TO
1 - 25 of 8
| Creator | Title | Description | Subject | Date | ||
|---|---|---|---|---|---|---|
| 1 |
 |
Van der Merwe, Mark | Learning 3D Reconstructions for Geometrically aware Robotic Grasping | Robotic grasping is a crucial subtask of many important robotic applications, such as in-home robotic assistance, emergency responce robots, and industrial robotics. Deep learning has enabled remarkable improvements in robotic grasp synthesis for previously unseen objects from partial object views. ... | 2020 | |
| 2 |
 |
Bull, Auguest John | Robotic Grasp Control Using Tactile Feedback | As we move towards more autonomous robots, object interaction and manipulation remains difficult for robots. Grasping approaches vary from learning-based to traditional control means, each with their own challenges. Learning-based methods perform well on specific tasks, but struggle to move to other... | 2020 | |
| 3 |
 |
Taylor, Andree Nicholas Crawford | Latent space planning for multi-object manipulation with enviornment-aware relational classifiers | A useful robot operating in human environments will no doubt encounter scenes where it needs to manage and manipulate multiple objects. The interactions of these objects with each other and the environment are important to reason about in order to predict the outcome of any action. We aim to learn a... | 2024 | |
| 4 |
 |
Robe, John William | The Design and Implementation of Autonomous Robotic Systems | This research focuses on the development of an autonomous robotic system using Robot Operating System (ROS), with the purpose of competing in the NASA Robotic Mining Competition in collaboration with the Utah Robotic Mining Project team. While completing this research, the following discoveries were... | 2017 | |
| 5 |
 |
Zubair, Jonathan | Design and Implementation of a Shrouded Rotor for Uncreasing Quadrotor Performance | Quadrotors have come to serve myriad purposes and have seen use as platforms for diverse activities including videography and remote sensing. These versatile aircraft, however, cannot remain in flight for extended periods of time. This is due to several factors including the aerodynamic regime in wh... | 2017 | |
| 6 |
 |
Kapetanovic, Stefan | Non-Anthropomorhic Deep Learning: Developing the "Eyes for the Internet of Things" | Deep Learning (DL) and Convolutional Neural Networks (CNNs) have been established as a powerful class of models for image recognition problems. Encouraged by this, we implemented a system that can accurately predict handwritten numbers from a raw CMOS machine image. Current forms of deep learning do... | 2017 | |
| 7 |
 |
Freckleton, K. Beau | Sarrus-based passive mechanism for rotorcraft perchings: Structural design and mass optimization | Current quad-rotors provide excellent maneuverability and opportunity for data collection in large scale areas such as agriculture, but lack the capability to maintain flight for an extended period of time. This is primarily due to a lack of energy supply, requiring operators to replace the battery ... | Drone aircraft; Drone aircraft -- Control systems; Sarrus | 2014-12 |
| 8 |
 |
Bracken, Kallie | Defining learning: mystifying machine learning as a powerful tool in a data-driven world | Until recently, the driving paradigm in software engineering has been to design applications for a predefined set of tasks. This approach, however, is quickly being dwarfed by data-driven applications which are designed to use knowledge and understanding to decide how they can best fulfill use... | Machine learning - Case studies; Machine learning - Study and Teaching; Machine Learning - Technique | 2016-04 |
1 - 25 of 8