木瓜福利影视

My research is at the intersection of AI ethics, cognitive science, and computational modelling, with a focus on ensuring that autonomous systems鈥攑articularly automated vehicles (AVs)鈥攎ake decisions that are ethically sound, socially legitimate, and transparently accountable. As intelligent machines increasingly operate in high-stakes environments, their actions have direct consequences for human lives, rights, and social values. My work addresses the urgent question: How can we ensure that AI systems reflect and respect the moral standards of the societies they serve?

My PhD research develops a novel ethical framework for aligning AI decision-making with human values, grounded in interdisciplinary insights from moral psychology, affective neuroscience, and ethical philosophy. I designed and implemented a hybrid AI architecture that translates human moral preferences into computational ethical goal functions. These goal functions are empirically validated through large-scale behavioural experiments and formalised using techniques from discrete choice modelling. This enables AVs to make ethically informed decisions in real time while remaining transparent and explainable.

My research highlights that ethical AI cannot be reduced to abstract rules or fixed utility functions. Moral norms are context-sensitive, culturally variable, and evolve over time. My work therefore proposes an adaptive, participatory approach: integrating stakeholder feedback, regulatory guidance, and experimental findings into a socio-technical feedback loop that refines ethical decision systems over time. I also explore the implications of these systems for legal compliance, public trust, and democratic legitimacy.

Beyond the AV domain, my research contributes to broader debates in machine ethics, AI alignment, and responsible innovation. It informs both the technical design of AI systems and the governance structures needed to regulate their ethical behaviour. By bridging philosophy, behavioural science, and computational modelling, I aim to advance the development of AI that is not only intelligent, but also just, fair, and societally aligned.