Now showing items 211-219 of 219
Analysis of Situated Interactive Non-Expert Instruction of A Hierarchical Task to a Learning Robot
(2023)
Interactive Task Learning (ITL) is an approach to designing robots that can learn tasks on the fly from human instruction and demonstration in a shared environment. ITL approaches until now have focused on extending a ...
Implicit Design Choices and Their Impact on Emotion Recognition Model Development and Evaluation
(2023)
Emotion recognition is a complex task due to the inherent subjectivity in both the perception and production of emotions. The subjectivity of emotions poses significant challenges in developing accurate and robust computational ...
Terrain-Aware Bipedal Locomotion
(2023)
Bipedal robots provide a path forward for autonomous systems to operate seamlessly in human-designed environments. They can traverse terrains compatible with wheeled robots and provide improved access to shelves and cabinets ...
Overcoming Barriers to Information Exchange on the Web
(2023)
We are increasingly relying on the internet and specifically the world wide web (WWW) to exchange information and access services.
Despite its ubiquitous use, there are two key barriers to accessing information
that is ...
On Improving Robustness of Deep Neural Networks for Computer Vision
(2023)
Over the past decade, deep learning has spearheaded a revolution in a myriad of applications, achieving remarkable success. This is particularly evident in the field of computer vision, which has undergone a transformative ...
Novel Imaging Systems Using Nanophotonic Devices
(2021)
Novel technologies and innovations lead to new applications. This dissertation demonstrates new applications enabled by novel nanophotonic devices. I will describe two nanophotonic devices: hyperbolic metamaterial and ...
Provably Efficient Reinforcement Learning: From Single-Agent MDPs to Markov Games
(2021)
Reinforcement Learning (RL) has achieved tremendous empirical successes in real-world decision-making problems. Along with its great empirical achievements, recently, the question of how to design efficient RL algorithms ...
Efficient Deep Learning Accelerator Architectures by Model Compression and Data Orchestration
(2022)
Deep neural networks (DNNs) have become the primary methods to solve machine learning and artificial intelligence problems in the fields of computer vision, natural language processing, and robotics. The advancements in ...
Data-Efficient Robotic Manipulation of Deformable One-dimensional Objects with Unreliable Dynamics
(2023)
If I were to ask you to fold a towel, you would probably do it without much thought or difficulty -- but how? How did you know where the towel was? Did you think about how the towel would move or deform, and how you'd react ...