A bottom-up mechanism for behavior selection in an artificial creature
Proceedings of the first international conference on simulation of adaptive behavior on From animals to animats
Adaptation in natural and artificial systems
Adaptation in natural and artificial systems
Planning motions with intentions
SIGGRAPH '94 Proceedings of the 21st annual conference on Computer graphics and interactive techniques
Artificial life meets entertainment: lifelike autonomous agents
Communications of the ACM
Further experience with controller-based automatic motion synthesis for articulated figures
ACM Transactions on Graphics (TOG)
A geometric modeling and animation system for virtual reality
Communications of the ACM
Genetic algorithms + data structures = evolution programs (3rd ed.)
Genetic algorithms + data structures = evolution programs (3rd ed.)
Evolution and Optimum Seeking: The Sixth Generation
Evolution and Optimum Seeking: The Sixth Generation
Genetic Algorithms in Search, Optimization and Machine Learning
Genetic Algorithms in Search, Optimization and Machine Learning
Intelligence Without Reason
Building Brains for Bodies
A Robot That Walks; Emergent Behaviors from a Carefully Evolved Network
A Robot That Walks; Emergent Behaviors from a Carefully Evolved Network
Modeling adaptive autonomous agents
Artificial Life
Behavioral Self-Organization in Lifelike Synthetic Agents
Autonomous Agents and Multi-Agent Systems
Hi-index | 0.00 |
One of the important characteristics of an autonomous robot lies in the capability of self-organizing its own behaviors in order to adapt to an unknown environment. The goal of this paper is to present an effective means for investigating such a capability, which enables us to graphically build a model of the autonomous robot and dynamically observe the emergence of reactive behaviors as a result of external stimulus controlled behavioral self-organization. In particular, the paper describes an integrated software workbench, called C4 (which stands for Create, Coordinate, Condition, and Co-evolve), for modeling and simulating autonomous robotic systems, e.g., legged and dual-arm ones. The module create enables us to build top-down graphical models of novel mechanisms, followed by primitive motion pattern (e.g., gaits) specification and visualization in the coordinate module. Learning mechanisms, as embedded in module condition further allow us to test how the animated robots acquire new behavioral rules triggerable by external stimuli. Finally, the module co-evolve facilitates the analysis of the distributed intelligence of robot groups, which manifests itself from the behaviors emergent from the interaction among individual robots.