2020/11/13 by Riccardo Bertolucci, Bertolucci, Riccardo, Alessio Capitanelli +7
Computer Science · Engineering · #AI-based Problem Solving and Planning #FOS: Computer and information sciences #Robot Manipulation and Learning #Robotic Path Planning Algorithms #Robotics (cs.RO) #Semantic Web and Ontologies
paper · pdf · doi:10.48550/arxiv.2011.06865
openalex publication_date 2020/11/13 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
This paper addresses two intertwined needs for collaborative robots operating\nin shop-floor environments. The first is the ability to perform complex\nmanipulation operations, such as those on articulated or even flexible objects,\nin a way robust to a high degree of variability in the actions possibly carried\nout by human operators during collaborative tasks. The second is encoding in\nsuch operations a basic knowledge about physical laws (e.g., gravity), and\ntheir effects on the models used by the robot to plan its actions, to generate\nmore robust plans. We adopt the manipulation in three-dimensional space of\narticulated objects as an effective use case to ground both needs, and we use a\nvariant of the Planning Domain Definition Language to integrate the planning\nprocess with a notion of gravity. Different complexity levels in modelling\ngravity are evaluated, which trade-off model faithfulness and performance. A\nthorough validation of the framework is done in simulation using a dual-arm\nBaxter manipulator.\n