In Evolutionary Robotics, evolutionary algorithms are used to co-optimize morphology and control. However, co-optimizing leads to different challenges: How do you optimize a controller for a body that often changes its number of inputs and outputs? Researchers must then make some choice between centralized or decentralized control. In this article, we study the effects of centralized and decentralized controllers on modular robot performance and morphologies. This is done by implementing one centralized and two decentralized continuous time recurrent neural network controllers, as well as a sine wave controller for a baseline. We found that a decentralized approach that was more independent of morphology size performed significantly better than the other approaches. It also worked well in a larger variety of morphology sizes. In addition, we highlighted the difficulties of implementing centralized control for a changing morphology, and saw that our centralized controller struggled more with early convergence than the other approaches. Our findings indicate that duplicated decentralized networks are beneficial when evolving both the morphology and control of modular robots. Overall, if these findings translate to other robot systems, our results and issues encountered can help future researchers make a choice of control method when co-optimizing morphology and control.

A challenge in evolutionary robotics is the in parallel adaptation of morphologies and controllers. Here, we considered encoding methods for morphogenesis of 2D virtual creatures that can be created from directed trees. Using an evolutionary algorithm, we optimized locomotion in these virtual creatures and compared a direct encoding, an L-System, and two types of encodings that produce neural networks—a Compositional Pattern Producing Network (CPPN) and a Cellular Encoding (CE). We evaluated these encodings based on performance and diversification, and we introduced an OpenAI gym environment as a computationally inexpensive benchmark for exploring morphological evolution. The direct encoding and L-System generated more fit solutions compared to the network strategies. Considering morphological diversity, the direct encoding finds solutions more locally in the morphological search space, the L-System made larger jumps across this search space, and both network approaches also make larger jumps though find fewer solutions in this space. With these results we show how encodings exhibit different characteristics as developmental approaches. Since the genotype-phenotype mapping plays a major role in evolutionary robotics, further modifications using more complex tasks and environments can lead to a better understanding of morphogenesis and thereby improve how morphologies and controllers of robots are evolved.

One of the core functions in most Evolutionary Algorithms is mutation. In complex search spaces, which are common in Evolutionary Robotics, mutation is often used both for optimizing existing solutions, described as exploitation, and for spanning the search space, called exploration. This presents a difficult challenge for researchers as mutation parameters must be selected with care in order to balance the two, often contradictory, effects. Strategies that vary mutation during the search often try to estimate these effects in order to modify the mutation parameters. In this regard MAP-Elites, a Quality Diversity algorithm, presents an interesting opportunity. Because factors related to exploration and exploitation are readily available during the search, optimization based on these factors could be utilized to improve the search. In this paper we study how online adaptation of mutation rate, dynamic mutation, affects MAP-Elites in order to gain insight into how the search process is affected by the mutation rate. Our study compares fixed and dynamic mutation parameters for two different complex gait controllers. The results show that dynamic mutation combines favorably with MAP-Elites and that there is a strong relation between mutation parameters and exploration that can be utilized.

This paper investigates the evolution of modular robots using different selection preferences (i.e., fitness functions), aiming at novelty, speed of locomotion, number of limbs, and combinations of these. The outcomes are analyzed from different perspectives: sampling of the search space, evolved morphologies, and evolved behaviors. This results in a wealth of findings, including a surprise about the number of sampled regions of the search space and the effect of different fitness functions on the evolved morphologies.

Evolving robot morphologies implies the need for lifetime learning so that newborn robots can learn to manipulate their bodies. An individual’s morphology will obviously combine traits of all its parents; it must adapt its own controller to suit its morphology, and cannot rely on the controller of any one parent to perform well without adaptation. This paper investigates the practicability and benefits of Lamarckian evolution in this setting. Implementing lifetime learning by means of on-line evolution, we first establish the suitability of an indirect encoding scheme that combines Compositional Pattern Producing Networks (CPPNs) and Central Pattern Generators (CPGs) as a relevant learner and controller for open-loop gait controllers. We then analyze a Lamarckian set-up and the effect of the parental genetic material on the early convergence to good locomotion performance.