Comparing Direct and Indirect Representations for Environment-Specific Robot Component Design

Abstract

We compare two representations used to define the morphology of legs for a hexapod robot, which are subsequently 3D printed. A leg morphology occupies a set of voxels in a voxel grid. One method, a direct representation, uses a collection of Bezier splines. The second, an indirect method, utilises CPPN-NEAT. In our first experiment, we investigate two strategies to post-process the CPPN output and ensure leg length constraints are met. The first uses an adaptive threshold on the output neuron, the second, previously reported in the literature, scales the largest generated artefact to our desired length. In our second experiment, we build on our past work that evolves the tibia of a hexapod to provide environment-specific performance benefits. We compare the performance of our direct and indirect legs across three distinct environments, represented in a high-fidelity simulator. Results are significant and support our hypothesis that the indirect representation allows for further exploration of the design space leading to improved fitness.

Constrained by Design: Influence of Genetic Encodings on Evolved Traits of Robots

“…With respect to encoding comparisons, studies in the literature have been excessively focused on performance ( Komosiński and Rotaru-Varga, 2001 ; Yosinski et al, 2011 ; Collins et al, 2019 ), i.e., fitness-oriented studies. This is the case from simple encodings ( Janikow and Michalewicz, 1991 ) for solving classical problems like the Knapsack ( Colombo and Mumford, 2005 ), to neuroevolution ( Gruau et al, 1996 ; Siddiqi and Lucas, 1998 ) and also complex applications like evolving robot morphologies coupled with controllers ( Hornby et al, 2003 ).…”

Path towards multilevel evolution of robots

“…Direct representation (eg. 3D voxel grids [1] , bezier splines [2], etc) is typically integer or binary-based and exhibits a (relatively) low level of phenotypic complexity. Indirect representation (eg.…”

Multi-Level Evolution for Robotic Design

“…to the design of robots whose behaviour is typically elicited through embodied cognition. This may involve optimizing the controller ( Cully and Mouret, 2016 ), the physical design ( Collins et al, 2019 ) or both ( Auerbach and Bongard, 2011 ). Optimization focusing on body-brain evolution remains complex since small changes in body design can lead to the need for major changes in the control strategy, and vice versa.…”