Adversarial Body Shape Search for Legged Robots

We propose an evolutionary computation method based on deep reinforcement learning to determine the vulnerability to adversarial attacks (such as corrosion and defects caused by collisions) on the length and thickness of parts of legged robots. This type of attack changes the robot’s body shape and interferes with walking; we call the attacked body the adversarial body shape. The proposed evolutionary computation method searches adversarial body shape by minimizing the expected cumulative reward earned through walking simulation. To evaluate the effectiveness of the proposed method, we performed experiments with three different legged robots (Walker2d, Ant-v2, and Humanoid-v2) in OpenAI Gym. The experimental results reveal that Walker2d and Ant-v2 are more vulnerable to attack on the length than on the thickness of the body parts, whereas Humanoid-v2 is vulnerable to attack on both the length and thickness. We further identified that the adversarial body shapes break left-right symmetry or shift the center of gravity of the legged robots. This method of finding adversarial body shapes can be used to proactively diagnose the vulnerability of legged robot walking.