Pre-Grasp Approaching on Mobile Robots: A Pre-Active Layered Approach

In Mobile Manipulation (MM), navigation and ma- nipulation are generally solved as subsequent disjoint tasks. Com- bined optimization of navigation and manipulation costs can im- prove the time efficiency of MM. However, this is challenging as precise object pose estimates, which are necessary for such com- bined optimization, are often not available until the later stages of MM. Moreover, optimizing navigation and manipulation costs with conventional planning methods using uncertain object pose esti- mates can lead to failures and hence requires re-planning. Hence, in the presence of object pose uncertainty, pre-active approaches are preferred. We propose such a pre-active approach for determining the base pose and pre-grasp manipulator configuration to improve the time efficiency of MM. We devise a Reinforcement Learning (RL) based solution that learns suitable base poses for grasping and pre-grasp manipulator configurations using layered learning that guides exploration and enables sample-efficient learning. Further, we accelerate learning of pre-grasp manipulator configurations by providing dense rewards using a predictor network trained on previously learned base poses for grasping. Our experiments validate that in the presence of uncertain object pose estimates, the proposed approach results in reduced execution time. Finally, we show that our policy learned in simulation can be easily transferred to a real robot.