Our project aims to utilize instrumented dog toys to collect data on dog play behaviors. The current project implementation is a food-safe silicone over-molded tennis ball with an embedded sensor package at its center. The sensors collect motion data (via an inertial measurement unit) and pressure data (via a barometer) as dogs play with the ball.
By collecting data from play behaviors over time, we hope to develop machine learning models that can quantify dog temperament elements. These models, along with subjective and objective measurements from veterinarians, will improve the efficiency and quality of training programs for nosework and assistance dogs.
We explore the emerging area of Animal-Computer Interaction focusing on interfaces for inter-species communication and on the design and evaluation of interactive technology for users of multiple species.
