论文信息 - Use of context blocks in genetic programming for evolution of robot morphology

Use of context blocks in genetic programming for evolution of robot morphology

The paper explores application of genetic programming to evolution of robot morphology, and co-evolution of morphology and low-level control. Extensions to standard genetic programming are presented that allow for straight-forward storage, retrieval, transfer, modification of data stored in the context of a syntactic tree, and shared by multiple nodes. These extensions are used to embed a genetic algorithm within the genetic programming approach to evolve values of constants. Experimental results are presented and evaluated.

[1] Karl Sims,et al. Evolving 3d morphology and behavior by competition , 1994 .

[2] Matthew P. Evett,et al. Numeric Mutation Improves the Discovery of Numeric Constants in Genetic Programming , 2007 .

[3] Henrik Hautop Lund,et al. Co-evolving Control and Morphology with LEGO Robots , 2003 .

[4] Daniel T. Larose,et al. Data Mining Methods and Models: Larose/Data Mining Methods and Models , 2005 .

[5] Gregory S. Hornby,et al. Body-brain co-evolution using L-systems as a generative encoding , 2001 .

[6] Jordan B. Pollack,et al. TITLE : Generative Representations for the Automated Design of Modular Physical Robots , 2003 .

[7] A. Topchy,et al. Faster genetic programming based on local gradient search of numeric leaf values , 2001 .

[8] Juraj Spalek,et al. On use of node-attached modules with ancestry tracking in genetic programming , 2012, PDeS.

[9] Daniel Marbach,et al. Co-evolution of Configuration and Control for Homogenous Modular Robots , 2004 .