironment. For the best performing algorithm, our framework generates variousaccelerator design candidates with varying performance, area, and powerconsumption. The framework also runs the ASIC flow of place and route andgenerates a layout of the floor-planed accelerator, which can be used totape-out the final hardware chip.

AutoSoC: Automating Algorithm-SOC Co-design for Aerial Robots