Abstract
We discuss planning implemented in a computational architecture called dynamical constraint programming. This architecture is totally constraint-based, with the semantics of constraints defined as a sort of dynamics. The degree of violation of constraints is captured in terms of potential energy, which is a real-valued function of the state of the constraint. The constraint is thus provided with a fine-grained declarative semantics. Control schemes for analog and symbolic inferences are obtained on the basis of the energy minimisation principle. Information processing occurs as dynamical interaction, so that tight feedback loops are established among diverse sorts of information. Planning is emergent and does not need any specific procedure (i.e., planner). Information processing for action selection (i.e., planning) emerges from the dynamical control of computation. The dynamical state and topology of constraints change in accordance with the interaction between agents and their ever-changing environments. Shifting between reactivity and deliberativity is also an emergent property of this dynamical control.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
P. E. Agre and D. Chapman, “Pengi: An Implementation of a Theory of Activity,” In Proceedings of the 6th National Conference on Artificial Intelligence (AAAI-87), 1987.
D. E. Appelt and K. Konolige, “A Nonmonotonic Logic for Reasoning about Speech Act and Belief Revision,” In Proceedings of the 2nd International Workshop on Non-Monotonic Reasoning, Lecture Notes in Artificial Intelligence, vol.346, pp.164–175, Springer-Verlag, 1989.
M. Boddy and T. Dean, “Solving Time-Dependent Planning Problems,” In Proceedings of the 11th International Joint Conference on Artificial Intelligence (IJCAI-89), pp.979–984, 1989.
R. Brooks, “Intelligence without Representation,” Artificial Intelligence, vol. 47, pp. 139–160, 1988.
R. Brooks, “Intelligence without Reason,” In Proceedings of the 12th International Joint Conference on Artificial Intelligence (IJCAI-91), pp.569–595, 1991.
P. R. Cohen and H. J. Levesque, “Persistence, Intention, and Commitment,” In P. R. Cohen, J. Morgan, and M. E. Pollack (eds.), Intentions in Communication, pp.33–69, MIT Press, 1990.
P. R. Cohen and H. J. Levesque, “Confirmations and Joint Action,” In Proceedings of the 12th International Joint Conference on Artificial Intelligence (IJCAI-91), pp.951–957, 1991.
T. Dean and M. Boddy, “An Analysis of Time-Dependent Planning,” In Proceedings of the 7th National Conference on Artificial Intelligence (AAAI-88), pp.49–54, 1988.
A. Drogoul and C. Dubreuil, “Eco-Problem-Solving Model:Resultsof the N-Puzzle,” In E. Werner and Y. Demazeau (eds), Decentralized A.I. 3, pp. 283–295, Elsevier/North-Holland, 1992.
J. Ferber and E. Jacopin, “The Framework of Eco-Problem Solving,” In Y. Demazeau and J.-P. Müller (eds), Decentralized A.I. 2, pp. 181–193, Elsevier/North-Holland, 1991.
S. Forrest (ed.), Emergent Computation, MIT Press, 1991.
K. Hasida, “Dynamics of Symbol Systems: An Integrated Architecture of Cognition,” In Proceedings of the International Conference on Fifth Generation Computer Systems (FGCS-92), pp.1141–1148, 1992.
K. Hasida, K. Nagao, and T. Miyata, “Joint Utterance: Intrasentential Speaker/Hearer Switch as an Emergent Phenomenon,” In Proceedings of the 13th International Joint Conference on Artificial Intelligence (IJCAI-93), pp.1193–1199, 1993.
P. Maes,“Situated Agents Can Have Goals,” In P. Maes (ed.), Designing Autonomous Agents: Theory and Practice from Biology to Engineering and Back, pp.49–70, MIT/Elsevier, 1991.
C. R. Perrault, “An Application of Default Logic to Speech Act Theory,” In P. R. Cohen, J. Morgan, and M. E. Pollack (eds.), Intentions in Communication, pp.161–185, MIT Press, 1990.
F. J. Pineda, “Generalisation of Backpropagation to Recurrent and Higher Order Neural Networks,“ In D. Z. Anderson (ed.) Neural Information Processing Systems, pp.602–611, 1988.
S. Rosenschein,“Formal theories of Knowledge in AI and Robotics,” Technical Report, CSLI-87-84, Center for Study of Language and Information, Stanford University, 1987.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Nagao, K., Hasida, K., Miyata, T. (1995). Emergent planning: A computational architecture for situated behaviour. In: Castelfranchi, C., Müller, JP. (eds) From Reaction to Cognition. MAAMAW 1993. Lecture Notes in Computer Science, vol 957. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0027055
Download citation
DOI: https://doi.org/10.1007/BFb0027055
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-60155-5
Online ISBN: 978-3-540-49532-1
eBook Packages: Springer Book Archive