Our Solartronic Autonomous Mini (SAM) Robot is an autonomous weight-loading robot programmed to navigate intelligently, avoiding obstacles and following human targets. This Arduino-based robot can utilize a solar energy collection system by integrating a photovoltaic panel into the surface. It can operate in an environmentally friendly and sustainable manner with a carrying capacity of up to 10 kg to assist in various tasks. SAM Robot is designed to intelligently and independently explore its surroundings, dodging obstacles and tracking human targets. This Arduino-based robot is an eco-friendly technical solution since it can be fully powered by the collected solar energy. It uses a variety of sensors and sophisticated algorithms to identify objects in front of it while reducing its dependency on conventional power sources. The SAM Robot’s intelligence is notable for its capacity to identify obstacles and follow human targets. Its control algorithm is designed to monitor the robot’s trajectory and detect any impending obstructions, whether in motion or stationary. Based on this feature, the SAM Robot is a very useful tool for a range of applications, including the transport of small objects as well as the handling of heavy or bulky loads.
Category: ypec-2024
As the traffic environment becomes increasingly complex, visually impaired individuals face numerous challenges when traveling, such as: inability to recognize traffic lights; struggling to pass when tactile paving is occupied; having trouble to use visually-based interactive devices like smartphones; difficulty in timely obstacle avoidance; inability to determine their current location in unfamiliar environments; and difficulty in seeking help during emergencies. Therefore, developing an intelligent travel assistance system based on voice interaction holds significant practical importance. This design aims to create a smart travel assistance system based on voice interaction with the following technical features: 1) Sidewalk detection using computer vision algorithms to detect deviations from the centerline, alerting with a buzzer; 2) Obstacle and traffic signal recognition using deep learning models and radar; 3) Intelligent voice interaction using AI speech recognition and NLP models; 4) GPS positioning to broadcast current location and nearby points of interest; 5) Fall detection using a gyroscope to measure angular velocity and acceleration, sending an emergency alert when necessary. This design not only provides visually impaired individuals with low-cost, high-safety travel assistance services but also enhances their ability and confidence to travel independently, improves their travel experience, and increases their enjoyment of traveling.
Categories
UG06 – AI Grader
Automatic grading tools are widely adopted in educational institutions, and various studies have proven that they can reduce the workload of school staff and improve students’ learning experiences. Existing automatic grading tools, such as nbgrader and Gradescope, can achieve automatic grading of programming-related queries, but feedback must be created manually. Limited by the needs of large-class teaching environments, a large number of manual tasks can also affect the quality of feedback, making it difficult for students to receive targeted and useful insights. This also increases the difficulty for teachers in summarizing students’ common mistakes. This project aims to grade students’ responses and provide comprehensive feedback. It integrates a Large Language Model (LLM) into nbgrader for grading, aiming to significantly enhance the feedback mechanism. To enrich the feedback with more detailed and useful insights, the system will leverage Retrieval Augmented Generation (RAG), which will fine-tune the feedback to be deeply informative by creating a knowledge base to provide constructive suggestions, thereby improving the efficiency and effectiveness of the grading process. Additionally, students’ answers and grading history will be recorded in a database to automatically analyze common errors and provide students with a chatbot for more personalized help.
This project aims to help homeless people, slums and lower income citizens. By using additive manufacturing to build houses and use our app for donations for charity to build new houses. Our app not only can accept donations, it can also trade, buy and sell housings and also check for the prices.
Categories
UG01 – GymingHK
Gyming HK is a fitness coaching app that integrates artificial intelligence to analyze the posture and habits of people working out to prevent injury and improve training efficiency in this society in which everyone wants to be healthy! The fitness business is expanding exponentially. There is a desperate need for education on how to work out without injury. We aims to provide a mobile application integrated pose analysis for user to receive real time feedback on their pose to prevent injury when working out.
Categories
UG03 – PharmAI
PharmAI is a cutting-edge and innovative solution to the modern day problem of medication selection. PharmAI’s main goal is to tackle the confusion that most customers experience when faced with rows of counter top medicine made available today. With PharmAI, customers would no longer have to feel conflicted in dealing with counter top medicine. As PharmAI would be build based on a knowledge-based AI, customers would be able to “consult” their medication needs. Then, the system would pull information from thousands of medical books and cases, referring back to the customer’s symptoms and inputs, ensuring quality medicinal recommendations every time.
Categories
UG04 – Knowledge Sharing Hub
This project combines the library management system and the optical character recognition (OCR) technology to support people to write book reports and share with the public through our system on the Internet. More advanced automated services are incorporated to library services that allow people to have a knowledge sharing hub to communicate their reading feedback. The system encourages people to cultivate a good reading habit to improve their reading ability and relieve pressure.
As the demand for e-learning continues to grow (14% GAGR between 2023 and 2032), it becomes increasingly difficult to provide expensive computing resources, especially the GPUs to support LLMs in teaching. It is also challenging to secure a centralized server, especially for programming tools such as OPT that allow students to execute arbitrary code. This complexity often leads to restricted access and functionality, thereby limiting the effectiveness of these tools. The project aims to develop an advanced version of the Online Python Tutor (OPT), named OPT Mentor. It incorporates OPTLite and WebLLM to offer students detailed explanations of error messages in context. It uses students’ own GPU to provide AI-powered suggestions for enhancing their code directly through a web browser without a network. Additionally, OPT Mentor is designed to integrate effortlessly with JupyterLite, allowing students to save and revisit their solutions in Jupyter notebooks anytime.
Unmanned aerial vehicles (UAVs) are used in the rapidly expanding drone delivery market to carry packages and supplies to clients. Recently, the Central Economic Work Conference emphasized Platform economics, Low-altitude economics, and Automation combined logistic model. As logistics industry is the largest among the four main economic pillars in Hong Kong. Moreover, Hong Kong is a core city in GBA, having status as an international leader in sectors including innovation and technology. It is important to discover the possibility of low-altitude economics, hence we are going to suggest an approach to regulating flight and safety. We suggest supervised reinforcement learning for path planning and fly control. The environment combines information of geospatial data from the Hong Kong Land Department and weather data from the Hong Kong Observatory; The agent is the 6 degree-of-freedom of the drone; while the reward and action are related to legislative restrictions from civil aviation department, the delivery mission from the customer, risks from environment, and spatial occupied by other drones. The overall aim of this system is to regulate flight under complex urban environments, prevent accidents and crashes, avoid violation of law, and establish a manageable low-altitude aerospace.
ArtInSight is an AI-powered art learning platform that enhances the way students engage with art by providing personalized learning experiences. To explain in detail, our platform includes an AI Art Vision module that enables users to explore artworks in-depth through instant identification, historical analysis, and comparative insights. With art style analysis, visualized notes, and the ability to explore art history and compare artists, we offer an immersive experience. With our fine-tuned Art GPT users can delve deep into every artwork, via crop-and-ask function to know more about specific area, and interact with our conversational art GPT To facilitate students’ learning and visualize all the knowledge points, we introduce features such as historical timelines, relationship mapping, dynamic challenges, and personalized guidance as well. This multifaceted approach not only facilitates knowledge acquisition but also nurtures creativity, critical thinking, and a lifelong appreciation for the arts. Additionally, ArtinSight utilizes Generative Al to create a polished artwork as reference based on users drawing and offer personlized in-depth comparative suggestions between both artworks. Users can modifiy an existing artpiece with preferred artistic styles, unleashing their artistic potential by generating unique artworks. This can achieve personlized one-on-one coaching on user application technique and improvment.