Model-Based and Neural-Aided Approaches for Dog Dead Reckoning

TL;DR

This paper introduces three inertial sensor-based algorithms for accurate dog positioning, demonstrating that neural-aided methods outperform model-based ones with less than 10% error, applicable to biological and robotic dogs.

Contribution

The paper presents a novel neural-aided approach for dog dead reckoning, improving accuracy over traditional model-based methods using new datasets and open-source code.

Findings

Neural-aided methods outperform model-based approaches in accuracy.

Achieved less than 10% absolute distance error.

Developed a wearable data recording device for canines.

Abstract

Modern canine applications span medical and service roles, while robotic legged dogs serve as autonomous platforms for high-risk industrial inspection, disaster response, and search and rescue operations. For both, accurate positioning remains a significant challenge due to the cumulative drift inherent in inertial sensing. To bridge this gap, we propose three algorithms for accurate positioning using only inertial sensors, collectively referred to as dog dead reckoning (DDR). To evaluate our approaches, we designed DogMotion, a wearable unit for canine data recording. Using DogMotion, we recorded a dataset of 13 minutes. Additionally, we utilized a robotic legged dog dataset with a duration of 116 minutes. Across the two distinct datasets we demonstrate that our neural-aided methods consistently outperform model-based approaches, achieving an absolute distance error of less than 10\%. Consequently, we provide a lightweight and low-cost positioning solution for both biological and legged robotic dogs. To support reproducibility, our codebase and associated datasets have been made publicly available.