On the relationship between environmental and morphological complexity in evolved robots

Auerbach, Joshua E.; Bongard, Josh

doi:10.1145/2330163.2330238

Cited by 44 publications

(66 citation statements)

References 31 publications

(41 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Including knowledge can be completely misleading [106], and must therefore be handled with care. When properly done, the gain may be significant [19,17,18,4,5,146,147], but more and more task agnostic methods have been proposed that also have a significant impact on ER efficiency [79,72,103,131,177,106]. These new techniques are very encouraging and allows us to think about a future with a truly automated behavior design method.…”

Section: Conclusion and Discussionmentioning

confidence: 99%

Beyond black-box optimization: a review of selective pressures for evolutionary robotics

Doncieux

Mouret

2014

Evol. Intel.

View full text Add to dashboard Cite

Evolutionary robotics is often viewed as the application of a family of black-box optimization algorithms -evolutionary algorithms -to the design of robots, or parts of robots. When considering evolutionary robotics as black-box optimization, the selective pressure is mainly driven by a user-defined, black-box fitness function, and a domain-independent selection procedure. However, most evolutionary robotics experiments face similar challenges in similar setups: the selective pressure, and, in particular, the fitness function, is not a pure user-defined black box. The present review shows that, because evolutionary robotics experiments share common features, selective pressures for evolutionary robotics are a subject of research on their own. The literature has been split into two categories: goal refiners, aimed at changing the definition of a good solution, and process helpers, designed to help the search process. Two subcategories are further considered: task-specific approaches, which require knowledge on how to solve the task and taskagnostic ones, which do not need it. Besides highlighting the diversity of the approaches and their respective goals, the present review shows that many task-agnostic process helpers have been proposed during the last years, thus bringing us closer to the goal of a fully automated robot behavior design process.

show abstract

Section: Conclusion and Discussionmentioning

confidence: 99%

Beyond black-box optimization: a review of selective pressures for evolutionary robotics

Doncieux

Mouret

2014

Evol. Intel.

View full text Add to dashboard Cite

show abstract

“…As researchers in these areas, we hope to reproduce or one day exceed natural evolution's most inspiring qualities, for example through open-ended evolution (Channon, 2001;Maley, 1999) or evolving a diverse collection of virtual morphologies (Auerbach and Bongard, 2012;Hornby and Pollack, 2002;Lehman and Stanley, 2011;Sims, 1994;Szerlip and Stanley, 2013). However, almost all EC and ALife experiments fall short on one very salient feature of natural evolution: that it effectively never ends.…”

Section: Introductionmentioning

confidence: 99%

Steps Toward a Modular Library for Turning Any Evolutionary Domain into an Online Interactive Platform

Szerlip

Stanley

2014

Artificial Life 14: Proceedings of the Fourteenth International Conference on the Synthesis and Simulation of Living Systems

View full text Add to dashboard Cite

Natural evolution inspires the fields of evolutionary computation (EC) and artificial life (ALife). A prominent feature of natural evolution is that it effectively never ends. However, most EC and ALife experiments are only run for several days or weeks at a time. Once an experiment concludes, reproducing, observing, or extending the results often requires considerable effort. In contrast, some Collaborative Interactive Evolution (CIE) systems, e.g. Picbreeder, were designed to preserve results as potential stepping stones to build upon later while taking advantage of human insight to solve challenging problems. Traditionally, building long-running and open experiments similar to Picbreeder presents a complex and timeconsuming software challenge. To reduce this challenge and thereby remove the barrier to situating almost any experiment within an interactive online framework, this paper presents the initial prototype for Worldwide Infrastructure for Neuroevolution (WIN). Built in the model of Picbreeder, WIN is a modular library for significantly reducing the complexity of creating fully persistent, online, and interactive evolutionary platforms for any new or existing domain. WIN Online, the public interface for WIN, provides an online collection of domains built with WIN that lets novice and expert users browse and meaningfully contribute to ongoing experiments. Two example experiments in this paper demonstrate WIN's potential to quickly bootstrap any evolutionary domain with online and interactive capabilities.

show abstract

“…One can investigate the relationship between control and morphology, as was done by Paul (Paul, 2006), and one can also study the relationship between task environment and morphology which is less well understood. In recent work (Auerbach and Bongard, 2012) we began to investigate this latter relationship by studying how the shape complexity of robot body parts varied when robots were evolved in more or less complex task environments. Here, that work is extended by studying a different aspect of morphological complexity: mechanical complexity, a function of the mechanical degrees of freedom of evolved robots.…”

Section: Introductionmentioning

confidence: 99%

“…Following the methods introduced in (Auerbach and Bongard, 2012), here robots are evolved not only to locomote over flat terrain, but to locomote in a number of more complex, icy task environments as well. However, while in that study robots were restricted to having two mechanical degrees of freedom, here robots are allowed more flexibility in their construction including the ability to utilize a greater number of degrees of freedom.…”

Section: Introductionmentioning

confidence: 99%

“…Here we define mechanical complexity to be the number of mechanical degrees of freedom in an evolved robot. This form of complexity can be considered an aspect of morphological complexity, but as will be shown, mechanical complexity is an orthogonal direction of complexity to the type of morphological complexity discussed in (Auerbach and Bongard, 2012), and provides additional insight into the relationship between task environments and the robots evolved inside them.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

On the Relationship Between Environmental and Mechanical Complexity in Evolved Robots

Auerbach

Bongard²

2012

Artificial Life 13

View full text Add to dashboard Cite

According to the principles of embodied cognition, intelligent behavior must arise out of the coupled dynamics of an agent's brain, body, and environment. This suggests that the morphological complexity of a robot should scale in relation to the complexity of its task environment. This idea is supported by recent work, which demonstrated that when evolving robot morphologies in simple and complex task environments more complex robot morphologies do tend to evolve in more complex task environments. Here this idea is extended to examining the mechanical complexity of evolved robots. Counter to intuition it is found that the mechanical complexity decreases in more complex task environments.

show abstract

On the relationship between environmental and morphological complexity in evolved robots

Cited by 44 publications

References 31 publications

Beyond black-box optimization: a review of selective pressures for evolutionary robotics

Beyond black-box optimization: a review of selective pressures for evolutionary robotics

Steps Toward a Modular Library for Turning Any Evolutionary Domain into an Online Interactive Platform

On the Relationship Between Environmental and Mechanical Complexity in Evolved Robots

Contact Info

Product

Resources

About