Objective learning from human demonstrations
Researchers in biomechanics, neuroscience, human–machine interaction and other fields
are interested in inferring human intentions and objectives from observed actions. The …
are interested in inferring human intentions and objectives from observed actions. The …
Online object and task learning via human robot interaction
This work describes the development of a robotic system that acquires knowledge
incrementally through human interaction where new objects and motions are taught on the …
incrementally through human interaction where new objects and motions are taught on the …
Hand-object interaction pretraining from videos
We present an approach to learn general robot manipulation priors from 3D hand-object
interaction trajectories. We build a framework to use in-the-wild videos to generate …
interaction trajectories. We build a framework to use in-the-wild videos to generate …
Learning stable dynamical systems for visual servoing
A Paolillo, M Saveriano - 2022 International Conference on …, 2022 - ieeexplore.ieee.org
This work presents the dual benefit of integrating imitation learning techniques, based on the
dynamical systems formalism, with the visual servoing paradigm. On the one hand …
dynamical systems formalism, with the visual servoing paradigm. On the one hand …
A geometric perspective on visual imitation learning
We consider the problem of visual imitation learning without human kinesthetic teaching or
teleoperation, nor access to an interactive reinforcement learning training environment. We …
teleoperation, nor access to an interactive reinforcement learning training environment. We …
Deep adaptive multi-intention inverse reinforcement learning
This paper presents a deep Inverse Reinforcement Learning (IRL) framework that can learn
an a priori unknown number of nonlinear reward functions from unlabeled experts' …
an a priori unknown number of nonlinear reward functions from unlabeled experts' …
[HTML][HTML] Learning by Demonstration of a Robot Using One-Shot Learning and Cross-Validation Regression with Z-Score
J Duque-Domingo, M García-Gómez, E Zalama… - Electronics, 2024 - mdpi.com
We introduce a One-Shot Learning system where a robot effectively learns how to
manipulate objects by relying solely on the object's name, a single image, and a visual …
manipulate objects by relying solely on the object's name, a single image, and a visual …
Visual geometric skill inference by watching human demonstration
We study the problem of learning manipulation skills from human demonstration video by
inferring the association relationships between geometric features. Motivation for this work …
inferring the association relationships between geometric features. Motivation for this work …
Analyzing neural jacobian methods in applications of visual servoing and kinematic control
Designing adaptable control laws that can transfer between different robots is a challenge
because of kinematic and dynamic differences, as well as in scenarios where external …
because of kinematic and dynamic differences, as well as in scenarios where external …
Offline learning of counterfactual predictions for real-world robotic reinforcement learning
We consider real-world reinforcement learning (RL) of robotic manipulation tasks that
involve both visuomotor skills and contact-rich skills. We aim to train a policy that maps …
involve both visuomotor skills and contact-rich skills. We aim to train a policy that maps …