Student Talks
NeRF for Robotics
Abstract: In this talk I'll describe how recent advances in neural rendering and novel view synthesis - namely NeRF - can be leveraged by robotic agents to improve performance in manipulation tasks. Specifically, I'll argue that NeRF can enable robotic policies to: (1) generalize to new viewpoints; (2) perceive specular and reflective surfaces in a [...]
Carnegie Mellon University
Search Algorithms and Search Spaces for Neural Architecture Search
Abstract: Neural architecture search (NAS) is recently proposed to automate the process of designing network architectures. Instead of manually designing network architectures, NAS automatically finds the optimal architecture in a data-driven way. Despite its impressive progress, NAS is still far from being widely adopted as a common paradigm for architecture design in practice. This thesis [...]
Carnegie Mellon University
MSR Thesis Talk – Evan Harber
Title: Stiffness Mapping of Deformable Objects Through Supervised Embedding and Gaussian Process Regression Abstract: The stiffness map of a deformable object stores information about that object's surface compliance. Thus, through a stiffness map, we gain insight into the physical properties of that object. Depending on the object, an understanding of stiffness has applications ranging [...]
MSR Thesis Talk – Gaurav Parmar
Title: Spatially-Adaptive Multilayer GAN Inversion Abstract: Existing GAN inversion and editing methods are well suited for only a target images that contain aligned objects with a clean background, such as portraits and animal faces, but often struggle for more difficult categories with complex scene layouts and object occlusions, such as cars, animals, and outdoor images. [...]
Robust Reinforcement Learning via Genetic Curriculum
Abstract: Achieving robust performance is crucial when applying deep reinforcement learning (RL) in safety critical systems. Some of the state of the art approaches try to address the problem with adversarial agents, but these agents often require expert supervision to fine tune and prevent the adversary from becoming too challenging to the trainee agent. While [...]
Mouth Haptics in VR using a Headset Ultrasound Phased Array
Abstract: This talk is the same one I will be presenting at the ACM CHI Conference on Human Factors in Computing Systems on May 2nd. Paper abstract: Today’s consumer virtual reality (VR) systems offer limited haptic feedback via vibration motors in handheld controllers. Rendering haptics to other parts of the body is an open challenge, [...]
Towards Large-scale and Long-term Neural Map Representations
Abstract: We address the problem of large-scale and long-term neural map representations. Maps, as our prior understanding toward the environment, provide valuable information for modern robotics applications such as autonomous driving and AR/VR. The size of maps largely affects the end task performance: usually a more detailed map can support better performance, but would cost [...]
Carnegie Mellon University
Self-Improving 3D Scene Representations
Abstract: Most computer vision models in deployment today are not continually learning. Instead, they are in a “test” mode, where they will behave the same way perpetually, until they are replaced by newer models. This is a problem, because it means the models may perform poorly as soon as their “test” environment diverges from their [...]
Carnegie Mellon University
MSR Thesis Talk – Manash Pratim Das
Title: Model-Accuracy Aware Anytime Planning with Simulation Verification for Navigating Complex Terrains Abstract: Off-road and unstructured environments often contain complex patches of various types of terrain, rough elevation changes, deformable objects, etc. An autonomous ground vehicle traversing such environments experiences physical interactions that are extremely hard to model at scale and thus very hard to [...]
Carnegie Mellon University
MSR Thesis Talk – Akshay Dharamavaram
Title: Stabilizing the Training Dynamics of Generative Models using Self-Supervision Abstract: Generative Models have been shown to be adept in mimicking the behavior of an unknown distribution solely from bootstrapped data. However, deep learning models have been shown to overfit in either the minimization or maximization stage of the two player min-max game, resulting [...]