Course Materials

Constructionist AI





This page contains links to recommended course materials, design methodologies and tutorials. We will be putting up discussion boards for this in the near future. In the mean time feel free to join our discussion on the MINDMAKERS Forum.


Constructionist AI

Constructionist AI is the methodological framework that best describes the philosophy behind MINDMAKERS.ORG. The approach has its roots in large systems development. A fundamental assumption behind Constructionist AI is that artificial intelligence is a science with a strong engineering foundation. AI systems that approximate human knowledge and skill, and systems like those we read about in classic science fiction stories, will not happen without the integration of a multitude of technologies, techniques, tricks, hard work, open-source software and close collaboration between industry and academia. It is simply impossible for a single company, inventor, university, professor or graduate student to invent and research all of the needed technologies. AI is multidisciplinary. This requires the application of sound engineering principles. Recognizing these facts now will help move the field sooner along more prosperous paths.

Supporting MINDMAKERS work on the OpenAIR specification, a key part of the Constructionist approach is modularization. Modular approaches have been shown to speed up the development of large, complex systems, and to facilitate the collaborations of large teams of researchers [Fink et al. 1995, 1996]. For instance, Martinho et al. [2000] describe an architecture designed to facilitate modular, rapid development of theatrical agents in virtual worlds. Like many other systems [cf. Granström et al. 2002, Laird 2002, McKevitt et al. 2002, Badler et al. 1999, Terzopolous 1999], architecture involves splitting the world and the agents into separate modules, each which can be developed somewhat independently of the others. This enables parallel execution of implementation, reducing development time, and combining the pieces to form a full system becomes a simpler task. Modularity has also played a large role in the construction of robotic systems such as Bischoff et al.'s impressive HERMES robot [2000] and Simmons et al.’s robot Grace [2003], the latter of which involved the work of 5 institutions and over 20 people.

Related Approaches

Constructionist Design Methodology. The Constructionist Design Methodology (CDM) builds upon earlier efforts related to Constructionist AI



Badler, N., M. S. Palmer, R. Bindiganavale (1999). Animation Control for Real-Time Virtual Humans. Communications of the ACM, August, vol. 42(8), 65-73.

Bischoff, R. (2000). Towards the Development of ‘Plug-and-Play' Personal Robots. 1st IEEE-RAS International Conference on Humanoid Robots. MIT, Cambridge, September 7-8.

Fink, G. A., N. Jungclaus, F. Kummer, H. Ritter, G. Sagerer (1996). A Distributed System for Integrated Speech and Image Understanding. International Symposium on Artificial Intelligence, 117-126, Cancun, Mexico.

Fink, G. A., N. Jungclaus, H. Ritter, G. Saegerer (1995). A Communication Framework for Heterogeneous Distributed Pattern Analysis. International Conference on Algorithms and Architectures for Parallel Processing, 881-890, Brisbane, Australia.

Granström, B., D. House, I. Karlsson (2002) (eds.). Multimodality in Language and Speech Systesm. Dodrecht, The Netherlands: Kluwer Academic Publishers.

Laird, J. (2002). Research in Human-Level AI Using Computer Games. Communications of the ACM, 45(1), 32-35.

Martinho, C., A. Paiva, & M. R. Gomes (2000). Emotions for a Motion: Rapid Development of Believable Pathematic Agents in Intelligent Virtual Environments. Applied Artificial Intelligence, 14(1), 33-68.

McKevitt, P., S. Ó Nulláin, C. Mulvihill (2002) (eds.). Language, Vision & Music. Amsterdam: John Benjamins.

Simmons, R., D. Goldberg, A. Goode, M. Montemerlo, N. Roy, B. Sellner, C. Urmson, A. Schultz, M. Abramson, W. Adams, A. Atrash, M. Bugajska, M. Coblenz, M. MacMahon, D. Perzanowski, I. Horswill, R. Zubek, D. Kortenkamp, B. Wolfe, T. Milam, B. Maxwell (2003). GRACE: An Autonomous Robot for the AAAI Robot Challenge. AI Magazine, 24(2), 51 – 72.

Terzopoulos, D. (1999). Artificial Life for Computer Graphics. Communications of the ACM, 42(8), 33-42.