RoboGen: Robot Generation through Artificial Evolution

Auerbach, Joshua E.; Aydin, Deniz; Maesani, Andrea; Kornatowski, Przemyslaw; Cieslewski, Titus; Heitz, G.; Fernando, Pradeep; Loshchilov, Ilya; Daler, Ludovic; Floreano, Dario

doi:10.7551/978-0-262-32621-6-ch022

Cited by 78 publications

(103 citation statements)

References 9 publications

Supporting

Mentioning

100

Contrasting

Order By: Relevance

“…Recently [1], we introduced the RoboGen TM open-source software and hardware platform for Evolutionary Robotics 1 , and described its success as an educational tool in a masters level course at EPFL. There it was shown that RoboGen could provide students with valuable hands on experience with Evolutionary Robotics, neural networks, physical simulation, 3D printing, mechanical assembly, and embedded processing.…”

Section: Extended Abstractmentioning

confidence: 99%

Rapid Evolution of Robot Gaits

Auerbach

Heitz

Kornatowski

et al. 2015

Proceedings of the Companion Publication of the 2015 Annual Conference on Genetic and Evolutionary Computation

Self Cite

View full text Add to dashboard Cite

EXTENDED ABSTRACTThe promise of Evolutionary Robotics (ER) [7] to completely automatize the design of robot controllers and/or morphologies is an idea with great appeal not only to researchers, but also to students. Recently [1], we introduced the RoboGen TM open-source software and hardware platform for Evolutionary Robotics 1 , and described its success as an educational tool in a masters level course at EPFL. There it was shown that RoboGen could provide students with valuable hands on experience with Evolutionary Robotics, neural networks, physical simulation, 3D printing, mechanical assembly, and embedded processing.However, when attempting to grab and hold student interest, the large requirements of time and computational resources required to achieve good results in ER systems may be discouraging. In fact, after two years of using RoboGen for class projects, the biggest student complaints all concerned the slow speed of evolutionary progress. In order to overcome these limitations, we present here a simple and effective technique for rapidly evolving robot gaits in a manner of seconds or minutes rather than hours or days. Moreover, through a previously executed, iterative procedure of tuning the simulator and the embedded processing of RoboGen robots, many of these evolved gaits can transfer to real robots with reasonable fidelity without requiring hardwarein-the-loop fitness evaluations [4,12] or online simulator updates [2].While there are several existing techniques for evolving natural looking and successful robot gaits [3,6,10], most 1

show abstract

Section: Extended Abstractmentioning

confidence: 99%

Rapid Evolution of Robot Gaits

Auerbach

Heitz

Kornatowski

et al. 2015

Proceedings of the Companion Publication of the 2015 Annual Conference on Genetic and Evolutionary Computation

Self Cite

View full text Add to dashboard Cite

show abstract

“…Then, the evolved robots can be manufactured using desktop 3Dprinters; as illustrated in Fig. 4 [62].…”

Section: Current State Of the Artmentioning

confidence: 99%

“…The proposed method has an improved crossover operator and a new fitness function. The Improved Same Adjacency (ISA) crossover operator takes into [62] consideration variable length chromosomes to allow rapid convergence and avoid premature convergence. The new fitness function is defined based on the path length, safety, and mobile robotic energy consumption.…”

Section: Current State Of the Artmentioning

confidence: 99%

Evolutionary Modular Robotics: Survey and Analysis

Alattas

Patel

Sobh

2018

J Intell Robot Syst

View full text Add to dashboard Cite

This paper surveys various applications of artificial evolution in the field of modular robots. Evolutionary robotics aims to design autonomous adaptive robots automatically that can evolve to accomplish a specific task while adapting to environmental changes. A number of studies have demonstrated the feasibility of evolutionary algorithms for generating robotic control and morphology. However, a huge challenge faced was how to manufacture these robots. Therefore, modular robots were employed to simplify robotic evolution and their implementation in real hardware. Consequently, more research work has emerged on using evolutionary computation to design modular robots rather than using traditional hand design approaches in order to avoid cognition bias. These techniques have the potential of developing adaptive robots that can achieve tasks not fully understood by human designers. Furthermore, evolutionary algorithms were studied to generate global modular robotic behaviors including; self-assembly, self-reconfiguration, self-repair, and self-reproduction. These characteristics allow modular robots to explore unstructured and hazardous environments. In order to accomplish the aforementioned evolutionary modular robotic promises, this paper reviews current research on evolutionary robotics and modular robots. The motivation behind this work is to identify the most promising methods that can lead to developing autonomous adaptive robotic systems that require the minimum task related knowledge on the designer side.

show abstract

“…In particular we chose the RoboGen TM Evolutionary Robotics platform [3] for experimentation, because it is open-source and has recently been ported to run inside a web browser. 18 All intervals/thresholds can be configured through a JSON file on the server.…”

Section: Robogen Tm Case-studymentioning

confidence: 99%

“…TM , an open-source platform for the co-evolution of robot bodies and brains [3]. Section 4 discusses the experimental results and highlights the key elements of the SPACE framework in comparison with alternative solutions from the literature.…”

Section: Introductionmentioning

confidence: 99%

The Seamless Peer and Cloud Evolution Framework

Leclerc

Auerbach

Iacca

et al. 2016

Proceedings of the Genetic and Evolutionary Computation Conference 2016

Self Cite

View full text Add to dashboard Cite

Evolutionary algorithms are increasingly being applied to problems that are too computationally expensive to run on a single personal computer due to costly fitness function evaluations and/or large numbers of fitness evaluations. Here, we introduce the Seamless Peer And Cloud Evolution (SPACE) framework, which leverages bleeding edge web technologies to allow the computational resources necessary for running large scale evolutionary experiments to be made available to amateur and professional researchers alike, in a scalable and cost-effective manner, directly from their web browsers. The SPACE framework accomplishes this by distributing fitness evaluations across a heterogeneous pool of cloud compute nodes and peer computers. As a proof of concept, this framework has been attached to the RoboGen TM open-source platform for the co-evolution of robot bodies and brains, but importantly the framework has been built in a modular fashion such that it can be easily coupled with other evolutionary computation systems.

show abstract

RoboGen: Robot Generation through Artificial Evolution

Cited by 78 publications

References 9 publications

Rapid Evolution of Robot Gaits

Rapid Evolution of Robot Gaits

Evolutionary Modular Robotics: Survey and Analysis

The Seamless Peer and Cloud Evolution Framework

Contact Info

Product

Resources

About