Model predictive control of legged and humanoid robots: models and algorithms

S Katayama, M Murooka, Y Tazaki - Advanced Robotics, 2023‏ - Taylor & Francis
Model predictive control (MPC) of legged and humanoid robotic systems has been an active
research topic in the past decade. While MPC for robotic systems has a long history, its …

Rapid locomotion via reinforcement learning

GB Margolis, G Yang, K Paigwar… - … Journal of Robotics …, 2024‏ - journals.sagepub.com
Agile maneuvers such as sprinting and high-speed turning in the wild are challenging for
legged robots. We present an end-to-end learned controller that achieves record agility for …

Neural volumetric memory for visual locomotion control

R Yang, G Yang, X Wang - … of the IEEE/CVF conference on …, 2023‏ - openaccess.thecvf.com
Legged robots have the potential to expand the reach of autonomy beyond paved roads. In
this work, we consider the difficult problem of locomotion on challenging terrains using a …

High-speed quadrupedal locomotion by imitation-relaxation reinforcement learning

Y **, X Liu, Y Shao, H Wang, W Yang - Nature Machine Intelligence, 2022‏ - nature.com
Fast and stable locomotion of legged robots involves demanding and contradictory
requirements, in particular rapid control frequency as well as an accurate dynamics model …

Agile but safe: Learning collision-free high-speed legged locomotion

T He, C Zhang, W **ao, G He, C Liu, G Shi - arxiv preprint arxiv …, 2024‏ - arxiv.org
Legged robots navigating cluttered environments must be jointly agile for efficient task
execution and safe to avoid collisions with obstacles or humans. Existing studies either …

Representation-free model predictive control for dynamic motions in quadrupeds

Y Ding, A Pandala, C Li, YH Shin… - IEEE Transactions on …, 2021‏ - ieeexplore.ieee.org
This article presents a novel representation-free model predictive control (RF-MPC)
framework for controlling various dynamic motions of a quadrupedal robot in three …

TAMOLS: Terrain-aware motion optimization for legged systems

F Jenelten, R Grandia, F Farshidian… - IEEE Transactions on …, 2022‏ - ieeexplore.ieee.org
Terrain geometry is, in general, nonsmooth, nonlinear, nonconvex, and, if perceived through
a robot-centric visual unit, appears partially occluded and noisy. This article presents the …

Learning vision-guided quadrupedal locomotion end-to-end with cross-modal transformers

R Yang, M Zhang, N Hansen, H Xu, X Wang - arxiv preprint arxiv …, 2021‏ - arxiv.org
We propose to address quadrupedal locomotion tasks using Reinforcement Learning (RL)
with a Transformer-based model that learns to combine proprioceptive information and high …

Opt-mimic: Imitation of optimized trajectories for dynamic quadruped behaviors

Y Fuchioka, Z **e… - 2023 IEEE International …, 2023‏ - ieeexplore.ieee.org
Reinforcement Learning (RL) has seen many recent successes for quadruped robot control.
The imitation of reference motions provides a simple and powerful prior for guiding solutions …