2019/01/20 by Jack Collins, Collins, Jack, Ben Cottier +3 · 1 citation
Biochemistry, Genetics and Molecular Biology · Engineering · #Cell Image Analysis Techniques #FOS: Computer and information sciences #Neural and Evolutionary Computing (cs.NE) #Robot Manipulation and Learning #Robotic Locomotion and Control #Robotics (cs.RO)
paper · pdf · doi:10.48550/arxiv.1901.06775
openalex publication_date 2019/01/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We compare two representations used to define the morphology of legs for a\nhexapod robot, which are subsequently 3D printed. A leg morphology occupies a\nset of voxels in a voxel grid. One method, a direct representation, uses a\ncollection of Bezier splines. The second, an indirect method, utilises\nCPPN-NEAT. In our first experiment, we investigate two strategies to\npost-process the CPPN output and ensure leg length constraints are met. The\nfirst uses an adaptive threshold on the output neuron, the second, previously\nreported in the literature, scales the largest generated artefact to our\ndesired length. In our second experiment, we build on our past work that\nevolves the tibia of a hexapod to provide environment-specific performance\nbenefits. We compare the performance of our direct and indirect legs across\nthree distinct environments, represented in a high-fidelity simulator. Results\nare significant and support our hypothesis that the indirect representation\nallows for further exploration of the design space leading to improved fitness.\n