Learning to walk with biped robot based on an improved proximal policy optimization algorithm

2021 ◽  
Author(s):  
Chao Zhang ◽  
Peisi Zhong ◽  
Zhongyuan Liang ◽  
Mei Liu ◽  
Xiao Wang ◽  
...  
2019 ◽  
Vol 31 ◽  
pp. 17-32 ◽  
Author(s):  
Mostafa A. Elhosseini ◽  
Amira Y. Haikal ◽  
Mahmoud Badawy ◽  
Nour Khashan

2021 ◽  
Vol 1754 (1) ◽  
pp. 012229
Author(s):  
Jinxiu Hou ◽  
Zhihong Yu ◽  
Qingping Zheng ◽  
Huating Xu ◽  
Shufang Li

2019 ◽  
Vol 11 (11) ◽  
pp. 168781401988808 ◽  
Author(s):  
Tran Thien Huan ◽  
Ho Pham Huy Anh ◽  
Cao Van Kien

This article proposes a new method used to optimize the design process of nature-walking gait generator that permits biped robot to stably and naturally walk with preset foot-lift magnitude. The new Jaya optimization algorithm is innovatively applied to optimize the biped gait four key parameters initiatively applied to ensure the uncertain nonlinear humanoid robot walks robustly and steadily. The efficiency of the proposed Jaya-based identification approach is compared with the central force optimization and improved differential evolution (modified differential evolution) algorithms. The simulation and experimental results tested on the original small-sized biped robot HUBOT-4 convincingly demonstrate that the novel proposed algorithm offers an efficient and stable gait for humanoid robots with precise height of foot-lift value.


Robotica ◽  
2021 ◽  
pp. 1-26
Author(s):  
Mathieu Hobon ◽  
Víctor De-León-Gómez ◽  
Gabriel Abba ◽  
Yannick Aoustin ◽  
Christine Chevallereau

Abstract The purpose is to define the range of feasible speeds for two walking motions for a particular planar biped robot, which differ in the definition of their finite-time double support phases. For each speed, these two walking motions are numerically obtained by using a parametric optimization algorithm, regarding a sthenic criterion. Results allow us to define the range of allowable speeds for each walking. One result is that the first gait is less consuming in energy for moderate to fast velocity with respect to the second one, while the second gait is more efficient for low walking velocity.


2020 ◽  
Vol 2020 ◽  
pp. 1-11
Author(s):  
Weiguang Wang ◽  
Hui Li ◽  
Wenjie Zhang ◽  
Shanlin Wei

D2D communication improves the cellular network performance by using proximity-based services between adjacent devices, which considered is an effective way to solve the problem of spectrum scarcity caused by tremendous mobile data traffic. If the cache-enabled users are willing to send the cached file to the requesters, the content delivery traffic can be offloaded through the D2D link. In this paper, we strive to find the maximum energy efficiency of the D2D caching network through the joint optimization of cache policy and content transmit power. Specifically, based on stochastic geometry-aided modeling of the network, we derive the data offloading rate in closed form, which jointly considers the effects of success sensing probability and success transmission probability. According to the data offloading rate, we formulate a joint optimization problem integrating cache policy and transmit power to maximize the system energy efficiency. To solve this problem, we propose two optimization algorithms that the cache policy optimization algorithm based on gradient update and the joint optimization algorithm. The simulation results demonstrate that the joint optimization has twice the superiority in improving the energy efficiency of the D2D caching network compared with other schemes.


Sign in / Sign up

Export Citation Format

Share Document