Probabilistic occlusion estimation in cluttered environments for active perception planning

Abstract

Abstract-This paper presents a probabilistic framework for scene modeling and active perception planning in complex environments. It tackles the problems of representing detection and transition uncertainties in multi-object scenes without knowledge of the total number of objects in the scenario. The correct association of observation data with scene information is essential for reasonable incorporation of sequencing measurements into the scene model. This work also deals with the probabilistic computation of object occlusions for probabilistic action planning in order to select the most profitable prospective viewpoint. Concepts from computer graphics and statistics are combined for the efficient and precise estimation of future observations.In an experimental setting this active perception system, integrated into an autonomous service robot, is evaluated in a kitchen scenario.

Active perception and scene modeling by planning with probabilistic 6D object poses

“…Feature characteristics and occlusion events are considered to determine the visibility of features. In [12] the methodology of occlusion calculation is detailed. Given the set of (expected) visible features and in consideration of the measurement uncertainty we formulate the likelihood of seeing the feature f (a t ) as P (f (a t )|q ).…”

“…The prospective action policy π is determined by maximizing the expected reward (12) which relates benefits and costs of future actions a t with the relation factor α. The first term states the expected benefit of applying the control action, the second term expresses the respective costs with r a (b ) denoting the action efforts.…”