OASIS is an opti-acoustic fusion method that integrates data from optical images with voxel carving techniques to achieve real-time 3D reconstruction unstructured underwater workspaces. High resolution underwater 3D scene reconstruction is crucial for various applications, including construction, infrastructure maintenance, monitoring, exploration, and scientific investigation. Prior work has leveraged the complementary...
[Read More]
Shared Autonomy Framework (SHARC)
Enabling remote novice users to conduct deep-ocean science operations with robotic manipulators
Conventional underwater intervention operations using robotic vehicles require expert teleoperators and limit interaction with remote scientists. In this work, we introduce the shared autonomy for remote collaboration (SHARC) framework which enables novice operators to cooperatively conduct underwater sampling and manipulation tasks. With SHARC, operators can plan and complete manipulation tasks...
[Read More]
ROV-VR
Leveraging virtual reality to improve underwater robotic vehicle piloting for deep-sea scientific sampling
For my senior capstone project at Olin, I led the development of a control room display in virtual reality (VR) to help improve operation of underwater remotely operated vehicles (ROVs). Thanks to generous support from the Dassault Systèmes Foundation, we were able to work on this project in collaboration with...
[Read More]
Robo Fish
Creating a small robotic fish with a soft tail
This project was created as part of the open-ended final project in my Robotics Systems Integration course, which had a particular focus on designing robotics systems with soft actuators. Working with hardware during COVID proved to be challenging, especially with each of us working from a separate location. We were...
[Read More]
Discrete Landmark Navigation
A study in finding the optimal path within stochastic graphs
For our final project in our Discrete Math course, my project partners and I wanted to find ways to use what we had learned in discrete to solve common robotics problems. Earlier in the course, we had touched upon the theory behind popular algorithms like Dijkstra’s and Bellman-Ford for finding...
[Read More]
Robo Dodgeball
Using machine learning to train a robot to play dodgeball
This project was created as part of the open-ended final project in my Computational Robotics course - we were provided with a gazebo simulator that provided the low-level controls for a Neato robotic vacuum, and it was up to us to decide what to do with it. For this project,...
[Read More]
Image-based 3D reconstruction
Creating 3D pointclouds from 2D photos
For our open-ended computer vision project in my Computational Robotics course, my project partner and I wanted to work on a project related to localization. The idea of SLAM in unstructured environments was pretty interesting to us, particularly the step where the pose of the camera is estimated relative to...
[Read More]
Particle Filter
Implementing a particle filter for mobile robot localization
As one of the first few projects in my Computational Robotics course, my project group and I implemented a Particle Filter to help localize a robot based on lidar data (in layman’s terms - figured out where the robot is on a map based on sensor input). As one of...
[Read More]
Chlorophyll-a Comparison
Comparing chl-a measurements from satellites, robotic floats, and shipborne fluorometers in New Zealand
During my semester abroad with SEA, taking the class “Directed Oceanographic Research” gave me the opportunity to complete a research project and communicate my results in a technical write-up. One of my primary motivations when studying with SEA was to learn more about the role robots played in the ocean...
[Read More]
Manipulator Calibration
Developing a calibration method extensible to deep-sea manipulators
During my Summer Student Fellowship with WHOI, I researched computer vision-based calibration methods that would be extensible to deep-sea manipulators. Hydraulic manipulator arms are commonly used for a variety of underwater tasks requiring a high degree of both strength and dexterity, ranging from scientific tasks such as capturing delicate live...
[Read More]