Summary of Project
Deep neural networks are powerful tools to learn representations from high-dimensional data. Deep imitation learning has been studied to enable robots to learn unknown dynamics and acquire complex visual-motor skills, which maps the raw pixels of the robot's observations to actions based on a pre-trained model obtained via leveraging the demonstration data from humans. However, learning from raw visual inputs typically requires a large database for model training. A robot cannot perform a new task with reasonable behaviors when given limited demonstration data on the task. That is to say, it is impractical for the robot to acquire skills and adapt to new scenarios for task execution. This is known as one of the key limitations for deep imitation learning, which should be addressed to improve its generality for adaptation to new tasks.
Academic criteria: A first-class undergraduate degree or a master degree.
Applicants will also need to meet the University’s English Language requirements by obtaining an IELTS score of at least 6.5 overall, with a minimum of 6.0 in each skills component.
Desirable Applicants will have:
• Strong programming skills
• Solid skills in theoretical analysis
• Strong communication skills in oral and written English
• Interest in autonomous robotics, machine learning, computer vision
Dr. Dandan Zhang, Prof. Nathan Lepora