Datasets for "Automatic Design of Mechanical Metamaterial Actuators"

Publication arXiv preprint: https://arxiv.org/abs/2002.03032 journal version: [add link to journal]   Code https://github.com/ComplexityBiosystems/metamech https://github.com/complexitybiosystems/metamech_datasets   Datasets Figure 2: antiparallel_{human,machine}design.stl: STL files for human design and machine design configurations performing antiparallel movement. Figure 3:  crane_scaling_dataframe.csv: raw efficiency values and execution times used to generate Figure 3 Figure 4: eta_random.dat, eta_triang.dat, plot_distrib.gnupot: raw values of efficiency and gnuplot script used to generate Figure 4 panel d eta_vs_displ_random.dat, eta_vs_displ_triang.dat, eta_vs_displ.gnuplot: raw values of efficiency and gnuplot script  used to generate Figure 4 panel c structures.tar.bz2: all the structures relative to Figure 4 panel d, in a format suitable for visualization with ovito software Figure 5:  data files for human and machine generated pairs of pliers in a format suitable for visualization with ovito software.  ".agr" and ".data" files can be opened with any text editor to directly visualize the raw data.   _rest.data: rest configurations which are represented in grey in Fig. 5a and Fig. 5b.  _F0.01.data: displaced configurations with input force Fext = 0.01 and output spring stiffness kext = 0.01, also reported in Fig. 5a and Fig. 5b. .agr: dataset for Figure 5c and 5d in xmgrace format. Figure 6: Fig6/Fig6b/.csv: raw values of efficiency used to generate Figure 6 panel b Fig6/Fig6c-training-data//.png: a total of 1.163.733 PNG images, of size 192 x 168 pixels, as described in the methods section of the manuscript, organized in directories corresponding to different runs. Fig6/Fig6c-training-data/metadata.csv: maps each image path to its associated efficiency value Fig6/Fig6c-efficiency-data/eta_design.stl: STL files for human design and machine design configurations performing orthogonal movement.  }.txt: raw values of efficiency used to generate Figure 6 panel c. Figure 7: Fig7/transfer_learning_regression_values.csv: full raw data, including regression coefficients, p-values, slopes and intercepts corresponding to Figure 7 panels i and j Figure S3: orthogonal_{human,machine