We argue that generally accepted methodologies of artificial intelligence research are limited in the proportion of human level intelligence they can be expected to emulate. We argue that the currently accepted decompositions and static representations used in such research are wrong. We argue for a shift to a process based model, with a decomposition based on task achieving behaviors as the organizational principle. In particular we advocate building robotic insects.
Cited By
- Mariani S and Omicini A (2018). Coordinating activities and change, Engineering Applications of Artificial Intelligence, 41:C, (298-309), Online publication date: 1-May-2015.
- Dusparic I and Cahill V Multi-policy optimization in self-organizing systems Proceedings of the First international conference on Self-organizing architectures, (101-126)
- Sadedin S and Paperin G Implications of the social brain hypothesis for evolving human-like cognition in digital organisms Proceedings of the 10th European conference on Advances in artificial life: Darwin meets von Neumann - Volume Part II, (61-68)
- Hoffmann H (2018). Perception through visuomotor anticipation in a mobile robot, Neural Networks, 20:1, (22-33), Online publication date: 1-Jan-2007.
- Martínez-Alfaro H and Cervantes-Casillas G Performance improvement of ad-hoc networks by using a behavior-based architecture Proceedings of the 4th Mexican international conference on Advances in Artificial Intelligence, (1103-1112)
- Weyns D and Holvoet T From reactive robotics to situated multiagent systems Proceedings of the 6th international conference on Engineering Societies in the Agents World, (63-88)
- Barto A and Mahadevan S (2019). Recent Advances in Hierarchical Reinforcement Learning, Discrete Event Dynamic Systems, 13:1-2, (41-77), Online publication date: 1-Jan-2003.
- Barto A and Mahadevan S (2019). Recent Advances in Hierarchical Reinforcement Learning, Discrete Event Dynamic Systems, 13:4, (341-379), Online publication date: 1-Oct-2003.
- Raducanu B, Sussner P and Graña M Steps towards one-shot vision-based self-localization Biologically inspired robot behavior engineering, (365-393)
- Russell S and Zimdars A Q-decomposition for reinforcement learning agents Proceedings of the Twentieth International Conference on International Conference on Machine Learning, (656-663)
- Duro R, Santos J and Becerra J Some approaches for reusing behaviour based robot cognitive architectures obtained through evolution Biologically inspired robot behavior engineering, (239-259)
- Hallerdal A and Hallam J Behaviour selection on a mobile robot using W-learning Proceedings of the seventh international conference on simulation of adaptive behavior on From animals to animats, (93-102)
- Belpaeme T and Birk A (2001). Hungry robots, XRDS: Crossroads, The ACM Magazine for Students, 8:2, (15-19), Online publication date: 1-Dec-2001.
- Butler G, Gantchev A and Grogono P Reusable Strategies for Software Agents via the Subsumption Architecture Proceedings of the Sixth Asia Pacific Software Engineering Conference
- Trappl R and Petta P What Governs Autonomous Actors Proceedings of the Computer Animation
- Nelson R and Aloimonos J (2019). Obstacle Avoidance Using Flow Field Divergence, IEEE Transactions on Pattern Analysis and Machine Intelligence, 11:10, (1102-1106), Online publication date: 1-Oct-1989.
Recommendations
Artificial intelligence implications for information retrieval
Overall, the field of information retrieval is already more aware than many other fields of the relevance of artificial intelligence (AI) [1-6]. Nonetheless there remain exciting applications of artificial intelligence that have been so far overlooked. ...
Artificial intelligence
AbstractArtificial intelligence (AI) is the Science and Engineering domain concerned with the theory and practice of developing systems that exhibit the characteristics we associate with intelligence in human behavior. Starting with a brief history of ...