Cat-Like Jumping and Landing of Legged Robots in Low Gravity Using Deep Reinforcement Learning

In this article, we show that learned policies can be applied to solve legged locomotion control tasks with extensive flight phases, such as those encountered in space exploration. Using an off-the-shelf deep reinforcement learning algorithm, we train a neural network to control a jumping quadruped...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE transactions on robotics Ročník 38; číslo 1; s. 317 - 328
Hlavní autori: Rudin, Nikita, Kolvenbach, Hendrik, Tsounis, Vassilios, Hutter, Marco
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: New York IEEE 01.02.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
Actuators
Algorithms
Attitude control
Control tasks
Deep learning
Deep learning in robotics and automation
Gravity
Kinematics
Landing
Legged locomotion
legged robots
Locomotion
Machine learning
Microgravity
Neural networks
Policies
Robot control
Robot dynamics
Robots
Space exploration
space robotics and automation
Task analysis
Task complexity
Training
ISSN:1552-3098, 1941-0468
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:In this article, we show that learned policies can be applied to solve legged locomotion control tasks with extensive flight phases, such as those encountered in space exploration. Using an off-the-shelf deep reinforcement learning algorithm, we train a neural network to control a jumping quadruped robot while solely using its limbs for attitude control. We present tasks of increasing complexity leading to a combination of 3-D (re)orientation and landing locomotion behaviors of a quadruped robot traversing simulated low-gravity celestial bodies. We show that our approach easily generalizes across these tasks and successfully trains policies for each case. Using sim-to-real transfer, we deploy trained policies in the real world on the SpaceBok robot placed on an experimental testbed designed for 2-D microgravity experiments. The experimental results demonstrate that repetitive controlled jumping and landing with natural agility is possible.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1552-3098
1941-0468
DOI:10.1109/TRO.2021.3084374