Article citationsMore>>

Radford, N.A., Strawser, P., Hambuchen, K., Mehling, J.S., Verdeyen, W.K., Donnan, A.S., Holley, J., Sanchez, J., Nguyen, V., Bridgwater, L., Berka, R., Ambrose, R., Myles Markee, M., Fraser-Chanpong, N.J., McQuin, C., Yamokoski, J.D., Hart, S., Guo, R., Parsons, A., Wightman, B., Dinh, P., Ames, B., Blakely, C., Edmondson, C., Sommers, B., Rea, R., Tobler, C., Bibby, H., Howard, B., Niu, L., Lee, A., Conover, M., Truong, L., Reed, R., Chesney, D., Platt Jr., R., Johnson, G., Fok, C.-L., Paine, N., Sentis, L., Cousineau, E., Sinnet, R., Lack, J., Powell, M., Morris, B., Ames, A. and Akinyode, J. (2015) Valkyrie: Nasa’s First Bipedal Humanoid Robot. Journal of Field Robotics, 32, 397-419.
https://doi.org/10.1002/rob.21560
https://onlinelibrary.wiley.com/doi/abs/10.1002/rob.21560

has been cited by the following article:

• TITLE: A Comparison of PPO, TD3 and SAC Reinforcement Algorithms for Quadruped Walking Gait Generation

  AUTHORS: James W. Mock, Suresh S. Muknahallipatna

  KEYWORDS: Reinforcement Learning, Machine Learning, Markov Decision Process, Domain Randomization

  JOURNAL NAME: Journal of Intelligent Learning Systems and Applications, Vol.15 No.1, February 28, 2023

  ABSTRACT: Deep reinforcement learning (deep RL) has the potential to replace classic robotic controllers. State-of-the-art Deep Reinforcement algorithms such as Proximal Policy Optimization, Twin Delayed Deep Deterministic Policy Gradient and Soft Actor-Critic Reinforcement Algorithms, to mention a few, have been investigated for training robots to walk. However, conflicting performance results of these algorithms have been reported in the literature. In this work, we present the performance analysis of the above three state-of-the-art Deep Reinforcement algorithms for a constant velocity walking task on a quadruped. The performance is analyzed by simulating the walking task of a quadruped equipped with a range of sensors present on a physical quadruped robot. Simulations of the three algorithms across a range of sensor inputs and with domain randomization are performed. The strengths and weaknesses of each algorithm for the given task are discussed. We also identify a set of sensors that contribute to the best performance of each Deep Reinforcement algorithm.