Search Results for author:
Found 19 papers, 8 papers with code
Dialogue Policies for Learning Board Games through Multimodal Communication
During policy training, we control for the simulated dialogue partner’s level of informativeness in responding to questions.
Interactive Continual Learning Architecture for Long-Term Personalization of Home Service Robots
Our results demonstrate the effectiveness of our architecture to allow a physical robot to continually adapt to the changes in the environment from limited data provided by the users (experimenters), and use the learned knowledge to perform object fetching tasks.
CBCL-PR: A Cognitively Inspired Model for Class-Incremental Learning in Robotics
For most real-world applications, robots need to adapt and learn continually with limited data in their environments.
Active Class Selection for Few-Shot Class-Incremental Learning
We term this model Few-shot Incremental Active class SeleCtiOn (FIASco).
How Do Human Users Teach a Continual Learning Robot in Repeated Interactions?
Continual learning (CL) has emerged as an important avenue of research in recent years, at the intersection of Machine Learning (ML) and Human-Robot Interaction (HRI), to allow robots to continually learn in their environments over long-term interactions with humans.
A Personalized Household Assistive Robot that Learns and Creates New Breakfast Options through Human-Robot Interaction
In this paper, we present a cognitive architecture for a household assistive robot that can learn personalized breakfast options from its users and then use the learned knowledge to set up a table for breakfast.
Continual Learning through Human-Robot Interaction -- Human Perceptions of a Continual Learning Robot in Repeated Interactions
Our results suggest that participants' perceptions of trust, competence, and usability of a continual learning robot significantly decrease over multiple sessions if the robot forgets previously learned objects.
Few-Shot Continual Active Learning by a Robot
The results show that our approach not only produces state-of-the-art results on the dataset but also allows a real robot to continually learn unseen objects in a real environment with limited labeling supervision provided by its user.
Don't Forget to Buy Milk: Contextually Aware Grocery Reminder Household Robot
The robot can also use the learned knowledge to correctly predict missing items over multiple weeks and it is robust against sensory and perceptual errors.
F-SIOL-310: A Robotic Dataset and Benchmark for Few-Shot Incremental Object Learning
To fill this gap, we present a new dataset termed F-SIOL-310 (Few-Shot Incremental Object Learning) which is specifically captured for testing few-shot incremental object learning capability for robotic vision.
Learning Novel Objects Continually Through Curiosity
Children learn continually by asking questions about the concepts they are most curious about.
Continual Learning of Visual Concepts for Robots through Limited Supervision
For many real-world robotics applications, robots need to continually adapt and learn new concepts.
EEC: Learning to Encode and Regenerate Images for Continual Learning
The two main impediments to continual learning are catastrophic forgetting and memory limitations on the storage of data.
What am I allowed to do here?: Online Learning of Context-Specific Norms by Pepper
The paper utilizes a recent state-of-the-art approach for incremental learning and adapts it for online learning of scenes (contexts).
Tell me what this is: Few-Shot Incremental Object Learning by a Robot
For many applications, robots will need to be incrementally trained to recognize the specific objects needed for an application.
Storing Encoded Episodes as Concepts for Continual Learning
The two main challenges faced by continual learning approaches are catastrophic forgetting and memory limitations on the storage of data.
Cognitively-Inspired Model for Incremental Learning Using a Few Examples
To solve this problem, we propose a novel approach inspired by the concept learning model of the hippocampus and the neocortex that represents each image class as centroids and does not suffer from catastrophic forgetting.
Teach Me What You Want to Play: Learning Variants of Connect Four through Human-Robot Interaction
The paper demonstrates a method for teaching a robot the win conditions of the game Connect Four and its variants using a single demonstration and a few trial examples with a question and answer session led by the robot.
Centroid Based Concept Learning for RGB-D Indoor Scene Classification
Inspection of the centroids generated by our approach on RGB-D datasets leads us to propose a method for merging conceptually similar categories, resulting in improved accuracy for all approaches.
