Noise and the Reality Gap: The Use of Simulation in Evolutionary Robotics

The pitfalls of naive robot simulations have been recognised for areas such as evolutionary robotics. It has been suggested that carefully validated simulations with a proper treatment of noise may overcome these problems. This paper reports the results of experiments intended to test some of these claims. A simulation was constructed of a two-wheeled Khepera robot with IR and ambient light sensors. This included detailed mathematical models of the robot-environment interaction dynamics with empirically determined parameters. Artificial evolution was used to develop recurrent dynamical network controllers for the simulated robot, for obstacle-avoidance and light-seeking tasks, using different levels of noise in the simulation. The evolved controllers were down-loaded onto the real robot and the correspondence between behaviour in simulation and in reality was tested. The level of correspondence varied according to how much noise was used in the simulation, with very good results achieved when realistic quantities were applied. It has been demonstrated that it is possible to develop successful robot controllers in simulation that generate almost identical behaviours in reality, at least for a particular class of robot-environment interaction dynamics.

[1]  O. Jacobs,et al.  Introduction to Control Theory , 1976, IEEE Transactions on Systems, Man, and Cybernetics.

[2]  Roman Kuchkuda,et al.  An introduction to ray tracing , 1993, Comput. Graph..

[3]  Andrew S. Glassner,et al.  An introduction to ray tracing , 1989 .

[4]  R. A. Brooks,et al.  Intelligence without Representation , 1991, Artif. Intell..

[5]  David R. Jefferson,et al.  Selection in Massively Parallel Genetic Algorithms , 1991, ICGA.

[6]  Rodney A. Brooks,et al.  Intelligence Without Reason , 1991, IJCAI.

[7]  Inman Harvey,et al.  Evolution Versus Design: Controlling Autonomous Robots , 1992, Proceedings of the Third Annual Conference of AI, Simulation, and Planning in High Autonomy Systems 'Integrating Perception, Planning and Action'..

[8]  Rodney A. Brooks,et al.  Artificial Life and Real Robots , 1992 .

[9]  F. Mondada,et al.  Modeling system-environment interaction: the complimentary roles of simulation and real world artifacts , 1993 .

[10]  Francesco Mondada,et al.  Automatic creation of an autonomous agent: genetic evolution of a neural-network driven robot , 1994 .

[11]  Tim Smithers,et al.  On why better robots make it harder , 1994 .

[12]  Randall D. Beer,et al.  Integrating reactive, sequential, and learning behavior using dynamical neural networks , 1994 .

[13]  Stefano Nolfi,et al.  How to Evolve Autonomous Robots: Different Approaches in Evolutionary Robotics , 1994 .

[14]  Charles E. Taylor,et al.  Selection for Wandering Behavior in a Small Robot , 1994, Artificial Life.

[15]  Inman Harvey,et al.  Seeing the light: artificial evolution, real vision , 1994 .

[16]  Adrian Thompson,et al.  Evolving Electronic Robot Controller that Exploit Hardware Resources , 1995, ECAL.