Declarative solutions for the the Manipulation of Articulated Objects Using Dual-Arm Robots

Abstract

The manipulation of exible object is of primary importance in industry 4.0 and in home environments scenarios. Traditionally, this problem has been tackled by developing ad-hoc approaches, that lack of exibility and portability. We propose an approach in which a

exible object is modelled as an articulated object, or rather, a set of links connect via joints. In this thesis we present a framework based on Answer Set Programming (ASP) for the automated manipulation of articulated objects in a robot architecture. In particular, ASP is employed for representing the con guration of the articulated object, for checking the consistency of the knowledge base, and for generating the sequence of manipulation actions. The framework is exempli ed and validated on the Baxter dual-arm manipulator on a simple reference scenario in which we carried out di erent experiments analysing the behaviours of di erent strategies for the action planning module. Our aim is to have an understanding of the performances of these approaches with respect to planning time and execution time as well. Then, we extend such scenario for having a higher accuracy of the setup, and to introduce a few constraints in robot actions execution to improve their feasibility. Given the extended scenario entails a high number of possible actions that can be fruitfully combined, we exploit macro actions from automated planning in the module that generates the sequence of actions, in order to deal with this extended scenario in a more e ective way. Moreover, we analyse the possibilities of mixed encodings with both simple actions and macro actions from automated planning in di erent "concentrations". We nally validate the framework also on this extended scenario, con rming the applicability of ASP also in this complex context, and showing the usefulness of macro actions in this robotics application.