Reflective Intelligence Amplification: Tackling Wicked Problems Through Dynamic Search Space Exploration

Project Description

The research objective is to develop a Reflective Intelligence Amplification method that is able to accelerate this learning process in a virtual computational environment. The method will aim to support a non-verbal ‘conversation’ between the practitioner and the computational environment. The non-verbal conversation will oscillate between the practitioner modifying the search space and the computer searching that space.

The three main outcomes of the research will be: a method, a system, and a case study. The method will be applicable to a wide variety of domains where wicked problems are prevalent. The system will focus on one domain, in this case long-term urban design and planning. The case study will show how the method and the system can be used to generate improved design proposals for a real urban design and planning problem.

Research Technical Area

  • Heuristic Search and Optimization
  • Reasoning under uncertainty
  • Intelligence Amplification

Benefits to the society

The world is full of pressing and urgent problems, most of which are wicked. The fact that Reflective Intelligence Amplification includes the human-in-the-loop, it is able to sidestep many of the hurdles that make the application of pure AI approaches (without humans) so difficult. In general, Reflective Intelligence Amplification can potentially deliver significant results of great benefit in the short term. Furthermore, Reflective Intelligence Amplification is likely to be one of the core tools required for developing the next generation of AI.

Team’s Principal Investigator

Associate Professor Patrick Janssen

National University of Singapore

Patrick Janssen is an Associate Professor at the Department of Architecture at the National University of Singapore and is the Director of the Design Automation Laboratory. He is also Adjunct Associate Professor in Automation in Urban Planning and Design at the 3D GeoInformation research group at the Department of Urbanism, Faculty of Architecture and the Built Environment, TU Delft. He received his PhD from Hong Kong Polytechnic University, his MSc in Cognitive Science and Intelligent Computing from Westminster University, and his AA Diploma from the Architectural Association. Patrick conducts research into computational methods and tools for design exploration and optimisation at the urban scale.