A holistic understanding of object properties across diverse sensory
mod...
Despite advances in Reinforcement Learning, many sequential decision mak...
Humans learn about objects via interaction and using multiple perception...
Learning to detect, characterize and accommodate novelties is a challeng...
Generalisation to unseen contexts remains a challenge for embodied navig...
Humans leverage multiple sensor modalities when interacting with objects...
We propose RAPid-Learn: Learning to Recover and Plan Again, a hybrid pla...
Creative Problem Solving (CPS) is a sub-area within Artificial Intellige...
Despite recent advances in Reinforcement Learning (RL), many problems,
e...
Interactive reinforcement learning, where humans actively assist during ...
The Artificial Intelligence (AI) for Human-Robot Interaction (HRI) Sympo...
Predicting future sensory states is crucial for learning agents such as
...
Robots frequently need to perceive object attributes, such as "red," "he...
Symbolic planning models allow decision-making agents to sequence action...
Establishing common ground between an intelligent robot and a human requ...
Due to the COVID-19 pandemic, conducting Human-Robot Interaction (HRI)
s...
The Artificial Intelligence (AI) for Human-Robot Interaction (HRI) Sympo...
Reinforcement learning (RL) is a popular paradigm for addressing sequent...
The past few years have seen rapid progress in the development of servic...
Natural language understanding for robotics can require substantial doma...
Efforts are underway at UT Austin to build autonomous robot systems that...