Model-Based and Neural-Aided Approaches for Dog Dead Reckoning
This work provides a lightweight and low-cost positioning solution for biological and robotic dogs, which is crucial for applications like medical monitoring, service roles, industrial inspection, and disaster response.
The authors propose three algorithms for dog dead reckoning (DDR) using only inertial sensors to address cumulative drift in canine and robotic dog positioning. Their neural-aided methods achieved an absolute distance error of less than 10% across 13 minutes of biological dog data and 116 minutes of robotic dog data, outperforming model-based approaches.
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.