Related papers: Learning Physical Intuition of Block Towers by Exa…

Intuitive observations show that a baby may inherently possess the capability of recognizing a new visual concept (e.g., chair, dog) by learning from only very few positive instances taught by parent(s) or others, and this recognition…

Can we learn the physics of matter in motion directly from images and video--and trust it? Answering this question requires integrating experiments, physics-based simulation, and data across traditionally separate disciplines. Much of this…

We present a novel approach to interactive 3D object perception for robots. Unlike previous perception algorithms that rely on known object models or a large amount of annotated training data, we propose a poking-based approach that…

This paper proposes a method to design protective foam for packaging 3D objects. Users first load a 3D object and define a block-based design space by setting the block resolution and the size of each block. The system then constructs a…

Learning physically structured representations of dynamical systems that include contact between different objects is an important problem for learning-based approaches in robotics. Black-box neural networks can learn to approximately…

Neural network modules conditioned by known priors can be effectively trained and combined to represent systems with nonlinear dynamics. This work explores a novel formulation for data-efficient learning of deep control-oriented nonlinear…

Reprogrammable mechanical metamaterials, composed of a lattice of discretely adaptive elements, are emerging as a promising platform for mechanical intelligence. To operate in unknown environments, such structures must go beyond passive…

Modeling complex physical dynamics is a fundamental task in science and engineering. Traditional physics-based models are sample efficient, and interpretable but often rely on rigid assumptions. Furthermore, direct numerical approximation…

Much of the remarkable progress in computer vision has been focused around fully supervised learning mechanisms relying on highly curated datasets for a variety of tasks. In contrast, humans often learn about their world with little to no…

A robot's ability to provide descriptions of its decisions and beliefs promotes effective collaboration with humans. Providing such transparency is particularly challenging in integrated robot systems that include knowledge-based reasoning…

Humans have the remarkable ability to use held objects as tools to interact with their environment. For this to occur, humans internally estimate how hand movements affect the object's movement. We wish to endow robots with this capability.…

Early in development, infants learn to extract surprisingly complex aspects of visual scenes. This early learning comes together with an initial understanding of the extracted concepts, such as their implications, causality, and using them…

Humans expertly navigate the world by building rich internal models founded on an intuitive understanding of physics. Meanwhile, despite training on vast quantities of internet video data, state-of-the-art deep learning models still fall…

Given a point cloud, we consider inferring kinematic models of 3D articulated objects such as boxes for the purpose of manipulating them. While previous work has shown how to extract a planar kinematic model (often represented as a linear…

Learning predictive models from interaction with the world allows an agent, such as a robot, to learn about how the world works, and then use this learned model to plan coordinated sequences of actions to bring about desired outcomes.…

We propose a novel Transformer-based architecture for the task of generative modelling of 3D human motion. Previous work commonly relies on RNN-based models considering shorter forecast horizons reaching a stationary and often implausible…

Our goal is to provide a review of deep learning methods which provide insight into structured high-dimensional data. Rather than using shallow additive architectures common to most statistical models, deep learning uses layers of…

Inspired by the necessity of morphological adaptation in animals, a growing body of work has attempted to expand robot training to encompass physical aspects of a robot's design. However, reinforcement learning methods capable of optimizing…

Adaptive control for real-time manipulation requires quick estimation and prediction of object properties. While robot learning in this area primarily focuses on using vision, many tasks cannot rely on vision due to object occlusion. Here,…

Emotions are very important for human intelligence. For example, emotions are closely related to the appraisal of the internal bodily state and external stimuli. This helps us to respond quickly to the environment. Another important…