1. Hierarchical learning of robotic contact policiesMihael Simonič, Aleš Ude, Bojan Nemec, 2023, original scientific article Abstract: The paper addresses the issue of learning tasks where a robot maintains permanent contact with the environment. We propose a new methodology based on a hierarchical learning scheme coupled with task representation through directed graphs. These graphs are constituted of nodes and branches that correspond to the states and robotic actions, respectively. The upper level of the hierarchy essentially operates as a decision-making algorithm. It leverages reinforcement learning (RL) techniques to facilitate optimal decision-making. The actions are generated by a constraint-space following (CSF) controller that autonomously identifies feasible directions for motion. The controller generates robot motion by adjusting its stiffness in the direction defined by the Frenet–Serret frame, which is aligned with the robot path. The proposed framework was experimentally verified through a series of challenging robotic tasks such as maze learning, door opening, learning to shift the manual car gear, and learning car license plate light assembly by disassembly.
Keywords: autonomous robot learning, learning, experience, compliance and impedance contro
Published in DiRROS: 21.09.2023; Views: 403; Downloads: 202
 Full text (1,73 MB)
This document has many files! More... |
2. Underwater measurements with UX robots; a new and available tool developed by UNEXUPNorbert Zajzon, Boglárka Anna Topa, Richárd Zoltán Papp, Jussi Aaltonen, José Miguel Almeida, Carlos Almeida, Alfredo Martins, Balázs Bodó, Stephen Henley, Márcio Tameirão Pinto, Gorazd Žibret, 2023, original scientific article Abstract: The UNEXMIN (Horizon 2020) and UNEXUP (EIT RawMaterials) projects developed a novel technology to send robots and even autonomously deliver optical images, 3D maps and other georeferenced scientific data from flooded underground environments, like abandoned mines, caves or wells. The concept turned into a market ready solution in seven years, where the last few years of field trials of the development beautifully demonstrating the technology's premier capabilities. Here in this paper, we focus on the wide variety of environments, circumstances and measurements where the UNEXMIN technology can be the best solution or the only solution to deliver certain research or engineering data. These are obtained from both simple and complex environments like different mines and caves, small and large cavities, long and tight tunnels and shafts, different visibility conditions, even different densities of the liquid medium where UX robots operated.
Keywords: autonomous robot, underwater measurements, UNEXUP project
Published in DiRROS: 07.09.2023; Views: 304; Downloads: 109
Full text (8,86 MB) |
