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

2026-03-08

AI Summary

This work addresses the challenge of inaccurate localization in both biological dogs and quadruped robots when relying solely on inertial sensors, where cumulative drift severely degrades performance. To mitigate this issue, the paper proposes three Dog Dead Reckoning (DDR) algorithms that, for the first time, integrate neural-augmented techniques into this domain by combining model-driven approaches with lightweight neural networks. Leveraging real-world data collected via the authors’ custom wearable device, DogMotion, the proposed methods achieve absolute distance errors below 10% on datasets from both biological dogs and quadruped robots, significantly outperforming purely model-based baselines and effectively suppressing error accumulation. The study delivers a low-cost, high-accuracy inertial localization solution, with code and data publicly released to support reproducibility and further research.

Technology Category

• Intelligent Robots: State Estimation
• Computer Vision: Motion & Tracking
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• dog dead reckoning
• inertial sensing
• positioning
• cumulative drift
• legged robots

Innovation

• dog dead reckoning
• neural-aided positioning
• inertial sensing
• legged robots
• wearable sensor