A Multi-Level Optimization Framework for Simultaneous Grasping and Motion Planning
Simon Zimmermann, Ghazal Hakimifard, Miguel Zamora, Roi Poranne, Stelian Coros
Abstract
We present an optimization framework for grasp and motion planning in the context of robotic assembly. Typically, grasping locations are provided by higher level planners or as input parameters. In contrast, our mathematical model simultaneously optimizes motion trajectories, grasping locations, and other parameters such as the pose of an object during handover operations. The input to our framework consists of a set of objects placed in a known configuration, their target locations, and relative timing information describing when objects need to be picked up, optionally handed over, and dropped off. To allow robots to reason about the way in which grasping locations govern optimal motions, we formulate the problem using a multi-level optimization scheme: the top level optimizes grasping locations; the mid-layer level computes the configurations of the robot for pick, drop and handover states; and the bottom level computes optimal, collision-free motions. We leverage sensitivity analysis to compute derivatives analytically (how do grasping parameters affect IK solutions, and how these, in turn, affect motion trajectories etc.), and devise an efficient numerical solver to generate solutions to the resulting optimization problem. We demonstrate the efficacy of our approach on a variety of assembly and handover tasks performed by a dual-armed robot with parallel grippers.