Data-Driven Measurement Models for Active Localization in Sparse Environments
This work addresses localization challenges for robots in sparse environments, such as tactile sensing, but is incremental as it builds on existing exploration and localization methods.
The paper tackles the problem of active localization in sparse environments by developing a two-stage algorithm that first constructs a data-driven measurement model through ergodic exploration and then uses it for localization, demonstrating in simulations and robot experiments that it can identify and localize objects based on sparse binary contacts.
We develop an algorithm to explore an environment to generate a measurement model for use in future localization tasks. Ergodic exploration with respect to the likelihood of a particular class of measurement (e.g., a contact detection measurement in tactile sensing) enables construction of the measurement model. Exploration with respect to the information density based on the data-driven measurement model enables localization. We test the two-stage approach in simulations of tactile sensing, illustrating that the algorithm is capable of identifying and localizing objects based on sparsely distributed binary contacts. Comparisons with our method show that visiting low probability regions lead to acquisition of new information rather than increasing the likelihood of known information. Experiments with the Sphero SPRK robot validate the efficacy of this method for collision-based estimation and localization of the environment.