2023
Tiboni, Gabriele; Protopapa, Andrea; Tommasi, Tatiana; Averta, Giuseppe
Domain Randomization for Robust, Affordable and Effective Closed-loop Control of Soft Robots Miscellaneous
2023.
Links | BibTeX | Tags: Domain randomization, FOS: Computer and information sciences, Machine Learning (cs.LG), Robotics, Robotics (cs.RO)
@misc{tiboni2023dr_soro,
title = {Domain Randomization for Robust, Affordable and Effective Closed-loop Control of Soft Robots},
author = {Gabriele Tiboni and Andrea Protopapa and Tatiana Tommasi and Giuseppe Averta},
doi = {10.48550/ARXIV.2303.04136},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
publisher = {arXiv},
keywords = {Domain randomization, FOS: Computer and information sciences, Machine Learning (cs.LG), Robotics, Robotics (cs.RO)},
pubstate = {published},
tppubtype = {misc}
}
Tiboni, Gabriele; Camoriano, Raffaello; Tommasi, Tatiana
PaintNet: Unstructured Multi-Path Learning from 3D Point Clouds for Robotic Spray Painting Miscellaneous
2023.
BibTeX | Tags: Domain randomization, point clouds, Robot learning, Robotics
@misc{tiboni2023paintnet,
title = {PaintNet: Unstructured Multi-Path Learning from 3D Point Clouds for Robotic Spray Painting},
author = {Gabriele Tiboni and Raffaello Camoriano and Tatiana Tommasi},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
keywords = {Domain randomization, point clouds, Robot learning, Robotics},
pubstate = {published},
tppubtype = {misc}
}
2020
Duan, Anqing; Camoriano, Raffaello; Ferigo, Diego; Huang, Yanlong; Calandriello, Daniele; Rosasco, Lorenzo; Pucci, Daniele
Learning to Avoid Obstacles with Minimal Intervention Control Journal Article
In: Frontiers in Robotics and AI, vol. 7, 2020, ISSN: 2296-9144, (Publisher: Frontiers).
Abstract | Links | BibTeX | Tags: humanoid robots, minimal intervention control, obstacle avoidance, Programming by Demonstration, Robotics
@article{duan_learning_2020,
title = {Learning to Avoid Obstacles with Minimal Intervention Control},
author = {Anqing Duan and Raffaello Camoriano and Diego Ferigo and Yanlong Huang and Daniele Calandriello and Lorenzo Rosasco and Daniele Pucci},
url = {https://www.frontiersin.org/articles/10.3389/frobt.2020.00060/abstract},
doi = {10.3389/frobt.2020.00060},
issn = {2296-9144},
year = {2020},
date = {2020-01-01},
urldate = {2020-01-01},
journal = {Frontiers in Robotics and AI},
volume = {7},
abstract = {Programming by demonstration has received much attention as it offers a general framework which allows robots to efficiently acquire novel motor skills from a human teacher. While traditional imitation learning that only focuses on either Cartesian or joint space might become inappropriate in situations where both spaces are equally important (e.g. writing or striking task), hybrid imitation learning of skills in both Cartesian and joint spaces simultaneously has been studied recently. However, an important issue which often arises in dynamical or unstructured environments is overlooked, namely how can a robot avoid obstacles? In this paper, we aim to address the problem of avoiding obstacles in the context of hybrid imitation learning. Specifically, we propose to tackle three subproblems: (i) designing a proper potential field so as to bypass obstacles, (ii) guaranteeing joint limits are respected when adjusting trajectories in the process of avoiding obstacles, and (iii) determining proper control commands for robots such that potential human-robot interaction is safe. By solving the aforementioned subproblems, the robot is capable of generalizing observed skills to new situations featuring obstacles in a feasible and safe manner. The effectiveness of the proposed method is validated through a toy example as well as a real transportation experiment on the iCub humanoid robot.},
note = {Publisher: Frontiers},
keywords = {humanoid robots, minimal intervention control, obstacle avoidance, Programming by Demonstration, Robotics},
pubstate = {published},
tppubtype = {article}
}
Programming by demonstration has received much attention as it offers a general framework which allows robots to efficiently acquire novel motor skills from a human teacher. While traditional imitation learning that only focuses on either Cartesian or joint space might become inappropriate in situations where both spaces are equally important (e.g. writing or striking task), hybrid imitation learning of skills in both Cartesian and joint spaces simultaneously has been studied recently. However, an important issue which often arises in dynamical or unstructured environments is overlooked, namely how can a robot avoid obstacles? In this paper, we aim to address the problem of avoiding obstacles in the context of hybrid imitation learning. Specifically, we propose to tackle three subproblems: (i) designing a proper potential field so as to bypass obstacles, (ii) guaranteeing joint limits are respected when adjusting trajectories in the process of avoiding obstacles, and (iii) determining proper control commands for robots such that potential human-robot interaction is safe. By solving the aforementioned subproblems, the robot is capable of generalizing observed skills to new situations featuring obstacles in a feasible and safe manner. The effectiveness of the proposed method is validated through a toy example as well as a real transportation experiment on the iCub humanoid robot.