Discover Ohara124c41/UPenn-GRASP_Lab-RoboticsCapstone-MIP Open Source

Contains my solutions for various Nanodegree Programs (Robotics, Artificial Intelligence, Machine Learning, Deep Reinforcement Learning, Computer Vision, Sensor Fusion, Flying Cars).

Udacity_Projects_Master_Repo

Hunter-UA-Drone

This project is provides specifications and strategies for the development of an autonomous hunter UAV. The task is to seek out other drones/UAVs and destroy them. An implementation is given using the Parrot Bebop 2 and the Jetson TX2 development kit.

Java

FCND-Drone-Building_an_Estimator

Scripted a state estimator for a quadrotor in C++, incorporating a sensor fusion (IMU, GPS, Magnetometer) environment using the EFK and MCL algorithms

Icahn Graduate School of Medicine: Systems Biology & Biotechnology Specialization

Systems-Biology-and-Biotechnology-Specialization

Solved the Inverse Kinematics problem for a six degree-of-freedom robotic arm (Kuka KR210) in a simulated environment to complete a pick-and-place operation. (implemented using ROS, Gazebo and RViz).

RoboND-Kinematics-Kuka-KR210

In this assignment, you will design a controller for a tele-manipulation task in eye surgery. For the design of your controller you can make use of the material provided in the lectures, including, but not limited to, passivity-based approaches and Haptic Shared Control.

Haptics-Bilateral_Teleoperation-1DOF_Experiments

FlexSat

Control Systems Design for Flexible Satellite with Star Tracker

CanSat Satellite Design Project at TU Berlin. The goal was to make a CanSat capable of downlinking telemetry data (from IMU, temperature, pressure, etc.) to a remote ground station. Upon landing, the satellite also works as an exploratory rover and must detach it's parachute and drive a minimum of 5m while still reporting sensor data.

CanSat

This project was used as the capstone project for Udacity's Machine Learning Nanodegree. Independent research was conducted and the findings were implemented for MIT's DeepTraffic Competition.

MLND-Capstone-DeepTraffic

JavaScript

SFND-RADAR-Target_Generation-n-Detection

Calibrate, threshold, and filter radar data to detect obstacles in real radar data. Analyze radar signatures to detect and track objects. Calculate velocity and orientation by correcting for radial velocity distortions, noise, and occlusions.

Implemented a motion planning algorithm to navigate through a simulated urban environment using a 2.5D map as a reference for obstacle positions, implementing A* and autonomous navigation

FCND-Drone-3D_Motion_Planning

Scripted a controller for a quadrotor in C++ implementing autonomous drone flight, fleets, and object tracking.

FCND-Drone-Building_a_Controller

Udacity Coursework for the AI Product Manager Nanodegree

AIPMND-AI_Product_Manager

HTML

AIBLND-Delivering_an_ML-AI_Strategy

Udacity's AI for Business Leaders Nanodegree Project - Delivering an ML/AI Strategy Course Capstone from beta-program (2020JAN).

Cybersecurity

VRND

Designed a modern apartment with high-performance lighting, custom materials, and animation using Unity.

DRLND-Collaborate-n-Competition

Learn how to apply reinforcement learning methods to applications that involve multiple, interacting agents. These techniques are used in a variety of applications, such as the coordination of autonomous vehicles.

Built a system that can recognize words communicated using the American Sign Language (ASL). Trained a set of Hidden Markov Models (HMMs) using part of a preprocessed dataset of tracked hand and nose positions extracted from video to try and identify individual words from test sequences. Experimented with model selection techniques including BIC, DIC, and K-fold Cross Validation.

AIND-ASL_Recognizer

Projects, lecture notes and information related to the Robotic's Specialization on Coursera via University of Pennsylvania

Robotics-Specialization

Transfer learning implementation from the Self-Driving Car Nanodegree

EIT-Digital_Real-Time-Operating-Systems

Course work for RTOS.

Udacity-Transfer_Learning

Created a DQN to solve OpenAI Gym's LunarLander environment.

LunarLander-DQN

Udacity Project Manager Nanodegree Coursework

PMND-Project_Management_Nanodegree

AIPM-Xray_Images-AutoML

AI for Product Managers Nanodegree Alpha/Beta - Classifying x-ray images from a dataset using AutoML

DRLND-Navigation

Value-based methods. Apply deep learning architectures to reinforcement learning tasks. Train your own agent that navigates a virtual world from sensory data.

Coursework projects, exercises and submissions for the User Interface Specialization

User-Interface-Design-Specialization

SDCND-Lane_Lines

Self-Driving Car project to detect lane lines in images using Python and OpenCV.

Policy-Based Methods. Learn the theory behind evolutionary algorithms and policy-gradient methods. Design your own algorithm to train a simulated robotic arm to reach target locations.

DRLND-Continuous_Control

Wrote the "Hello, world!" of drone programming with event-driven code that causes a quadrotor to take off, fly in a square, and land.

FCND-Drone-Backyard_Flyer

This project was for a course at TU/e called System Validation. The goal was to create an architecture with parallel components and use formal model checking to evaluate the model. The use case is a simplified EUV wafer stepper from ASML.

ASML-Wafer_Stepper

Languages

Japanese, Chinese Preparation for Language Proficiency Exams

RoboND-Autonomous_Search_Rover

Wrote a computer vision pipeline (using Python and OpenCV) to perform color thresholding, as well as perspective and coordinate transforms to complete the task of autonomous mapping and navigation in a simulated (Unity) environment.

Built dashboards using Tableau to analyze the occurrence of flight delays and cancellations in major airlines based on time, location and season.

DFND-Flight-Delays-and-Cancellations

HTML

RoboND-PR2-3D_Perception

Created a perception pipeline to perform object recognition, then successfully completed a tabletop pick and place operation using a PR2 robot in simulation.

Built a model to predict the value of a given house in the Boston real estate market using various statistical analysis tools. Identified the best price that a client can sell their house utilizing machine learning.

MLND-Predicting_Boston_Housing_Pricing

HTML

LABELEDBY.

Fast-Fashion utilizing Industry 4.0 techniques including 3D printing, laser cutting and machine learning

Advanced_Model-Based_Nonlinear_Control_Systems

Nonlinear control system applications and analysis.

First machine learning project for beta testing (Udacity MLND-T). The students will be utilizing n-grams and associations to detect plagiarized essay submissions.

MLNDT-Beta-Plagiarism_Detection

Used logic and planning techniques to create an AI that finds the most efficient route to route cargo around the world to their respective destinations. This project used a combination of propositional logic and search along with A* heuristics to find optimal planning solutions. Planning and scheduling systems power automation and logistics operations, and aerospace applications like the Hubble telescope and NASA Mars rovers.

AIND-Planning