[HTML][HTML] Robot skill learning in latent space of a deep autoencoder neural network
Just like humans, robots can improve their performance by practicing, ie by performing the
desired behavior many times and updating the underlying skill representation using the …
desired behavior many times and updating the underlying skill representation using the …
A probabilistic model of gaze imitation and shared attention
An important component of language acquisition and cognitive learning is gaze imitation.
Infants as young as one year of age can follow the gaze of an adult to determine the object …
Infants as young as one year of age can follow the gaze of an adult to determine the object …
A cognitive framework for imitation learning
In order to have a robotic system able to effectively learn by imitation, and not merely
reproduce the movements of a human teacher, the system should have the capabilities of …
reproduce the movements of a human teacher, the system should have the capabilities of …
Learning two-person interaction models for responsive synthetic humanoids
Imitation learning is a promising approach for generating life-like behaviors of virtual
humans and humanoid robots. So far, however, imitation learning has been mostly restricted …
humans and humanoid robots. So far, however, imitation learning has been mostly restricted …
Towards robot cultures?: Learning to imitate in a robotic arm test-bed with dissimilarly embodied agents
The study of imitation and other mechanisms of social learning is an exciting area of
research for all those interested in understanding the origin and the nature of animal …
research for all those interested in understanding the origin and the nature of animal …
User feedback in latent space robotic skill learning
In order to operate in everyday human environment, humanoids robots will need to
autonomously learn and adapt their actions, using among other reinforcement learning …
autonomously learn and adapt their actions, using among other reinforcement learning …
Imitation learning and anchoring through conceptual spaces
In order to have a robotic system able to effectively learn by imitation and not merely
reproduce the movements of a human teacher, the system should have the capability to …
reproduce the movements of a human teacher, the system should have the capability to …
On building a person: benchmarks for robotic personhood
J Barresi - Journal of Experimental & Theoretical Artificial …, 2020 - Taylor & Francis
ABSTRACT I present criteria or benchmarks of personhood that robotic agents must pass for
them to match us in social intelligence and indicate some current successes and difficulties …
them to match us in social intelligence and indicate some current successes and difficulties …
Learning high-level tasks through imitation
This paper presents the cognitive architecture Con-SCIS (conceptual space based cognitive
imitation system), which tightly links low-level data processing with knowledge …
imitation system), which tightly links low-level data processing with knowledge …
Anchoring by imitation learning in conceptual spaces
In order to have a robotic system able to effectively learn by imitation, and not merely
reproduce the movements of a human teacher, the system should have the capabilities of …
reproduce the movements of a human teacher, the system should have the capabilities of …