Task-oriented planning for manipulating articulated mechanisms under model uncertainty

Abstract

Abstract-Personal robots need to manipulate a variety of articulated mechanisms as part of day-to-day tasks. These tasks are often specific, goal-driven, and permit very little bootstrap time for learning the articulation type. In this work, we address the problem of purposefully manipulating an articulated object, with uncertainty in the type of articulation. To this end, we provide two primary contributions: first, an efficient planning algorithm that, given a set of candidate articulation models, is able to correctly identify the underlying model and simultaneously complete a task; and second, a representation for articulated objects called the Generalized Kinematic Graph (GK-Graph), that allows for modeling complex mechanisms whose articulation varies as a function of the state space. Finally, we provide a practical method to auto-generate candidate articulation models from RGB-D data and present extensive results on the PR2 robot to demonstrate the utility of our representation and the efficiency of our planner.

FlowBot3D: Learning 3D Articulation Flow to Manipulate Articulated Objects

“…Several works have focused specifically on visual recognition and estimation of articulation parameters, learning to predict the pose [31,30,26,11,15] and identify articulation parameters [13,32] to obtain action trajectories. Moreover, [21,4,6] tackle the problem using statistical motion planning.…”

V-MAO: Generative Modeling for Multi-Arm Manipulation of Articulated Objects

“…Kumar et al [18] propose to estimate mass distribution of an articulated objects through manipulation. Narayanan et al [19] introduced kinematic graph representation and an efficient planning algorithm for object articulation manipulation. More recently, Mittal et al [20] constructed a mobile manipulation platform that integrates articulation perception and planning.…”