Adversarial Body Shape Search for Legged Robots

  title={Adversarial Body Shape Search for Legged Robots},
  author={Takaaki Azakami and Hiroshi Kera and K. Kawamoto},
—We propose an evolutionary computation method for an adversarial attack on the length and thickness of parts of legged robots by deep reinforcement learning. This attack changes the robot body shape and interferes with walking—we call the attacked body as adversarial body shape . The evolu- tionary 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 perform… 

Figures and Tables from this paper


Jointly Learning to Construct and Control Agents using Deep Reinforcement Learning
The approach maintains a distribution over designs and uses reinforcement learning to optimize a control policy to maximize expected reward over the design distribution, and gives the controller access to design parameters to allow it to tailor its policy to each design in the distribution.
Challenges and Countermeasures for Adversarial Attacks on Deep Reinforcement Learning
This work investigates the vulnerabilities that an adversary can exploit to attack DRL along with state-of-the-art countermeasures to prevent such attacks and highlights open issues and research challenges for developing solutions to deal with attacks on DRL-based intelligent systems.
Reinforcement Learning for Improving Agent Design
It is demonstrated that an agent can learn a better structure of its body that is not only better suited for the task, but also facilitates policy learning.
Proximal Policy Optimization Algorithms
We propose a new family of policy gradient methods for reinforcement learning, which alternate between sampling data through interaction with the environment, and optimizing a "surrogate" objective
MuJoCo: A physics engine for model-based control
A new physics engine tailored to model-based control, based on the modern velocity-stepping approach which avoids the difficulties with spring-dampers, which can compute both forward and inverse dynamics.
Differential Evolution – A Simple and Efficient Heuristic for global Optimization over Continuous Spaces
It is demonstrated that the new heuristic approach for minimizing possibly nonlinear and non-differentiable continuous spacefunctions Converges faster and with more certainty than manyother acclaimed global optimization methods.
Characterizing Attacks on Deep Reinforcement Learning
The first targeted attacks based on action space and environment dynamics based on temporal consistency information among frames are proposed and introduced, and a sampling strategy is proposed to better estimate gradient in black-box setting.
NerveNet: Learning Structured Policy with Graph Neural Networks
NerveNet is proposed to explicitly model the structure of an agent, which naturally takes the form of a graph, and is demonstrated to be significantly more transferable and generalizable than policies learned by other models and are able to transfer even in a zero-shot setting.
Ala Al-Fuqaha, Dinh Thai Hoang, and Dusit Niyato. Challenges and countermeasures for adversarial attacks on deep reinforcement learning
  • IEEE Transactions on Artificial Intelligence
  • 2022