Article

Learning fast and agile quadrupedal locomotion over complex terrain

2023-10-18

Abstract excerpt

In this paper, we propose a robust controller that achieves natural and stably fast locomotion on a real blind quadruped robot. With only proprioceptive information, the quadruped robot can move at a maximum speed of 10 times its body length per second, and has the ability to pass through various complex terrains. The controller is trained in the simulation environment by model-free reinforcement learning and no s...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 4b8d322f-e0f0-5cf9-b334-6522d3f960eb
DOI: 10.22541/au.169762718.83712763/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Learning fast and agile quadrupedal locomotion over complex terrainDOI 10.22541/au.169762718.83712763/v1Read

Automated Evolutionary Gait Tuning for Humanoid Robots Using Inverse Kinematics and Genetic AlgorithmsSemantic proximity Read

A simple network of proprioceptive reflexes can produce a variety of bipedal gaitsSemantic proximity Read

Exploration-based learning of a stabilizing controller predicts locomotor adaptationSemantic proximity Read

A Neuromuscular Model of Human Locomotion Combines Spinal Reflex Circuits with Voluntary MovementsSemantic proximity Read

High-level motor planning allows flexible walking at different gait patterns in a neuromechanical modelSemantic proximity Read

Lifelike Agility and Play on Quadrupedal Robots using Reinforcement Learning and Generative Pre-trained ModelsSemantic proximity Read

Design and Programming of a Robotic Puppetry Robot Based on Natural Learner Unit Pattern Generators Neural NetworksSemantic proximity Read

Predictive simulation of human movement in OpenSim using floating-base task space controlSemantic proximity Read

Investigating the roles of reflexes and central pattern generators in the control and modulation of human locomotion using a physiologically plausible neuromechanical modelSemantic proximity Read

Bio-Inspired Optimal Control Framework to Generate Walking Motions for the Humanoid Robot iCub Using Whole Body ModelsSemantic proximity Read

Bipedal Robot Joint Trajectory Generation for Predetermined Zero Momentum PointSemantic proximity Read

A survey of research on several problems in the RoboCup3D simulation environmentSemantic proximity Read