Julia López Gómez

• Explored the use of MCTS for manipulation in known benchmarks such as Gymnasium or Metaworld.
• Focused on understanding the integration of Reinforcement Learning (RL) concepts, Monte-Carlo simulations, and tree search algorithms with discretised manipulation scenarios.
• Implemented AlphaZero from scratch, achieving policy generation for the selected benchmarks.
• Supervision: Dr. Nicolas Mansard (LAAS-CNRS) and Prof. Ludovic Righetti (NYU).

github.com/julialopezgomez/monte-carlo-manipulation

• Continuing the work of my MINF1 dissertation, focusing on the development of an algorithm to compute manipulation plans in optimisation-based settings.
• Developed a manipulation planner capable of operating in optimisation-based settings through convex decomposition techniques (IRIS variants) and Mixed-Integer Quadratic Programming.
• Utilizing the Drake Robotics Toolbox for implementation and visualization.
• Expected to contribute to the state-of-the-art in Robot Planning.
• Supervision: Dr. Steve Tonneau.

github.com/julialopezgomez/minf2-repo

• Collaborated in a team of two to implement and analyze different object segmentation techniques.
• Implemented UNet, Autoencoder, CLIP, and Point-Based Segmentation techniques using PyTorch.
• Utilized Nvidia GPU servers to accelerate model training.
• Conducted a comparative analysis of the performance of each technique on the Oxford III Pet Dataset.
• Achieved a Dice score of over 80% for the CLIP model.

github.com/julialopezgomez/computer-vision-project

• Used Tensorflow and Keras to train different CNN models for activity and respiratory condition classification.
• Utilised Android Studio to develop an app for data collection and live classification.
• Achieved an accuracy of over 90% for activity detection (ascending and descending stairs, running, walking, shuffle walking, sitting, standing, lying down -on right, left, back and stomach- , and miscellaneous movements).
• Achieved an accuracy of over 80% for respiratory condition classification (normal, hyperventillation, coughing, and others - laughing, talking, singing).
• Leveraged different regularisation techniques to improve validation and real-time performance.

• Supporting the background on IoT research, investigated the use of IoT devices in healthcare applications for the elderly.

• Formalized the use of a tangent parametrization of the robot configuration space (TC-space) in robot manipulation, leveraging the recent advancements of the C-IRIS algorithm in motion planning.
• Proved the scalability of C-IRIS to robots with universal joints.
• Utilized the Drake Robotics Toolbox for implementation and visualization.
• Leveraged the mathematics of motion and manipulation planning, robot kinematics, algebraic rotations (SO(3) group), and optimization techniques.
• Achieved a 1st Class mark.
• Future Work - MINF2: Produce an algorithm to compute manipulation plans in the TC-space, contributing to the state-of-the-art in Robot Planning.

• Collaborated in a team of three to enhance sheep counting accuracy using PyTorch.
• Identified challenges of existing literature in detecting occluded sheep and selected a more comprehensive dataset to improve performance in such scenarios.
• Implemented transfer learning techniques to adapt pre-trained models for sheep detection, such as SSD and Faster R-CNN.
• Utilized Nvidia GPU servers to accelerate model training.

• Learning ROS2 and creating student guides from scratch.
• Delivered workshops on Raspberry Pi and Arduino to Computer Science students.
• Maintained 3D printers, prepared electronic kits, and supported student projects.
• Received The Edinburgh Award for my contributions as a Makerspace Student Technician.

• Developed a CanSat and a 3-unit CubeSat as payloads for a student-assembled rocket.
• Learned and designed the circuit schematics and PCBs of the payload with Altium Designer.
• 2nd position in Combined 3km Launch Vehicle and CanSat category at Mach-23 competition.
• Key skills: Python, Raspberry Pi, embedded programming, parafoil design, etc.
• From August 2023: Co-leading the team, mentoring 1st and 3rd Year students.
• Research Experiments: Microbial Air Sampler, Simulated Life Search, Albedo Detection, etc.
• Invited to Airbus CubeSat day to present our project to other UK satellite student teams.

• Contributed to agile product development using Java, Maven, SQL, and Spring Boot.
• Developed backend solutions integrating with Oracle Databases.
• Utilized React.js for frontend development in a collaborative environment.

• Demonstrator for INF1A - Introduction to Computation.
• Ran weekly labs, helping first-year students in their learning of Haskell and Computational Logic.

• Started as an Informatics Parent for incoming first-year students.
• Mentoring 11 first-year students, providing guidance and support in their transition to university.

• Gathered weekly feedback from over 300 students and communicated it with university faculty.
• Achieved the transition of a module from online to in-person post-COVID by advocating for student interests with school authorities and professors.
• Received The Edinburgh Award for Leadership in Student Opportunities.

• Started as an Informatics Parent for incoming first-year students.
• Mentoring 11 first-year students, providing guidance and support in their transition to university.

• Designed and developed a personal portfolio website to showcase my academic and professional achievements.
• Utilized HTML, CSS, and JavaScript to create a responsive and interactive user experience.
• Implemented collapsible sections for a clean and organized layout.
• Integrated a particle.js background for a dynamic visual effect.

• Invited to Airbus CubeSat Day to present our Payload project with Endeavour Rockets to other UK satellite student teams.
• Our project included the 3-unit CubeSat payload, with an experiment to simulate the search of life in Exoplanets.
• Engaged in discussions with industry professionals and other student teams.