Evolving robot sub-behaviour modules using Gene Expression Programming

详细信息    查看全文

• 作者：Jonathan Mwaura (1)
  Ed Keedwell (2)
  
  1. Department of Computer Science ; University of Pretoria ; Pretoria ; South Africa
  2. College of Engineering ; Mathematics and Physical Sciences ; University of Exeter ; Exeter ; UK
  
• 关键词：Gene Expression Programming ; Subsumption architecture ; Layered learning ; Evolutionary robotics ; Robot behaviour coordination
• 刊名：Genetic Programming and Evolvable Machines
• 出版年：2015
• 出版时间：June 2015
• 年：2015
• 卷：16
• 期：2
• 页码：95-131
• 全文大小：2,709 KB
• 参考文献：1. D. Bajaj, H.A. Marcelo, An Incremental Approach in Evolving Robot Behaviour. In / Proceedings of the Sixth International Conference on control, Automation, Robotics and Vision. IEEE, (2000)
  2. M. Botros. Evolving complex robotic behaviors using genetic programming. In / Genetic Systems Programming, Volume 13 of Studies in Computational Intelligence, eds. by A. Abraham, N. Nedjah, L. de Macedo Mourelle, (Springer, Berlin, 2006), pp. 173鈥?91
  3. Brooks, RA (1986) A robust layered control system for a mobile robot. IEEE J. Robot. Autom. 2: pp. 14-23 CrossRef
  4. A. Cangelosi, J.L. Elman, Gene Regulation and Biological Development in Neural Networks: an Exploratory Model. Technical report, Institute of Psychology, CNR, Viale Marx 15, Rome (1995)
  5. Cherubini, A, Giannone, F, Iocchi, L Layered learning for a Soccer legged robot helped with a 3d simulator. In: Visser, U, Ribeiro, F, Ohashi, T, Dellaert, F eds. (2008) RoboCup 2007: Robot Soccer World Cup XI. Springer, Berlin, pp. 385-392 CrossRef
  6. S. Clancy, W. Brown, Translation: DNA to mRNA to protein. Nat. Educ. 1(1), 101 (2008)
  7. Darwen, PJ, Xin, Yao (1997) Speciation as automatic categorical modularization. Trans. Evol. Comput. 1: pp. 101-108 CrossRef
  8. Jong, H (2002) Modelling and simulation of genetic regulatory systems: a literature review. J. Comput. Biol. 9: pp. 67-103 CrossRef
  9. S. Doncieux, J.-B. Mouret, N. Bredeche. Exploring new horizons in evolutionary design of robots. In Workshop on Exploring new horizons in evolutionary design of robots at IROS 2009, (Saint Louis, United States 2009), pp. 5鈥?2
  10. P. D眉rr, C. Mattiussi, D. Floreano, Neuroevolution with analog genetic encoding. In / Proceedings of the 9th International Conference on Parallel Problem Solving from Nature, vol. 6856 of Lecture Notes in Computer Science, (Springer, Berlin 2006), pp. 671鈥?80.
  11. D眉rr, P, Mattiussi, F, Floreano, D (2010) Genetic representation and evolvability of modular neural controllers. IEEE Comput. Int. Mag. 5: pp. 10-19 CrossRef
  12. Ferreira, C (2001) Gene expression programming: a new adaptive algorithm for solving problems. J. Complex Syst. 13: pp. 87-129
  13. Ferreira, C (2006) Gene Expression Programming: mathematical Modelling by an Artificial Intelligence. Springer, Berlin
  14. D. Floreano, L. Keller, Evolution of adaptive behaviour in robots by means of Darwinian selection. J. PLoS Biol. 8(1), e1000292 (2010)
  15. D. Floreano, F. Mondada, Automatic Creation of an Autonomous Agent: genetic Evolution of a Neural-Network Driven Robot. In / Proceedings of the 3rd International Conference on Simulation of Adaptive Behavior (MIT Press-Bradford Books, Cambridge, 1994)
  16. D. Floreano, F. Mondada, Evolution of Plastic Neurocontrollers for Situated Agents. In From Animals to Animats 4, eds. by P. Maes, M. Mataric, J.-A. Meyer, J. Pollack, S. Wilson, in / Proceedings of the 4th International Conference on Simulation of Adaptive Behavior (SAB鈥?996), (MIT Press, MA, 1996), pp. 402鈥?10
  17. F. Gomez, R. Miikulainen, Incremental evolution of complex general behaviour. Technical report, Technical report AI96-248, (Austin, TX: University of Texas at Austin, 1996)
  18. Griffiths, AJF, Miller, JH, Suzuki, DT, Lewontin, RC, Gelbart, WM (2000) An Introduction to Genetic Analysis. W. H. Freeman, New York
  19. D. Gu, H. Hu, Evolving fuzzy logic controllers for Sony legged robots. In A. Birk, S. Coradeschi, S. Tadokoro, editors, / RoboCup 2001, LNAI 2377, (Springer Berlin Heidelberg, 2002), pp. 356鈥?61.
  20. D. Gu, H. Hu, J. Reynolds, E. Tsang. GA-based learning in behaviour based robotics. In / Proceedings of the IEEE International Symposium on Computational Intelligence in Robotics and Automation, pp. 16鈥?0, (2003)
  21. I. Harvey, P. Husbands, D. Cliff, Issues in Evolutionary Robotics. In / Proceedings of the 3rd International Conference on Simulation of Adaptive Behavior, vol 2, eds. by J.-A. Meyer, H. Roitblat, S. Wilson, pp. 73鈥?10, (1993)
  22. Harvey, I, Husbands, P, Cliff, D, Thompson, A, Jakobi, N (1997) Evolutionary robotics: the Sussex approach. J. Robot. Auton. Syst. 20: pp. 205-224 CrossRef
  23. L. Hugues, N. Bredeche, A quick programming guide for Simbad simulator. URL http://simbad.sourceforge.net/guide.php. August (2005)
  24. Jacobs, RA, Jordan, MI (1994) Hierarchical mixtures of experts and the EM algorithm. Neural Comput. 6: pp. 181-214 CrossRef
  25. R.A. Jacobs, M.I. Jordan, A.G. Barto, Task decomposition through competition in a modular connectionist architecture: the what and where vision tasks. / Cogn. / Sci. 15, 219鈥?50 (1991)
  26. S. Kent, Evolutionary approaches to robot path planning. PhD thesis, Brunel University, (1999)
  27. Koza, JR (1992) Genetic Programming: on the Programming of Computers by Means of Natural Selection. MIT Press, Cambridge
  28. J.R. Koza, Evolution of aubsumption using genetic programming. In P. Bourgine F.J. Varela, ed. / Proceedings of the 1st European Conference on Artificial Life: Towards a Practice of Autonomous Systems, pp. 110鈥?19, (1993)
  29. C. Lazarus, H. Hu, Using genetic programming to evolve robot behaviours. In / Proceedings of the 3rd British Conference on Autonomous Mobile Robotics and Autonomous Systems, (2001)
  30. C. Lazarus, H. Hu, Evolving goalkeeper behaviours for simulated Soccer competition. In / Proceedings of the 3rd IASTED International Conference on Artificial Intelligence and Applications, (2003)
  31. Lee, W-P (1999) Evolving complex robot behaviors. J. Inf. Sci. 121: pp. 1-25 CrossRef
  32. Y. Liu, X. Yao, T. Higuchi, / Evolutionary ensembles with negative correlation learning. / IEEE Trans. / Evol. / Comput. 4(4), 380鈥?87 (2000)
  33. MacNeil, LT, Walhout, AJM (2011) Gene regulatory networks and the role of robustness and stochasticity in the control of gene expression. Genome Res. 21: pp. 645-657 CrossRef
  34. M.J. Mataric, / A Distributed Model for Mobile Robot Environment-Learning and Navigation. Technical report, Massachusetts Institute of Technology, (Cambridge, MA, USA, 1990)
  35. M.J. Mataric, Learning in behaviour-based multi-robot systems: policies, models, and other agents. J. Cogn. Syst. Res. 2, 81鈥?3 (2001)
  36. C. Mattiussi, D. Floreano, Evolution of analog networks using local string alignment on highly reorganizable genomes. In / Proceedings of the 2004 NASA/DoD Conference on Evolution Hardware, (IEEE Computer Society, 2004), pp. 30鈥?7
  37. Mattiussi, C, Floreano, D (2007) Analog genetic encoding for the evolution of circuits and networks. IEEE Trans. Evol. Comput. 11: pp. 596-607 CrossRef
  38. C. Mautner, R.K. Belew, Evolving robot morphology and control. In / Proceedings of the Artificial Life and Robotics (AROB), (1999)
  39. J.-B. Mouret, S. Doncieux, Overcoming the bootstrap problem in evolutionary robotics using behavioral diversity. In / Proceedings of the IEEE Congress on Evolutionary Computation鈥?9, pp. 1161鈥?168, (2009)
  40. Murphy, RR (2000) Introduction to AI Robotics. MIT Press, Cambridge
  41. J. Mwaura, Evolution of robotic behaviours using gene expression programming. PhD thesis, University of Exeter, Exeter, UK, (2011)
  42. J. Mwaura, E. Keedwell, / Adaptive Gene Expression Programming Using a Simple Feedback Heuristic. In / Proceedings of the AISB (Edinburgh, UK, 2009)
  43. J. Mwaura, E. Keedwell, Evolution of robotic behaviours using gene expression programming. In / Proceedings of the IEEE Congress on Evolutionary Computation (CEC2010), (Barcelona, Spain, 2010), pp. 1鈥?
  44. J. Mwaura, E. Keedwell, Evolving modularity in robot behaviour using gene expression programming, in / Towards Autonomous Robotic Systems鈥?2th Annual Conference, (TAROS 2011), August 31鈥揝eptember 2, vol. 6856 of Lecture Notes in Computer Science, ed. by R. Gross, L. Alboul, C. Melhuish, M. Witkowski, T.J. Prescott, J. Penders (Springer, Sheffield, UK, 2011), pp. 392鈥?93
  45. Nelson, AL, Grant, E, Galeotti, JM, Rhody, S (2004) Maze exploration behaviours using an integrated evolutionary robotics environment. J. Robot. Auton. Syst. 46: pp. 159-173 CrossRef
  46. A.L. Nelson, E. Grant, Developmental analysis in evolutionary robotics. In / Proceedings of the 2006 IEEE SMC Mountain Workshop on Adaptive and Learning Systems (SMCals06), pp. 201鈥?06, (2006)
  47. Nolfi, S (1998) Evolutionary robotics: exploiting the full power of self organization. J. Connect. Sci. 10: pp. 167-183 CrossRef
  48. Nolfi, S (2006) Behaviour as a complex adaptive system: on the role of self-organization in the development of individual and collective behaviour. J. ComplexUs 2: pp. 195-203
  49. Nolfi, S, Floreano, D (2000) Evolutionary Robotics. The Biology, Intelligence, and Technology of Self-organizing Machines. MIT Press, Cambridge
  50. Nordin, P, Banzhaf, W (1997) Real time control of a Khepera robot using genetic programming. J. Cybern. Control 26: pp. 533-561
  51. Prescott, TJ, Redgrave, P, Gurney, K (1999) Layered control architectures in robots and vertebrates. J. Adapt. Behav. 7: pp. 99-127 CrossRef
  52. T. Reil, Dynamics of Gene Expression in an Artificial Genome鈥攊mplications for Biological and Artificial Ontogeny. In / Proceedings of the 5th European Conference on Advances in Artificial Life, ECAL 鈥?9, (Springer, 1999), pp. 457鈥?66
  53. Reil, T Artificial genomes as models of gene regulation. In: Kumar, S, Bentley, PJ eds. (2003) On Growth, Form and Computers. Elsevier, Amsterdam
  54. T. Thompson, J. Levine, Scaling-up behaviours in evotanks: applying subsumption principles to artificial neural networks. In / Proceedings of the IEEE Symposium on Computational Intelligence and Games, (2008)
  55. Togelius, J (2004) Evolution of a subsumption architecture neurocontroller. J. Intell. Fuzzy Syst. 15: pp. 15-20
  56. J. Urzelai, D. Floreano, Incremental evolution with minimal resources. In / Proceedings of the International KHEPERA Workshop, (1999)
  57. Urzelai, J, Floreano, D (2001) Evolution of adaptive synapses: robots with fast adaptive behaviour in new environments. J. Evol. Comput. 9: pp. 495-524 CrossRef
  58. M. Wahde, Evolution robotics: the use of artificial evolution in robotics, a tutorial. In / Proceedings of the IEEE/ESJ International Conference on Intelligent Robots and Systems, (2004)
  
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Software Engineering, Programming and Operating Systems
  Electronic and Computer Engineering
  Programming Techniques
  Programming Languages, Compilers and Interpreters
  
• 出版者：Springer Netherlands
• ISSN：1573-7632

文摘

Many approaches to AI in robotics use a multi-layered approach to determine levels of behaviour from basic operations to goal-directed behaviour, the most well-known of which is the subsumption architecture. In this paper, the performances of the unigenic Gene Expression Programming (ugGEP) and multigenic GEP (mgGEP) in evolving robot controllers for a wall following robot are analysed. Additionally, the paper introduces Regulatory Multigenic Gene Expression Programming, a new evolutionary technique that can be utilised to automatically evolve modularity in robot behaviour. The proposed technique extends the mgGEP algorithm, by incorporating a regulatory gene as part of the GEP chromosome. The regulatory gene, just as in systems biology, determines which of the genes in the chromosome to express and therefore how the controller solves the problem. In the initial experiments, the proposed algorithm is implemented for a robot wall following problem and the results compared to that of ugGEP and mgGEP. In addition to the wall following behaviour, a robot foraging behaviour is implemented with the aim of investigating whether the position of a specific module (sub-expression tree) in the overall expression tree is of importance when coding for a problem.