Fig. 5
From: Bio-inspired neural networks with central pattern generators for learning multi-skill locomotion
Robot recovering from fall in the real world. (a) Snapshots of the robot performing agile fall recovery motions after experiencing external disturbance. (b) Roll pitch angles. The readings of the roll and pitch angle of the gyroscope reveals how fast the robot is capable of reorienting and recovering from a fall. (c) Snapshots of fall recovery on various terrains with different initial postures. (c1) Carpet. (c2) Grass. (c3) Mattress. (see Supplementary Video S2 for the corresponding video. Video URL: https://youtu.be/TCY2-pvkbjg).
