Morpho-evolution with learning using a controller archive as an inheritance mechanism
This work addresses the problem of efficient joint optimization of morphology and control in evolutionary robotics, offering incremental improvements for researchers in this domain.
The paper tackles the challenge of mismatched inherited controllers in joint body-plan and control optimization by proposing a framework that combines evolutionary algorithms for body-plan generation with learning algorithms for neural controller optimization, using an external archive of learned controllers to increase learning speed and magnitude compared to starting from scratch, as demonstrated in two tasks and three environments.
The joint optimisation of body-plan and control via evolutionary processes can be challenging in rich morphological spaces in which offspring can have body-plans that are very different from either of their parents. This causes a potential mismatch between the structure of an inherited controller and the new body. To address this, we propose a framework that combines an evolutionary algorithm to generate body-plans and a learning algorithm to optimise the parameters of a neural controller. The topology of this controller is created once the body-plan of each offspring body-plan is generated. The key novelty of the approach is to add an external archive for storing learned controllers that map to explicit `types' of robots (where this is defined with respect the features of the body-plan). By learning from a controller with an appropriate structure inherited from the archive, rather than from a randomly initialised one, we show that both the speed and magnitude of learning increases over time when compared to an approach that starts from scratch, using two tasks and three environments. The framework also provides new insights into the complex interactions between evolution and learning.