PhD Speaking Qualifier
PhD Student
Robotics Institute,
Carnegie Mellon University

Continual Reinforcement Learning using Self-Activating Neural Ensembles

Abstract: The ability for an agent to continuously learn new skills without catastrophically forgetting existing knowledge is of critical importance for the development of generally intelligent agents. Most methods devised to address this problem depend heavily on well-defined task boundaries which simplify the problem considerably. Our task-agnostic method, Self-Activating Neural Ensembles (SANE), uses a hierarchical [...]

PhD Speaking Qualifier
Robotics Institute,
Carnegie Mellon University

Unsupervised 2D-3D Lifting with Deep Structure Priors

Abstract: Learning to estimate non-rigid 3D structures from 2D imaged observations is bottle-necked by the availability of abundant 3D annotated data. Learning methods that reduce the amount of required annotation is of high practical value. In this regard, Non-Rigid Structure from Motion (NRSfM) methods offer the opportunity to infer 3D structures solely from 2D annotations. [...]

PhD Speaking Qualifier
PhD Student
Robotics Institute,
Carnegie Mellon University

Model Adaptation for Compliant Parallel Robot with Nonstationary Dynamics

Abstract: Soft robots can be constructed with few parts and from a wide variety of materials. This makes them a potentially appealing choice for applications where there are resource constraints on system fabrication. However, soft robot dynamics are difficult to accurately model analytically, due to a multiphysics coupling between shape, forces, temperature, and history of [...]

PhD Speaking Qualifier
PhD Student
Robotics Institute,
Carnegie Mellon University

Adaptive Safety Margins for Safe Replanning 
under Time-Varying Disturbances

Abstract: Safe real-time navigation is a considerable challenge because engineers often need to work with uncertain vehicle dynamics, variable external disturbances, and imperfect controllers. A common strategy used to address safety is to employ hand-defined margins for obstacle inflation. However, arbitrary static margins often fail in more dynamic scenarios, and using worst-case assumptions proves to [...]

PhD Speaking Qualifier
PhD Student
Robotics Institute,
Carnegie Mellon University

HyperDynamics: Generating Expert Dynamics Models by Observation

Abstract: We propose HyperDynamics, a framework that conditions on an agent’s interactions with the environment and optionally its visual observations, and generates the parameters of neural dynamics models based on inferred properties of the dynamical system. Physical and visual properties of the environment that are not part of the low-dimensional state yet affect its temporal [...]

PhD Speaking Qualifier
PhD Student
Robotics Institute,
Carnegie Mellon University

Direct Fitting of Mixture Models

Abstract: There exist many choices of 3D shape representation. Some recent work has advocated for the use of Gaussian Mixture Models as a compact representation for 3D shapes and scenes. These models are typically fit to point clouds, even when the shapes were obtained as 3D meshes. Here we present a formulation for fitting Gaussian [...]

PhD Speaking Qualifier
Principal Research Programmer / Analyst
Robotics Institute,
Carnegie Mellon University

Terrain Perception using Structured Light for Micro-Rovers

Abstract: With continuing advancement in technology, the future of planetary exploration is likely to be dominated by robotic missions. Yet rovers capable of science investigations are slow and bulky with very limited computing which prohibits demonstrating full autonomy. These rovers are also risk averse due to their huge mission cost. However there is a new [...]

VASC Seminar
Ricardo Martin-Brualla
Researcher
Google

Photorealistic Reconstruction of Landmarks and People using Implicit Scene Representation

Abstract: Reconstructing scenes to synthesize novel views is a long standing problem in Computer Vision and Graphics. Recently, implicit scene representations have shown novel view synthesis results of unprecedented quality, like the ones of Neural Radiance Fields (NeRF), which use the weights of a multi-layer perceptron to model the volumetric density and color of a [...]

PhD Thesis Proposal
Robotics Institute,
Carnegie Mellon University

Bayesian Models for Science-Driven Robotic Exploration

Abstract: Planetary rovers have traversed many kilometers and made major scientific discoveries. However, they spend a considerable amount of time awaiting instructions from ground operators. The reason is that they are designed for automated science data collection, not for autonomous exploration. The exploration of more distant worlds with stronger communication constraints will require a new [...]