May 2022

3D printed robot dog walking on terrain for STEM education

In this project, I made a robot dog for STEM education based on 3D printing and Arduino development kit. On top of this, I completed the integration of ESP32 and MPU6050, which gave the robot the ability of motion detection. Through the calculation of the motion data and the implemented PID control system, I completed a very good Self-Balance function. In addition, I also tried to apply the self-balance algorithm to the motion state which improves the motion posture and optimize the performance of the robot dog walking on certain terrain. Finally, I sorted out the problems encountered in the development process and some important principles into a document for STEM education, which can help others better understand and apply related content.

BREED HKU’s quadruped robot – DoggiE @6th Inno Show

Quadruped robots are envisioned to play an inseparable part of urban operations under the new normal, to perform versatile errands like instant data-retrieval in inaccessible/a multitude of environments, real-time monitoring. Such robots have been heavily researched and developed recently, offering optimal endurance, maneuverability and stability, as demonstrated by models in the market, like ANYmal C and the Alien go robot.

DoggiE aims to become the first industrial-grade quadruped robot developed by HKU, to accomplish accolades of the quadruped robot “Spot” at Boston Dynamics, to supplement task forces during emergencies and shortage of manpower, broadening the range of surveyance, and minimizing injuries/damage to human resources, with less than half of the cost (~300k). It offers versatile functionality, being capable of climbing stairs, implementing computer-vision, object retrieval and self-recovery. We believe establishing the technical basis of DoggiE, enables engaging in partnerships with the government or companies specializing in outdoor robotic solutions.

RoboMaster @ 6th Inno Show

Students will design and develop different types of robots that can launch projectiles in a complex battlefield. The robots are required to cooperate with each other and work together to attack the base of the opponent and at the same time protect their own base. Students will form a team to participate in the RoboMaster 2022 Robotics Competition and compete against other teams from all over the world using their self-build robots.

Pick and Place Game App for 3D Printed Robotic Arm

AI versus human players in games has been an increasingly popular topic, especially after the victory of AlphaGo. This project aims at developing a Connect Four AI for STEM education that utilizes a mobile application and a robotic arm to play with human opponents. In order to accomplish the objective, multiple software and hardware tools and methods were employed to design the system workflow of the Android application. Furthermore, experiments were conducted to select the best approaches. Based on the results, computer vision with OpenCV circle and color detection was used to recognize the board, and an optimized minimax algorithm with Alpha-Beta pruning was implemented to calculate the next best move. With the completed product, players have an advanced Connect Four gaming experience by playing against the perfect AI, which can be utilized in STEM education by demonstrating the strength of AI in making decisions and recognizing objects. However, with the limitations in the application and robotic arm, the product can further be improved to enhance usability and gaming experience in the future.

Smart Soccer Robot @ 6th Inno Show

This project aims to build a soccer robot including a design, a final product and a business plan for our product. The design of our group’s soccer robot is based on a real spider. It includes the spider legs and webs. The spider front legs design helps trap the ball and not to get out again. Our soccer robot is user friendly. It contains two modes of control. With the attractive outfit of our robot at the same time, our robot aims to attract more teenagers in Hong Kong to know more and get interested in STEM.

Design and Build an Intraocular Pressure Controllable Gadget

Glaucoma is the second leading cause of irreversible blindness and its diagnosis is often delayed due to its painless symptoms and slow development of loss of eyesight. A gadget is needed to be built to increase intraocular pressure such that the deformation of optic nerve can be studied to facilitate research in the diagnosis of Glaucoma. A goggles-like device was built using TPU by 3D-printing. It exerts force on the eye periphery hence causing pressure build up. It was then tested and it showed successful results during clinical testing.

Smart Patrol Robot – Lost & Found

In this project, the goal is to develop the lost and found functionality of the patrol robot supplied by Airport Authority Hong Kong, where the robot patrols around designated areas and the camera of the robot will capture the surroundings. With object detection performed with an AI model, the robot will find lost items in the checkpoints and then store information of 2nd class objects, such as wallets, into a database. If lost belongings are found, the robot will report to the staff at the Hong Kong international Airport through a Telegram report channel and update a web portal which shows records of lost items.

Smart Water Auditing using IoT and Machine Learning

The Smart Water Auditing using IoT, and Machine Learning project aims to provide insights on how water is being in the households of Hong Kong to reduce the consumption of water and raise the awareness of people’s water consumption habits. To help increase participants’ water consumption awareness, a dashboard was designed to provide a simple yet interactive way for users to review their water usage. To create a dashboard, a graphical user interface and a communications system must be designed. However, the initial design of the dashboard suffered from connection issues and graphical user interface performance issues, both of which are essential functions of the dashboard. Therefore, extensive testing and optimisation was necessary to mitigate these problems. However, the dashboard still suffers from minor stuttering due to the microcontroller’s limited performance. Despite this, the design of the dashboard was a success, and it serves as a crucial medium for participants to review their water statistics.