Multi-Level Evolution for Robotic Design

Abstract

Multi-level evolution (MLE) is a novel robotic design paradigm which decomposes the design problem into layered sub-tasks that involve concurrent search for appropriate materials, component geometry and overall morphology. This has a number of advantages, mainly in terms of quality and scalability. In this paper, we present a hierarchical approach to robotic design based on the MLE architecture. The design problem involves finding a robotic design which can be used to perform a specific locomotion task. At the materials layer, we put together a simple collection of materials which are represented by combinations of mechanical properties such as friction and restitution. At the components layer we combine these materials with geometric design to form robot limbs. Finally, at the robot layer we introduce these evolved limbs into robotic body-plans and learn control policies to form complete robots. Quality-diversity algorithms at each level allow for the discovery of a wide variety of reusable elements. The results strongly support the initial claims for the benefits of MLE, allowing for the discovery of designs that would otherwise be difficult to achieve with conventional design paradigms.

A model-free method to learn multiple skills in modular robots

“…Furthermore, by utilising the additional bootstrapped samples in our optimiser we might learn faster using of data-driven techniques, for example, surrogate models and MAP-elites/novelty-search [37][38][39] to increase learning speed and encourage diversity in solutions. The fast parallelised learning of modular behaviours can help us to speed up the design of hierarchical control-structures like finite-state machines or behavioural trees [37,40,41].…”

Diversity‐Based Topology Optimization of Soft Robotic Grippers

“…These typically use inexpensive physics engines with soft material primatives to evolve or learn high performing designs for mobile "soft robots" and artificial life forms. [21,[35][36][37][38] As the field has developed, evermore accurate simulators have been developed, increasing modelling fidelity, expanding environment realism and adding features. The current state of the art still lacks physical grounding, however; generated designs are either unsuited to physical manufacture or unable to cross the reality gap.…”