PolyU URIS
2023-2024
Project 1
Title: Development of an Intelligent Trash Pick-up Robot
Member: Mr WANG Zian (EEE, YEAR-3), Mr CHEN Xianzhe (EEE, YEAR-3), Mr WU Hengyu (EEE, YEAR-3)
Motivation: Cleaning trash on streets is a boring job, and mobile sweeping robots are a good choice to replace human workers. However, the existing sweeping robots are mainly restricted to flat ground, and they blindly clean designated areas, which is inefficient generally.
Objective: This project aims at developing a mobile robot that has high terrain adaptability yet can carry the modules of auto navigation, computer version and unmanned control, to perform automatic trash classification and collection.
Project 2
Title: Making Advanced Driver Assistance Systems (ADAS) Personalized and Connected
Member: Mr LU Dingfu (EEE, YEAR-2)
Motivation: Advanced Driver Assistance Systems (ADAS) have garnered considerable attention due to their potential to enhance road safety and driving comfort. However, current ADAS implementations often adopt a one-size-fits-all approach, leading to fixed settings that may not accommodate individual driver preferences or habits. This lack of personalization could result in suboptimal user experiences and even safety risks. Moreover, intersections with limited visibility present significant challenges for road safety. The increasing number of accidents at such locations underscores the need for robust, proactive measures to mitigate blind spot-related risks.
Objective: The project aims to develop a more comprehensive Advanced Driver Assistance System (ADAS) system that not only enhances the driving experience by personalizing safety features but also improves road safety by addressing visibility issues at intersections.
Project 3
Title: Applying Evolutionary Game Theory to Analyze Autonomous Bus Control System Algorithms
Member: Mr FENG Zhanpeng (ISE, YEAR-4)
Motivation: The development of autonomous vehicles, including autonomous buses, has been a primary focus of research and development in recent years. Autonomous buses have the potential to significantly improve the efficiency, safety, and sustainability of public transportation systems. To fully realize these benefits, it is necessary to develop practical algorithms that govern the behavior of these vehicles.
Objective: The project will focus on the application of evolutionary game theory to the analysis of algorithms used in autonomous bus control systems, investigating how various strategies employed by autonomous buses affect the overall performance, efficiency, and safety of the transportation system.
Project 4
Title: Personalized route designing and decision making for autonomous vehicles
Member: Ms CHEN Yijia (EEE, YEAR-4) , Ms WU Meijia (COMP, Year-4)
Motivation: To ensure driving satisfaction, autonomous vehicles need to design personalized routes and driving styles for individuals, which is an essential part of shared autonomy. Even though some advanced autonomous driving systems are able to control various actions of vehicles, the coordination between the human driver and the vehicle has not reached the desired level.
Objective: This project aims at developing a framework and the associated algorithms such that the vehicle is able to capture the intention of the human driver and then plans the route for the near future.
Project 5
Title: A USV and UAV-based Collaborative Autonomous System for Maritime Search and Operation
Motivation: As shown in the right figure, a human-driven boat is collecting trash at Victoria Harbour. This is the current practice for trash collection in Hong Kong, and obviously, it is time and labour-consuming (at least one driver and one person to collect trash should be on the boat).
Objective: This project aims at developing an unmanned surface vehicle (USV) and unmanned aerial vehicle (UAV)-based collaborative autonomous system for maritime search and operation, such as trash searching and collecting. The UAV will explore the ability of fast movement and the large field-of-view for searching. The UAV will transmit the location of the identified trash wirelessly to the USV, and the USV will plan its path for collecting trash in an optimal manner such as in the shortest time and using the minimum energy consumption.
2022-2023
Project 1
Title: Interaction-Aware Trajectory Prediction of Surrounding Vehicles in a Congested Environment
Member: Mr. Fuad Hasan (AAE, YEAR-4)
Motivation: For safe autonomous driving in a congested environment, it is important for an autonomous vehicle to predict the future trajectory of the surrounding vehicles to make important control decisions during lateral movements such as lane change.
Objective: This project aims at developing an interaction-aware approach to accurately predict the future trajectories of the surrounding vehicles via the integration of data-driven methods with probabilistic-machine learning methods.
Achievement:
1st Runner-up in AI HK OpenCup 2022 (with HKD 20,000 cash award) (with an ME UG student Mr. Hamad Khan)
A published journal paper (know more)
Project 2
Title: Commanding a Group of UAVs/robots via Face Engagement and Voice
Member: Mr. Samuel YAKOBUS (EIE, YEAR-3)
Motivation: A traditional approach to control a group of UAVs/robots is to use controller software to program the movement or task of the UAVs/robots. The input or controls are given through commands of code given by the operator. In this project, we are trying to see if we can give more creative inputs through gestures, including face engagements, and voice, which can be more intuitive to human operators. This might be able to bridge the gap between humans and robots as not everyone is as technical.
Objectives:
Develop a set of facial engagements, gestures, and voices from human operators that can use to control a sub-group of UAVs/robots accurately.
Explore the idea of Human-Robot Interaction where a human operator and a sub-group of UAVs/robots can agree on interaction through the input of commands through cameras and microphones.
Project 3
Title: Human-machine Cooperative Path Planning and Tracking Control Design for Highly Automated Vehicles
Members: Mr. Yutong LIU (EIE, YEAR-4), Mr. Haoran QIN (EIE, YEAR-4), Mr. Meng WANG (COMP, YEAR-4)
Supervisors: Dr. Chao HUANG (chief supervisor) and Dr. Hailong HUANG (co-supervisor)
Motivation: In recent years, autonomous driving has been extremely improving because of its huge potential to reduce accidents and optimize transportation efficiency, and it allows some people with physical limitations to drive vehicles. However, autonomous driving causes some problems, such as misidentification, instability of the computing system, passengers’ uncomfortableness with the driving pattern and so on. These complicated issues may be solved by an experienced human driver, showing that machine is unable to completely replace human at present. As a result, the human-machine cooperative system attracts more attention, which combines the advantages of autonomous driving and manual driving.
Objectives:
Develop a cooperative path planning and tracking control system for a highly automated vehicle with the consideration of human driver and automation system in the static environment and the specified dynamic environment.
Improve the safety and efficiency in improving the mechanical awareness of human drivers’ planning and increasing the prediction time.