Probabilistic Localization of Insect-Scale Drones on Floating-Gate Inverter Arrays

TL;DR

This paper introduces a low-power, hardware-efficient probabilistic localization framework for insect-scale drones using a novel compute-in-memory approach with a harmonic mean Gaussian mixture model, enabling accurate 3D localization with minimal energy.

Contribution

It presents a new HMGM model and CIM-based hardware implementation for efficient 3D map representation and drone localization, reducing power consumption and computational complexity.

Findings

Localization error of ~0.1125 m, close to software methods (~0.08 m)

Ultra-low power consumption of ~17 μW during operation

Fast processing time of 1.33 ms per depth frame

Abstract

We propose a novel compute-in-memory (CIM)-based ultra-low-power framework for probabilistic localization of insect-scale drones. The conventional probabilistic localization approaches rely on the three-dimensional (3D) Gaussian Mixture Model (GMM)-based representation of a 3D map. A GMM model with hundreds of mixture functions is typically needed to adequately learn and represent the intricacies of the map. Meanwhile, localization using complex GMM map models is computationally intensive. Since insect-scale drones operate under extremely limited area/power budget, continuous localization using GMM models entails much higher operating energy -- thereby, limiting flying duration and/or size of the drone due to a larger battery. Addressing the computational challenges of localization in an insect-scale drone using a CIM approach, we propose a novel framework of 3D map representation using a harmonic mean of "Gaussian-like" mixture (HMGM) model. The likelihood function useful for drone localization can be efficiently implemented by connecting many multi-input inverters in parallel, each programmed with the parameters of the 3D map model represented as HMGM. When the depth measurements are projected to the input of the implementation, the summed current of the inverters emulates the likelihood of the measurement. We have characterized our approach on an RGB-D indoor localization dataset. The average localization error in our approach is $\sim$0.1125 m which is only slightly degraded than software-based evaluation ($\sim$0.08 m). Meanwhile, our localization framework is ultra-low-power, consuming as little as $\sim$17 $\mu$W power while processing a depth frame in 1.33 ms over hundred pose hypotheses in the particle-filtering (PF) algorithm used to localize the drone.