Sticky Feet - Evolution in a Multi-Creature Physical Simulation

نویسنده

  • Greg Turk
چکیده

We demonstrate artificial evolution in a system that combines physical simulation with competition between creatures. The simulated creatures are constructed using point masses that are connected by oscillating springs. The creatures pull themselves across their 2D environment by varying the amount of friction at different point masses, giving them sticky feet. Creatures combat one another, and the victor of such an encounter earns the right to reproduce, possibly with mutation. Rather than testing one individual against another in pairs, as many as 100 creatures move and interact with each other in the same 2D environment. Over time, the initial creatures are replaced by new creatures that are more agile and better at combating others. The evolved creatures from such simulations exhibit a wide array of body plans, locomotion styles, and interaction behaviors.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Energy as a driver of diversity in open-ended evolution

We investigate the consequences of introducing an energy model into open ended evolutionary simulations. We propose a metamodel for simulations that incorporate an energy model and apply that model by extending Turk’s Sticky Feet model. We show that introducing an energy model produces simulations with measurably increased diversity of the simulated population.

متن کامل

Virtual fluid environment on behavior ability for artificial creature

An environment plays an important role in behaviors acquisition for artificial creatures. Thus, the environment must obey the physical laws. In this paper, it is examined how the behavior differences appear when the artificial creature autonomously behaves in some fluid environments. We construct the approximate virtual fluid environment with low computing costs to simulate the behavior acquisi...

متن کامل

Coordination and Synchronization of Locomotion in a Virtual Robot

This paper investigates the use of a multi-objective approach for evolving artificial neural networks that act as controllers for the legged locomotion of a 3-dimensional, artificial quadruped creature simulated in a physics-based environment. The Pareto-frontier Differential Evolution (PDE) algorithm is used to generate a pareto optimal set of artificial neural networks that optimizes the conf...

متن کامل

Trading-off Mind Complexity and Locomotion in a Physically Simulated Quadruped

This paper investigates the use of a multi-objective approach for evolving artificial neural networks that act as controllers for the legged locomotion of a 3-dimensional, artificial quadruped creature simulated in a physics-based environment. The Pareto-frontier Differential Evolution (PDE) algorithm is used to generate a pareto optimal set of artificial neural networks that optimizes the conf...

متن کامل

Trading-off Mind Complexity and Locomotion in Virtually Embodied Quadruped Robot

This paper investigates the use of a multi-objective approach for evolving artificial neural networks that act as controllers for the legged locomotion of a 3-dimensional, artificial quadruped creature simulated in a physics-based environment. The Paretofrontier Differential Evolution (PDE) algorithm is used to generate a pareto optimal set of artificial neural networks that optimizes the confl...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2010