Mapping with sparse local sensors and strong hierarchical priors

摘要: The paradigm case for robotic mapping assumes large quantities of sensory information which allow the use relatively weak priors. In contrast, present study considers problem in environments where only sparse, local is available. To compensate these likelihoods, we make strong hierarchical object Hierarchical models were popular classical blackboard systems but are here applied a Bayesian setting and novelly deployed as algorithm. We give proof concept results, intended to demonstrate algorithm's applicability part tactile SLAM module whiskered SCRATCHbot mobile robot platform.