Samuel Gossett

Project

Portfolio

Welcome!

Explore my Projects and Experiences!

Welcome to my portfolio! I'm Samuel Gossett, and this is where I will be showcasing a diverse range of projects in Software, Hardware, and Embedded Systems. This portfolio serves as a platform to showcase my expertise and experiences in robotics and other similar fields. Feel free to explore my projects and learn more about my skills and capabilities. Keep scrolling to see my current study topics and what I am interested in.

Oh... I'm also a big-time rower!!

Interests:

Industry Interests:
- Optimal Control
- Motion Planning
- Optimal Control
- Embedded Systems
- SLAM
- Machine Learning
- Learning-Based Control/Planning
- Med-tech

Recreational Interests:
- Rowing (Rowed at Clemson, Head of the Charles)
- Basketball (Big NBA fan)
- College Football (Clemson fan obv)
- Weightlifting
- Videogames (Valorant and CIV especially)
- Hanging with Friends

This Semester:
Introduction to Robotics
Topics to be covered include modeling techniques (kinematics and dynamics) for a variety of robotic systems, ranging from manipulator arms and car-like vehicles to soft robots, an introduction to control and motion planning for such systems, and concepts of sensing and perception. The course will also discuss the basics of machine learning techniques in robotics.

What I'm Working on Now:

This Semester:
Robot Motion Planning
Provides an overview of state-of-the-art techniques for robot motion planning. The emphasis is on the algorithms. It covers topology of configuration spaces, potential functions, roadmaps, cell decompositions, sampling-based algorithms, and model checking approaches to robot motion planning and control.

This Semester:
Robot Learning
This class will discuss recent developments in machine learning and perception for robotics. Specifically, we will study advanced concepts in perception and decision-making algorithms in order to provide theoretical and experimental frameworks for robot learning. Topics will include 3D vision, sensorimotor paradigms for perception and action, robot reinforcement learning, imitation learning, inverse reinforcement learning, exploration, options, model-based approaches, POMDP and human-machine and social interaction.

This Semester:
Cyber-Physical Systems
This course introduces students to the principles underlying the design and analysis of cyber-physical systems - computational systems that interact with the physical world. We will study a wide range of applications of such systems ranging from robotics, through medical devices, to smart manufacturing plants. A strong emphasis will be put on building high-assurance systems with real-time and concurrent behaviors. The student will gain both in-depth knowledge and hands-on experience on the specification, modeling, design, and analysis of representative cyber-physical systems.

Next Semester:
Embedded System Design
This course introduces students to a unified view of hardware and software in embedded systems. The lectures will survey a comprehensive array of techniques including system specification languages, embedded computer architecture, real-time operating systems, hardware-software codesign, and co-verification techniques. The lectures will be complemented by assignments and projects that involve system design, analysis, optimization, and verification.

What I'm Working on Next:

Next Semester:
Deep Learning
Feed-forward networks., Backpropagation. Training strategies for deep networks. Convolutional networks. Recurrent neural networks. Deep reinforcement learning. Deep unsupervised learning. Exposure to Pytorch and other modern programming tools.

Next Semester:
Optimal Control/Dynamic Programming
The principle of optimality as a unified approach to optimal control of dynamic systems and Markovian decision problems. Applications from control theory and operations research include linear-quadratic problems, the discrete Kalman Filter, inventory control, network, investment, and resource allocation models. Adaptive control and numerical solutions through successive approximation and policy iteration, suboptimal control, and neural network applications involving functional approximations and learning.

Next Semester:
Medical Robotics
This course will be composed of lectures, tutorials, and group work. We will study the design, mechanics, materials, manufacturing, and control of robots and associated technologies for medical applications. We will cover theory, on medical robotics and case studies, including examples from medical companies and research groups.This class is aimed toward graduate students in engineering; no medical background is required. We will study and explore design principles of different mechatronic components and systems for medical robots. We will cover in-depth especially the meso-scale actuators, sensors, and body construction methods.