Bayesian Optimisation for Safe Navigation under Localisation Uncertainty
This addresses safety issues for mobile robots in uncertain environments, representing an incremental improvement over standard Bayesian optimisation methods.
The paper tackles the problem of mobile robot navigation in outdoor terrain where localisation uncertainty can lead to unsafe paths and distorted traversability models, and presents a novel Bayesian optimisation method that incorporates localisation uncertainty using a Gaussian process model for uncertain inputs, achieving improved safety in simulations and real robot experiments.
In outdoor environments, mobile robots are required to navigate through terrain with varying characteristics, some of which might significantly affect the integrity of the platform. Ideally, the robot should be able to identify areas that are safe for navigation based on its own percepts about the environment while avoiding damage to itself. Bayesian optimisation (BO) has been successfully applied to the task of learning a model of terrain traversability while guiding the robot through more traversable areas. An issue, however, is that localisation uncertainty can end up guiding the robot to unsafe areas and distort the model being learnt. In this paper, we address this problem and present a novel method that allows BO to consider localisation uncertainty by applying a Gaussian process model for uncertain inputs as a prior. We evaluate the proposed method in simulation and in experiments with a real robot navigating over rough terrain and compare it against standard BO methods.