Manipulation of Articulated Objects Using Dual-arm Robots via Answer Set Programming

Abstract

The manipulation of articulated objects is of primary importance in Robotics and can be considered as one of the most complex manipulation tasks. Traditionally, this problem has been tackled by developing ad hoc approaches, which lack flexibility and portability. In this paper, we present a framework based on answer set programming (ASP) for the automated manipulation of articulated objects in a robot control architecture. In particular, ASP is employed for representing the configuration of the articulated object for checking the consistency of such representation in the knowledge base and for generating the sequence of manipulation actions. The framework is exemplified and validated on the Baxter dual-arm manipulator in the first, simple scenario. Then, we extend such scenario to improve the overall setup accuracy and to introduce a few constraints in robot actions execution to enforce their feasibility. The extended scenario entails a high number of possible actions that can be fruitfully combined together. Therefore, we exploit macro actions from automated planning in order to provide more effective plans. We validate the overall framework in the extended scenario, thereby confirming the applicability of ASP also in more realistic Robotics settings and showing the usefulness of macro actions for the robot-based manipulation of articulated objects.

Logic programming for deliberative robotic task planning

“…Several other implementations of ASP have been proposed by Tu et al (2007), where an Answer Set-based Conditional Planner (ASCP) is presented with applications also to robotic examples; Chen et al (2013), where ASP is implemented on the OK-KeJia service robot prototype for planning and decision-making based on multiple sources of information in the context of human-robot interaction; Baral and Son (2015), proving the advantages of using ASP for task planning and failure analysis and explanation in human-robot interaction; Ji (2009) for the domestic service scenario; Sridharan et al (2019), combining ASP with Markov decision processes in a domestic scenario; Bertolucci et al (2021) for dual arm manipulation; Falkner et al (2018) propose a review of recent applications of ASP to industry, while Erdem and Patoglu (2018) survey recent applications in various robotic fields. Finally, we mention recently growing interest in ASP applications to the scheduling problem, either in transportation/routing (Gebser et al 2018;Abels et al 2019) or space assignment (Dodaro et al 2021(Dodaro et al , 2022 scenarios.…”

CNL2ASP: Converting Controlled Natural Language Sentences into ASP

“…The manipulation of articulated objects is an important task in real-world robot scenarios. Bertolucci et al (2021) presented an ASP framework for handling the manipulation of an articulated object in a 2D workspace with the possibility of performing actions like rotating one of its link with respect to another one around their joint. The framework was composed by five modules, namely Knowledge Base, Goal Checker, Consistency Checking, Action Planner, and Motion Planner.…”

“…All the modules but Motion Planner were implemented using ASP. In this section, we focus on the Action Planner as described by the encoding reported in the Figure 6 of the paper by Bertolucci et al (2021), since it involves a number of interesting constructs, such as temporal concepts as well as the concept of angle.…”

“…Comparison of the performances. The encoding generated by the CNL specifications described before has been compared to the original one proposed by Bertolucci et al (2021), referred to as Original. In particular, we considered all the instances with 12 and 14 joints, with granularity equal to 180 and 90, and we set the number of maximum steps equal to 10.…”

Task Allocation for Multi-Robot Task and Motion Planning: a case for Object Picking in Cluttered Workspaces

“…As a result, one would need observation based re-planning within the PDDL framework, which require additional mapping between the PDDL action space and the observation space of the robot [2]. A cluttered table-top scenario in the context of single-robot TMP is considered in [17,36].…”