Search Results for author:
Found 11 papers, 5 papers with code
Extending 3D body pose estimation for robotic-assistive therapies of autistic children
In real-world settings, the proposed model performs similarly to a Kinect depth camera and manages to successfully estimate the 3D body poses in a much higher number of frames.
Gaussian Mixture Models for Affordance Learning using Bayesian Networks
Affordances are fundamental descriptors of relationships between actions, objects and effects.
Robotic Learning the Sequence of Packing Irregular Objects from Human Demonstrations
The human demonstrations were collected using our proposed VR platform, BoxED, which is a box packaging environment for simulating real-world objects and scenarios for fast and streamlined data collection with the purpose of teaching robots.
Action-conditioned Benchmarking of Robotic Video Prediction Models: a Comparative Study
In contrast, we argue that if these systems are to be used to guide action, necessarily, the actions the robot performs should be encoded in the predicted frames.
Action Anticipation for Collaborative Environments: The Impact of Contextual Information and Uncertainty-Based Prediction
We propose to use the uncertainty about each prediction as an online decision-making criterion for action anticipation.
Cleaning tasks knowledge transfer between heterogeneous robots: a deep learning approach
In this paper, a robot is taught to perform two different cleaning tasks over a table, using a learning from demonstration paradigm.
Applying Domain Randomization to Synthetic Data for Object Category Detection
Recent advances in deep learning-based object detection techniques have revolutionized their applicability in several fields.
Automatic generation of object shapes with desired functionalities
3D objects (artefacts) are made to fulfill functions.
Learning at the Ends: From Hand to Tool Affordances in Humanoid Robots
One of the open challenges in designing robots that operate successfully in the unpredictable human environment is how to make them able to predict what actions they can perform on objects, and what their effects will be, i. e., the ability to perceive object affordances.
Anticipation in Human-Robot Cooperation: A Recurrent Neural Network Approach for Multiple Action Sequences Prediction
Recent approaches based on neural networks have led to encouraging results in the human action prediction problem both in continuous and discrete spaces.
Language Bootstrapping: Learning Word Meanings From Perception-Action Association
The model is based on an affordance network, i. e., a mapping between robot actions, robot perceptions, and the perceived effects of these actions upon objects.
