Real-World Reproduction of Evolved Robot Morphologies: Automated Categorization and Evaluation

Samuelsen, Eivind; Glette, Kyrre

doi:10.1007/978-3-319-16549-3_62

Cited by 17 publications

(19 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lipson and Pollack ( 2000 ) first demonstrated that this approach is also applicable in systems where the final (i.e., after evolution has run its course) results are realized and evaluated as actual physical robots, with substantial research revisiting this approach. For example, generative encodings have been explored and resulted in physically instantiated robots in Hornby et al ( 2003 ) and Samuelsen and Glette ( 2015 ), resulting in regular, symmetrical, and insect-like bodies and behaviors. Moreover, robot shapes have been optimized in Clark et al ( 2012 ) and Corucci et al ( 2015 ), resulting in dynamic body-brain behavior for aquatic robots.…”

Section: Related Workmentioning

confidence: 99%

Lamarckian Evolution of Simulated Modular Robots

et al. 2019

Self Cite

View full text Add to dashboard Cite

We study evolutionary robot systems where not only the robot brains but also the robot bodies are evolvable. Such systems need to include a learning period right after 'birth' to acquire a controller that fits the newly created body. In this paper we investigate the possibility of bootstrapping infant robot learning through employing Lamarckian inheritance of parental controllers. In our system controllers are encoded by a combination of a morphology dependent component, a Central Pattern Generator (CPG), and a morphology independent part, a Compositional Pattern Producing Network (CPPN). This makes it possible to transfer the CPPN part of controllers between different morphologies and to create a Lamarckian system. We conduct experiments with simulated modular robots whose fitness is determined by the speed of locomotion, establish the benefits of inheriting optimized parental controllers, shed light on the conditions that influence these benefits, and observe that changing the way controllers are evolved also impacts the evolved morphologies.

show abstract

Section: Related Workmentioning

confidence: 99%

Lamarckian Evolution of Simulated Modular Robots

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…Finally, the combined morphology-controller robots are prone to reality gap issues, potentially even more so than when control systems only are evolved. In particular, it seems to often be the case that some morphology-controller combinations work relatively as expected from simulation, while other combinations suffer from a large reality gap [3,6,7].…”

Section: Introductionmentioning

confidence: 97%

“…Most examples of the potential of co-evolution of morphologies and controllers are found within the field of virtual creatures, where a physical counterpart of the simulated system may not be available [4,5]. However, there have also been some examples of evolution in simulation leading to instantiation of working physical robots [3,6,7], and recently even simulationless evolution of robotic morphologies [8].…”

Section: Introductionmentioning

confidence: 99%

“…Experiments on evolving morphologies and controllers employ a variety of different building blocks, from convenient physics simulation primitives in the case of virtual creatures [4,13], to building blocks which are convenient to prototype and integrate with actuators in the case of physical instantiation [3,6,16,7]. In these cases, focus has been more on the evolutionary design process, and the resulting physical robots are mostly meant to validate the approach.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Overcoming Initial Convergence in Multi-objective Evolution of Robot Control and Morphology Using a Two-Phase Approach

Nygaard

Samuelsen

Glette

2017

Applications of Evolutionary Computation

Self Cite

View full text Add to dashboard Cite

Co-evolution of robot morphologies and control systems is a new and interesting approach for robotic design. However, the increased size and ruggedness of the search space becomes a challenge, often leading to early convergence with sub-optimal morphology-controller combinations. Further, mutations in the robot morphologies tend to cause large perturbations in the search, effectively changing the environment, from the controller's perspective. In this paper, we present a two-stage approach to tackle the early convergence in morphology-controller coevolution. In the first phase, we allow free evolution of morphologies and controllers simultaneously, while in the second phase we re-evolve the controllers while locking the morphology. The feasibility of the approach is demonstrated in physics simulations, and later verified on three different real-world instances of the robot morphologies. The results demonstrate that by introducing the two-phase approach, the search produces solutions which outperform the single co-evolutionary run by over 10%.

show abstract

“…The same evaluation procedure was used to compare the performance of the simulated robots and the performance of the physical robots. Five robots were manufactured and three out of five robots have significantly lower performance in reality [63].…”

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

Real-World Reproduction of Evolved Robot Morphologies: Automated Categorization and Evaluation

Cited by 17 publications

References 14 publications

Lamarckian Evolution of Simulated Modular Robots

Lamarckian Evolution of Simulated Modular Robots

Overcoming Initial Convergence in Multi-objective Evolution of Robot Control and Morphology Using a Two-Phase Approach

Evolutionary Modular Robotics: Survey and Analysis

Contact Info

Product

Resources

About