Anton Bernatskiy

Evolving Robot Morphology Facilitates the Evolution of Neural Modularity and Evolvability

Although recent work has demonstrated that modularity can increase evolvability in non-embodied systems, it remains to be seen how the morphologies of embodied agents influences the ability of an evolutionary algorithm to find useful and modular controllers for them. We hypothesize that a modular control system may enable different parts of a robots body to sense and react to stimuli independently, enabling it to correctly recognize a seemingly novel environment as, in fact, a composition of familiar percepts and thus respond appropriately without need of further evolution. Here we provide evidence that supports this hypothesis: We found that such robots can indeed be evolved if (1) the robots morphology is evolved along with its controller, (2) the fitness function selects for the desired behavior and (3) also selects for conservative and robust behavior. In addition, we show that if constraints (1) and (3) are relaxed, or structural modularity is selected for directly, the robots have too little or too much modularity and lower evolvability. Thus, we demonstrate a previously unknown relationship between modularity and embodied cognition: evolving morphology and control such that robots exhibit conservative behavior indirectly selects for appropriate modularity and, thus, increased evolvability.

Improving Robot Behavior Optimization by Combining User Preferences

Recently it has been demonstrated that collaboration between automated algorithms and human users can be especially effective in robot behavior optimization tasks. In particular, we recently introduced a Fitness-based Search with Preferencebased Policy Learning (FS-PPL) approach, in which the algorithm models the user based on her preferences and then uses the model, along with the fitness function, to guide search. However, so far only interaction between a single human user and an evolutionary algorithm was considered. If multiple users contribute preferences, the algorithm must determine whether to model them separately or jointly. In this paper we describe an algorithm in which one evolutionary algorithm interacts with two users and determines the best way to model them automatically. We test the algorithm with automated substitutes for human users and show that it performs better for two users working together than for the same users working separately, thus demonstrating the potential for crowdsourcing robot behavior optimization.

Morphological Modularity Can Enable the Evolution of Robot Behavior to Scale Linearly with the Number of Environmental Features

In evolutionary robotics, populations of robots are typically trained in simulation before one or more of them are instantiated as physical robots. However, in order to evolve robust behavior, each robot must be evaluated in multiple environments. If an environment is characterized by

Exploiting the Relationship Between Structural Modularity and Sparsity for Faster Network Evolution

f

Modularity and Sparsity: Evolution of Neural Net Controllers in Physically Embodied Robots

free parameters, each of which can take one of

Simulating the evolution of soft and rigid-body robots

n_p

Choice of robot morphology can prohibit modular control and disrupt evolution.

features, each robot must be evaluated in all

Evolving morphology automatically reformulates the problem of designing modular control

n_p^f

Ecological modularity as a means to reduce necessary training environments in evolutionary robotics

environments to ensure robustness. Here we show that, if the robots are constrained to have modular morphologies and controllers, they only need to be evaluated in

Reducing Training Environments in Evolutionary Robotics Through Ecological Modularity

n_p