2020/10/02 by Riccardo Bertolucci, Alessio Capitanelli, Bertolucci, Riccardo +11 · 1 citation
Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Formal Methods in Verification #Logic in Computer Science (cs.LO) #Logic, Reasoning, and Knowledge #Multi-Agent Systems and Negotiation #Robotics (cs.RO)
paper · pdf · doi:10.48550/arxiv.2010.01164
openalex publication_date 2020/10/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
The manipulation of articulated objects is of primary importance in Robotics,\nand can be considered as one of the most complex manipulation tasks.\nTraditionally, this problem has been tackled by developing ad-hoc approaches,\nwhich lack flexibility and portability.\n In this paper we present a framework based on Answer Set Programming (ASP)\nfor the automated manipulation of articulated objects in a robot control\narchitecture. In particular, ASP is employed for representing the configuration\nof the articulated object, for checking the consistency of such representation\nin the knowledge base, and for generating the sequence of manipulation actions.\n The framework is exemplified and validated on the Baxter dual-arm manipulator\nin a first, simple scenario. Then, we extend such scenario to improve the\noverall setup accuracy, and to introduce a few constraints in robot actions\nexecution to enforce their feasibility. The extended scenario entails a high\nnumber of possible actions that can be fruitfully combined together. Therefore,\nwe exploit macro actions from automated planning in order to provide more\neffective plans. We validate the overall framework in the extended scenario,\nthereby confirming the applicability of ASP also in more realistic Robotics\nsettings, and showing the usefulness of macro actions for the robot-based\nmanipulation of articulated objects. Under consideration in Theory and Practice\nof Logic Programming (TPLP).\n