论文信息 - Learning to Survive

Learning to Survive

The paper discusses possible ways for an autonomous robotic agent to learn to survive. Pitfalls linked with this task and possibilities to overcome them are investigated. This is done in respect to an existing real-world setup and concrete learning approaches as well as on a general level. The connection between the energy-level of a robotic agent and its survivability is examined in some detail.

Andreas Birk | A. Birk

[1] John R. Koza,et al. Genetic Programming II , 1992 .

[2] Luc Steels,et al. Discovering the Competitors , 1996, Adapt. Behav..

[3] D. E. Goldberg,et al. Genetic Algorithms in Search , 1989 .

[4] Lawrence J. Fogel,et al. Artificial Intelligence through Simulated Evolution , 1966 .

[5] K. Dautenhahn,et al. Trying to imitate-a step towards releasing robots from social isolation , 1994, Proceedings of PerAc '94. From Perception to Action.

[6] H. P. Schwefel,et al. Numerische Optimierung von Computermodellen mittels der Evo-lutionsstrategie , 1977 .

[7] Vidroha Debroy,et al. Genetic Programming , 1998, Lecture Notes in Computer Science.

[8] Ingo Rechenberg,et al. Evolutionsstrategie : Optimierung technischer Systeme nach Prinzipien der biologischen Evolution , 1973 .

[9] Stewart W. Wilson. The animat path to AI , 1991 .

[10] Andreas Birk. Robotic Control via Stimulus Response Learning , 1996 .

[11] Luc Steels,et al. Cooperation between distributed agents through self-organisation , 1990, EEE International Workshop on Intelligent Robots and Systems, Towards a New Frontier of Applications.

[12] David E. Goldberg,et al. Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[13] Luc Steels,et al. The "Artificial Life" Route to "Artificial Intelligence": Building Situated Embodied Agents , 1995 .

[14] Luc Steels,et al. A selectionist mechanism for autonomous behavior acquisition , 1997, Robotics Auton. Syst..