GadenTools: A Toolkit for Testing and Simulating Robotic Olfaction Tasks With Jupyter Notebook Support Pepe Ojeda 1 , Jose-Raul Ruiz-Sarmiento 1 , Javier Monroy 1 and Javier Gonzalez-Jimenez 1 Machine Perception and Intelligent Robotics Group (MAPIR-UMA). Malaga Institute for Mechatronics Engineering & Cyber-Physical Systems (IMECH.UMA). University of Malaga. SPAIN Abstract. This work presents GadenTools, a toolkit designed to ease the development and integration of mobile robotic olfaction applications by enabling a convenient and user-friendly access to Gaden’s realistic gas dispersion simulations. It is based on an easy-to-use Python API, and includes an extensive tutorial developed with Jupyter Notebook and Google Colab technologies. A detailed set of examples illustrates aspects ranging from basic access to sensory data or the generation of ground- truth images, to the more advanced implementation of plume tracking algorithms, all in an online web-editor with no installation requirements. All the resources, including the source code, are made available in an online open repository. Keywords: Robotic Olfaction, Gas Dispersion Simulation, Python, Jupyter Notebook, Google Colaborative 1 Introduction Mobile robot olfaction (MRO ) is the field concerned with the integration and application of the sense of smell into mobile robots. It is a widely multidis- ciplinary research area, involving problems such as chemical sensing and clas- sification [4,15], dispersion modeling [5,7], optimal sampling [8] or gas source localization [10,17], among others. There are many potential applications for autonomous, mobile robotic agents with the ability to sense the presence of gases in an environment, e.g. locating leaks in pipes, detecting dangerous substances, rescue missions, air quality moni- toring, etc. As a result of these interesting prospects, the field of robotic olfaction has steadily been gaining attention over the years, and is expected to continue to do so as the available technology improves. A key hurdle, preventing much research from reaching the degree of matu- rity necessary for real-world deployment, is the lack of proper datasets and tools in the field that can be used to conduct ground truth evaluations. Works deal- ing with these concepts are crucial, and highly popular in other fields such as