Newly accepted papers from our lab.
HOI4ABOT: Human-Object Interaction Anticipation for Human Intention Reading Collaborative roBOTs,
We propose an efficient and robust transformer-based model to detect and anticipate Human-Object Interactions from videos. This enhanced anticipation empowers robots to proactively assist humans, resulting in more efficient and intuitive collaborations. Our model outperforms state-of-the-art results in HOI detection and anticipation in VidHOI dataset with an increase of 1.76% and 1.04% in mAP respectively while being 15.4 times faster. We showcase the effectiveness of our approach through experimental results in a real robot, demonstrating that the robot’s ability to anticipate HOIs is key for better Human-Robot Interaction
Esteve Valls Mascaro, Daniel Sliwowski, and Dongheui Lee, HOI4ABOT: Human-Object Interaction Anticipation for Human Intention Reading Collaborative roBOTs, Conference on Robot Learning (CoRL), 2023. (Webpage, opens an external URL in a new window, Paper, opens an external URL in a new window)
© Daniel Sliwowski
HOI4ABOT paper overview image
A man approaches a kitchen isle with a robot. The robot proactively helps the man by pouring him a drink.
Unsupervised human-to-robot motion retargeting via expressive latent space
This paper introduces a novel approach for human-to-robot motion retargeting, enabling robots to mimic human motion with precision while preserving the semantics of the motion. For that, we propose a deep learning method for direct translation from human to robot motion. Our method does not require annotated paired human-to-robot motion data, which reduces the effort when adopting new robots
Yashuai Yan, Esteve Valls Mascaro and Dongheui Lee, Unsupervised human-to-robot motion retargeting via expressive latent space, IEEE International Conference on Humanoid Robots (HUMANOIDS), pp.-, 2023 (ArXiv, opens an external URL in a new window, Website, opens an external URL in a new window)
© @Esteve Valls Mascaro
Humanoids Overview
Overview of the paper ImitationNet: Unsupervised human-to-robot motion retargeting via shared latent space
Effects of Robotic Expertise and Task Knowledge on Physical Ergonomics and Joint Effciency in a Human-Robot Collaboration Task
Matteo Pantano, Arianna Curioni, Daniel Regulin, Tobias Kamps and Dongheui Lee, Effects of Robotic Expertise and Task Knowledge on Physical Ergonomics and Joint Effciency in a Human-Robot Collaboration Task, IEEE International Conference on Humanoid Robots (HUMANOIDS), pp.-, 2023
A Passivity-based Approach for Variable Stiffness Control with Dynamical Systems
Youssef Michel, Matteo Saveriano and Dongheui Lee, A Passivity-based Approach for Variable Stiffness Control with Dynamical Systems, IEEE Transactions on Automation Science and Engineering, pp. - , 2023
A Shared Control Approach Based on First-Order Dynamical Systems and Closed-Loop Variable Stiffness Control
Haotian Xue, Youssef Michel, and Dongheui Lee, A Shared Control Approach Based on First-Order Dynamical Systems and Closed-Loop Variable Stiffness Control, Journal of Intelligent and Robotic Systems, pp. - , 2023
A Learning Based Shared Control Approach For Contact Tasks
Youssef Michel, Zhendong Li, and Dongheui Lee, A Learning Based Shared Control Approach For Contact Tasks, IEEE Robotics and Automation Letters (RA-L), pp. - , 2023. DOI: 10.1109/LRA.2023.3322332
Strictly Positive Realness-Based Feedback Gain Design Under Imperfect Input-Output Feedback Linearization in Prioritized Control Problem
The prioritized control problem is a process to find a control strategy for a dynamical system with prioritized multiple outputs, so that it can operate outside its nonsingular domain. Singularity typically leads to imperfect inversion in the prioritized control problem, which in turn results in imperfect input-output feedback linearization. In this paper, we propose a method based on the Kalman-Yakubovich-Popov lemma that compensates nonlinear feedback terms caused by the imperfect inversion of the prioritized control problem. In order to realize this idea, we prove existence of a feedback gain matrix that gives a strictly positive real transfer function whose output matrix is identical to the feedback gain matrix. Our proof is constructive so that a set of such matrices can be found. Also, we provide a numerical approach that gives a larger set of feedback gain matrices and validate the result with numerical examples.
Sang-ik An, Gyunghoon Park, and Dongheui Lee, Strictly Positive Realness-Based Feedback Gain Design Under Imperfect Input-Output Feedback Linearization in Prioritized Control Problem, IEEE Conference on Decision and Control (CDC), 2023.
Unifying Skill-Based Programming and Programming by Demonstration through Ontologies
Thomas Eiband, Florian Lay, Korbinian Nottensteiner, Dongheui Lee, Unifying Skill-Based Programming and Programming by Demonstration through Ontologies, Procedia Computer Science, Volume 232, 2024, Pages 595-605
Overview image for the "Unifying Skill-Based Programming and Programming by Demonstration through Ontologies" paper.
Simplifying Robot Grasping in Manufacturing with a Teaching Approach based on a Novel User Grasp Metric
Matteo Pantano, Vladislav Klass, Qiaoyue Yang, Akhil Sathuluri, Daniel Regulin, Lucas Janisch, Markus Zimmermann, and Dongheui Lee, Simplifying Robot Grasping in Manufacturing with a Teaching Approach based on a Novel User Grasp Metric, 5th International Conference on Industry 4.0 and Smart Manufacturing, 2023