Related papers: Interactive Learning of State Representation throu…
Broadly intelligent agents should form task-specific abstractions that selectively expose the essential elements of a task, while abstracting away the complexity of the raw sensorimotor space. In this work, we present Neuro-Symbolic…
Whereas machine learning models typically learn language by directly training on language tasks (e.g., next-word prediction), language emerges in human children as a byproduct of solving non-language tasks (e.g., acquiring food). Motivated…
We introduce a simple new method for visual imitation learning, which allows a novel robot manipulation task to be learned from a single human demonstration, without requiring any prior knowledge of the object being interacted with. Our…
Robots can learn from humans by asking questions. In these questions the robot demonstrates a few different behaviors and asks the human for their favorite. But how should robots choose which questions to ask? Today's robots optimize for…
We consider the problem of building a state representation model in a continual fashion. As the environment changes, the aim is to efficiently compress the sensory state's information without losing past knowledge. The learned features are…
Recent robot learning methods commonly rely on imitation learning from massive robotic dataset collected with teleoperation. When facing a new task, such methods generally require collecting a set of new teleoperation data and finetuning…
For a robot to be called socially intelligent, it must be able to infer users internal states from their current behaviour, predict the users future behaviour, and if required, respond appropriately. In this work, we investigate how robots…
We aim to enable robot to learn object manipulation by imitation. Given external observations of demonstrations on object manipulations, we believe that two underlying problems to address in learning by imitation is 1) segment a given…
Humans use semantic concepts such as spatial relations between objects to describe scenes and communicate tasks such as "Put the tea to the right of the cup" or "Move the plate between the fork and the spoon." Just as children, assistive…
An outstanding challenge for the widespread deployment of robotic systems like autonomous vehicles is ensuring safe interaction with humans without sacrificing performance. Existing safety methods often neglect the robot's ability to learn…
A central problem in artificial intelligence is that of planning to maximize future reward under uncertainty in a partially observable environment. In this paper we propose and demonstrate a novel algorithm which accurately learns a model…
In order for robots to autonomously navigate and operate in diverse environments, it is essential for them to recognize the state of their environment. On the other hand, the environmental state recognition has traditionally involved…
As robot systems become more ubiquitous, developing understandable robot systems becomes increasingly important in order to build trust. In this paper, we present an approach to developing a holistic robot explanation system, which consists…
Human-to-human conversation is not just talking and listening. It is an incremental process where participants continually establish a common understanding to rule out misunderstandings. Current language understanding methods for…
The named concepts and compositional operators present in natural language provide a rich source of information about the kinds of abstractions humans use to navigate the world. Can this linguistic background knowledge improve the…
While the basic laws of Newtonian mechanics are well understood, explaining a physical scenario still requires manually modeling the problem with suitable equations and associated parameters. In order to adopt such models for artificial…
Explanations constitute an important aspect of successful human robot interactions and can enhance robot understanding. To improve the understanding of the robot, we have developed four levels of explanation (LOE) based on two questions:…
Continual learning refers to the ability of a biological or artificial system to seamlessly learn from continuous streams of information while preventing catastrophic forgetting, i.e., a condition in which new incoming information strongly…
When robots perform long action sequences, users will want to easily and reliably find out what they have done. We therefore demonstrate the task of learning to summarize and answer questions about a robot agent's past actions using natural…
Safe human-robot interactions require robots to be able to learn how to behave appropriately in \sout{humans' world} \rev{spaces populated by people} and thus to cope with the challenges posed by our dynamic and unstructured environment,…