Related papers: Probing Physics Knowledge Using Tools from Develop…

We develop data-driven methods for incorporating physical information for priors to learn parsimonious representations of nonlinear systems arising from parameterized PDEs and mechanics. Our approach is based on Variational Autoencoders…

The ability to recognize objects despite there being differences in appearance, known as Core Object Recognition, forms a critical part of human perception. While it is understood that the brain accomplishes Core Object Recognition through…

The deployment of reinforcement learning (RL)-based controllers on physical systems is often limited by poor generalization to real-world scenarios, known as the simulation-to-reality (sim-to-real) gap. This gap is particularly challenging…

Acquiring the mathematical, conceptual, and problem-solving skills required in university-level physics courses is hard work, and the average student often lacks the knowledge and study skills they need to succeed in the introductory…

When we humans look at a video of human-object interaction, we can not only infer what is happening but we can even extract actionable information and imitate those interactions. On the other hand, current recognition or geometric…

Foundation models are premised on the idea that sequence prediction can uncover deeper domain understanding, much like how Kepler's predictions of planetary motion later led to the discovery of Newtonian mechanics. However, evaluating…

Many model-based Visual Odometry (VO) algorithms have been proposed in the past decade, often restricted to the type of camera optics, or the underlying motion manifold observed. We envision robots to be able to learn and perform these…

Solving partial differential equations (PDEs) is a required step in the simulation of natural and engineering systems. The associated computational costs significantly increase when exploring various scenarios, such as changes in initial or…

Visual object tracking (VOT) is an essential component for many applications, such as autonomous driving or assistive robotics. However, recent works tend to develop accurate systems based on more computationally expensive feature…

Understanding physical phenomena is a key competence that enables humans and animals to act and interact under uncertain perception in previously unseen environments containing novel object and their configurations. Developmental psychology…

Physics-informed deep operator networks (DeepONets) have emerged as a promising approach toward numerically approximating the solution of partial differential equations (PDEs). In this work, we aim to develop further understanding of what…

Effective inclusion of physics-based knowledge into deep neural network models of dynamical systems can greatly improve data efficiency and generalization. Such a-priori knowledge might arise from physical principles (e.g., conservation…

Recent advancements in deep learning, computer vision, and embodied AI have given rise to synthetic causal reasoning video datasets. These datasets facilitate the development of AI algorithms that can reason about physical interactions…

Physical agents that can autonomously generate engaging, life-like behaviour will lead to more responsive and interesting robots and other autonomous systems. Although many advances have been made for one-to-one interactions in well…

These lectures deal with the problem of inductive inference, that is, the problem of reasoning under conditions of incomplete information. Is there a general method for handling uncertainty? Or, at least, are there rules that could in…

Self-supervised goal-conditioned reinforcement learning enables robots to autonomously acquire diverse skills without human supervision. However, a central challenge is the goal setting problem: robots must propose feasible and diverse…

Gradient-based meta-learning methods have primarily been applied to classical machine learning tasks such as image classification. Recently, PDE-solving deep learning methods, such as neural operators, are starting to make an important…

Physics-informed deep learning has been developed as a novel paradigm for learning physical dynamics recently. While general physics-informed deep learning methods have shown early promise in learning fluid dynamics, they are difficult to…

We propose a new technique for pushing an unknown object from an initial configuration to a goal configuration with stability constraints. The proposed method leverages recent progress in differentiable physics models to learn unknown…

One of the first tasks we learn as children is to grasp objects based on our tactile perception. Incorporating such skill in robots will enable multiple applications, such as increasing flexibility in industrial processes or providing…