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

We present fully autonomous source seeking onboard a highly constrained nanoquadcopter, by contributing application-specific system and observation featuredesign to enable inference of a deep-RL policy onboard a nano quadcopter. Ourdeep-RL algorithm finds a high-performance solution to a challenging problem,even in presence of high noise levels and generalizes across real andsimulation environments with different obstacle configurations. We verify ourapproach with simulation and in-field testing on a Bitcraze CrazyFlie usingonly the cheap and ubiquitous Cortex-M4 microcontroller unit. The results showthat by end-to-end application-specific system design, our contributionconsumes almost three times less additional power, as compared to competinglearning-based navigation approach onboard a nano quadcopter. Thanks to ourobservation space, which we carefully design within the resource constraints,our solution achieves a 94% success rate in cluttered and randomized testenvironments, as compared to the previously achieved 80%. We also compare ourstrategy to a simple finite state machine (FSM), geared towards efficientexploration, and demonstrate that our policy is more robust and resilient atobstacle avoidance as well as up to 70% more efficient in source seeking. Tothis end, we contribute a cheap and lightweight end-to-end tiny robot learning(tinyRL) solution, running onboard a nano quadcopter, that proves to be robustand efficient in a challenging task using limited sensory input.

Learning to Seek: Autonomous Source Seeking with Deep Reinforcement Learning Onboard a Nano Drone Microcontroller