Bio-Inspired Models and Biologically Plausible Mechanisms for Long-Term Motion Learning

Biological systems can learn from interactions with their environment throughout their lifetime. Learning is a defining ability of biological systems, whereby experience leads to behavioral adaptations that improve performance. Artificial systems need the ability to learn on a continual basis to be successfully act and adapt in the real world.

New generation of robotics & AI applications will require a new type of machine intelligence that is able to learn in a long-term manner. Such machines will need to acquire new skills without compromising old ones, adapt to changes, and apply previously learned knowledge to new tasks - all while conserving limited resources such as computing power, memory, and energy.

The ambition behind this project is to enhance the comprehension of biological underpinnings for long-term learning, including adaptability and autonomy exhibited by animals, as well as creating innovative machine intelligence and robotic solutions, and applied control systems characterized by greater adaptability, resilience, and energy efficiency.

In this project, the successful PhD student will focus on one of the following areas: Modelling and transfer of human/animal excellence/knowledge for autonomous motion learning, detection & generation; Enhancement of sensory-motor and learning capabilities; Optimized morphological design for behavioural variability;

Optimal dynamics control for motor control learning.

You will address these issues by: (1) modelling and designing control systems considering the bio-inspired models, and (2) analysing the systems using simulations, and experiments with various robotics systems available at the university.

The ideal applicant should possess experience and a keen interest in robotics, control, machine intelligence and signal processing. However, the specific focus of the research is likely to depend on the skills of the successful candidate. This is an exciting interdisciplinary research project that offers experience with design and control of a long-term learning intelligent machine.

You will get opportunities to present your work at national and international conferences. The knowledge and skills you learn during this project will be applicable to systems from different fields such as human-robot collaboration & interactions, agriculture & aquaculture environment control, soft robotics & new actuations, rehabilitation, and embodied artificial intelligence.