Multi-scale assembly with robot teams

Abstract

We present algorithms and experiments for multi-scale assembly of complex structures by multi-robot teams. We focus on tasks where successful completion requires multiple types of assembly operations with a range of precision requirements. We develop a hierarchical planning approach to multi-scale perception in support of multi-scale manipulation, in which the resolution of the perception operation is * Corresponding author; e-mail: mdogar@csail.mit.edu 1 The first three authors contributed equally to this paper. This paper is a revision of Dogar et al. (2014) matched with the required resolution for the manipulation operation. We demonstrate these techniques in the context of a multi-step task where robots assemble large box-like objects, inspired by the assembly of an airplane wing. The robots begin by transporting a wing panel, a coarse manipulation operation that requires a wide field of view, and gradually shift to narrower field of view but more accurate sensors for part alignment and fastener insertion. Within this framework we also provide for failure detection and recovery: upon losing track of a feature, the robots retract to using wider field of view systems to re-localize. Finally, we contribute collaborative manipulation algorithms for assembling complex large objects. First, the team of robots coordinates to transport large assembly parts which are too 2 heavy for a single robot to carry. Second, the fasteners and parts are co-localized for robust insertion and fastening. We implement these ideas using four KUKA youBot robots and present experiments where our robots successfully complete all 80 of the attempted fastener insertion operations.

A review of collective robotic construction

“…In contrast, natural systems operate without global sensing and comparatively little or no direct communication. The loose coupling between animals allows efficient parallel and scalable construction, as well as robustness to individual failures (34). Similarly, to benefit from many agents, CRC algorithms typically try to maximize concurrency while minimizing individual agent reliance on global information.…”

“…Often, construction algorithms assume a "seed," a starting point in the environment, that allows robots to compute a shared coordinate system (14,45). Other researchers model assembly of discrete elements in a continuous space (22,34,41,45), i.e., where depositions are not constrained in a lattice. In practical automation systems, e.g., (47), this representation is common because it corresponds to the space in which sensing and control of rigid elements take place.…”

Improving Robot Success Detection using Static Object Data

“…We define success in terms of two object relationships: in and on, and we assume oracle-level grasping and localization during action execution. c) Egocentric Vision: Existing work detects action outcomes using extrinsic camera viewpoints [21]. However, as robots move from research labs to homes, static cameras become impractical and intrusive.…”

Realization of heavy object transportation by mobile robots using handcarts and outrigger

“…Liu et al presented the transportation system with a gripper robot and a lifter robot [6]. Doger et al realized assembling of large boxlike objects by using a kind of hierarchical planning [7]. These studies deal with transport by coordinated grasping.…”