4.6 Article

Learning Free Gait Transition for Quadruped Robots Via Phase-Guided Controller

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Proceedings Paper Automation & Control Systems

Sim-to-Real Learning of All Common Bipedal Gaits via Periodic Reward Composition

Jonah Siekmann et al.

Summary: By defining a parameterized reward function using simple probabilistic periodic costs, we successfully achieved the transfer of various gaits of bipedal robots from simulation to reality. This method can assist in learning different gaits and is applicable to common bipedal locomotion.

2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2021) (2021)

Proceedings Paper Automation & Control Systems

Collision-Free MPC for Legged Robots in Static and Dynamic Scenes

Magnus Gaertner et al.

Summary: The model predictive controller proposed in this study allows legged robots to discover collision-free locomotion while considering system dynamics, friction constraints, kinematic limitations, and collision detection. The approach combines a relaxed barrier function in the optimization cost function to ensure collision avoidance without increasing computational complexity, demonstrating successful collision-free motions in challenging indoor environments. Additionally, the inclusion of dynamic obstacles and motion prediction capabilities enhances the robot's ability to anticipate and avoid potential collisions.

2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2021) (2021)

Proceedings Paper Automation & Control Systems

Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robots

Zhongyu Li et al.

Summary: Researchers developed robust walking controllers using a model-free reinforcement learning framework for bipedal robots to train in simulation and transfer to a real robot, using domain randomization to facilitate sim-to-real transfer.

2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2021) (2021)

Proceedings Paper Automation & Control Systems

Imitation Learning from MPC for Quadrupedal Multi-Gait Control

Alexander Reske et al.

Summary: This study introduces a learning algorithm for training a single policy to imitate multiple gaits of a walking robot. By utilizing MPC-Net and a mixture-of-experts network (MEN), as well as introducing new loss functions, expert selection behavior is successfully achieved, leading to improved policy performance.

2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2021) (2021)

Article Computer Science, Software Engineering

CARL: Controllable Agent with Reinforcement Learning for Quadruped Locomotion

Ying-Sheng Luo et al.

ACM TRANSACTIONS ON GRAPHICS (2020)

Article Robotics

Learning quadrupedal locomotion over challenging terrain

Joonho Lee et al.

SCIENCE ROBOTICS (2020)

Article Robotics

Multi-expert learning of adaptive legged locomotion

Chuanyu Yang et al.

SCIENCE ROBOTICS (2020)

Article Robotics

A Simple Yet Effective Whole-Body Locomotion Framework for Quadruped Robots

Gennaro Raiola et al.

FRONTIERS IN ROBOTICS AND AI (2020)

Article Robotics

MPC-Net: A First Principles Guided Policy Search

Jan Carius et al.

IEEE ROBOTICS AND AUTOMATION LETTERS (2020)

Article Multidisciplinary Sciences

Programmable coupled oscillators for synchronized locomotion

Sourav Dutta et al.

NATURE COMMUNICATIONS (2019)

Article Robotics

Learning agile and dynamic motor skills for legged robots

Jemin Hwangbo et al.

SCIENCE ROBOTICS (2019)

Article Chemistry, Multidisciplinary

A Bio-Inspired Control Strategy for Locomotion of a Quadruped Robot

Yinquan Zeng et al.

APPLIED SCIENCES-BASEL (2018)

Article Computer Science, Software Engineering

DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills

Xue Bin Peng et al.

ACM TRANSACTIONS ON GRAPHICS (2018)

Article Computer Science, Software Engineering

Mode-Adaptive Neural Networks for Quadruped Motion Control

He Zhang et al.

ACM TRANSACTIONS ON GRAPHICS (2018)

Article Robotics

Per-Contact Iteration Method for Solving Contact Dynamics

Jemin Hwangbo et al.

IEEE ROBOTICS AND AUTOMATION LETTERS (2018)

Article Robotics

Selecting gaits for economical locomotion of legged robots

Weitao Xi et al.

INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH (2016)

Article Computer Science, Artificial Intelligence

Design of Spiking Central Pattern Generators for Multiple Locomotion Gaits in Hexapod Robots by Christiansen Grammar Evolution

Andres Espinal et al.

FRONTIERS IN NEUROROBOTICS (2016)

Article Multidisciplinary Sciences

A simple rule for quadrupedal gait generation determined by leg loading feedback: a modeling study

Yasuhiro Fukuoka et al.

SCIENTIFIC REPORTS (2015)

Review Computer Science, Artificial Intelligence

Central pattern generators for locomotion control in animals and robots: A review

Auke Jan Ijspeert

NEURAL NETWORKS (2008)