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/

Zendy Plus

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

Zendy Tools

Zendy Open

This paper presents Navion, an energy-efficient accelerator forvisual-inertial odometry (VIO) that enables autonomous navigation ofminiaturized robots (e.g., nano drones), and virtual/augmented reality onportable devices. The chip uses inertial measurements and mono/stereo images toestimate the drone's trajectory and a 3D map of the environment. This estimateis obtained by running a state-of-the-art VIO algorithm based on non-linearfactor graph optimization, which requires large irregularly structured memoriesand heterogeneous computation flow. To reduce the energy consumption andfootprint, the entire VIO system is fully integrated on chip to eliminatecostly off-chip processing and storage. This work uses compression and exploitsboth structured and unstructured sparsity to reduce on-chip memory size by4.1$\times$. Parallelism is used under tight area constraints to increasethroughput by 43%. The chip is fabricated in 65nm CMOS, and can process752$\times$480 stereo images from EuRoC dataset in real-time at 20 frames persecond (fps) consuming only an average power of 2mW. At its peak performance,Navion can process stereo images at up to 171 fps and inertial measurements atup to 52 kHz, while consuming an average of 24mW. The chip is configurable tomaximize accuracy, throughput and energy-efficiency trade-offs and to adapt todifferent environments. To the best of our knowledge, this is the first fullyintegrated VIO system in an ASIC.

Navion: A 2mW Fully Integrated Real-Time Visual-Inertial Odometry Accelerator for Autonomous Navigation of Nano Drones