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

Nano-sized drones, with palm-sized form factor, are gaining relevance in theInternet-of-Things ecosystem. Achieving a high degree of autonomy for complexmulti-objective missions (e.g., safe flight, exploration, object detection) isextremely challenging for the onboard chip-set due to tight size, payload(<10g), and power envelope constraints, which strictly limit both memory andcomputation. Our work addresses this complex problem by combining bio-inspirednavigation policies, which rely on time-of-flight distance sensor data, with avision-based convolutional neural network (CNN) for object detection. Ourfield-proven nano-drone is equipped with two microcontroller units (MCUs), asingle-core ARM Cortex-M4 (STM32) for safe navigation and exploration policies,and a parallel ultra-low power octa-core RISC-V (GAP8) for onboard CNNinference, with a power envelope of just 134mW, including image sensors andexternal memories. The object detection task achieves a mean average precisionof 50% (at 1.6 frame/s) on an in-field collected dataset. We compare fourbio-inspired exploration policies and identify a pseudo-random policy toachieve the highest coverage area of 83% in a ~36m^2 unknown room in a 3minutes flight. By combining the detection CNN and the exploration policy, weshow an average detection rate of 90% on six target objects in anever-seen-before environment.

Bio-inspired Autonomous Exploration Policies with CNN-based Object Detection on Nano-drones