معرفی
Martim Brandão is a Lecturer (Assistant Professor) in Robotics and Autonomous Systems at King's College London, leading the Responsible Robotics and AI (RRAI) Lab and co-directing the UKRI Centre for Doctoral Training in Safe and Trusted AI. His work focuses on mitigating risks in AI/robotics, ethical algorithm design, and socially just technologies. He holds a PhD in Engineering from Waseda University, with postdoctoral experience at King's College London, Oxford Robotics Institute, and Waseda's Takanishi Laboratory.
- Education: PhD in Engineering (Waseda University, Japan), Postdoc (King's College London, Oxford Robotics Institute, Waseda)
- Key Research Interests: Ethical AI, Explainable Planning, Fairness in Robotics, Adversarial Attacks on Motion Planners, Human-Robot Interaction
His recent publications address critical issues such as bias in reinforcement learning, ethical dilemmas for delivery robots, and fair drone delivery path optimization. He co-leads initiatives like the Sustainability Hub and Trusted Autonomous Systems Hub, emphasizing responsible innovation. His work bridges technical rigor with societal impact, advocating for transparency and equity in autonomous systems.
Awards: None explicitly listed, though his roles and collaborations reflect institutional recognition. Grants: Secured £400k from the AI Security Institute for human-AI collaboration research (2025).
Labs/Teams: RRAI Lab (King's), CDT in Safe and Trusted AI (co-director), and collaborations with interdisciplinary centers like the Centre for Data Futures.
