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

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on robotics Ročník 38; číslo 1; s. 317 - 328
Hlavní autoři:	Rudin, Nikita, Kolvenbach, Hendrik, Tsounis, Vassilios, Hutter, Marco
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	New York IEEE 01.02.2022 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	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 přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

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.
Bibliografie:	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