Report
Continuous Versatile Jumping Using Learned Action Residuals
| العنوان: | Continuous Versatile Jumping Using Learned Action Residuals |
|---|---|
| المؤلفون: | Yang, Yuxiang, Meng, Xiangyun, Yu, Wenhao, Zhang, Tingnan, Tan, Jie, Boots, Byron |
| سنة النشر: | 2023 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Robotics, Computer Science - Artificial Intelligence, Computer Science - Machine Learning |
| الوصف: | Jumping is essential for legged robots to traverse through difficult terrains. In this work, we propose a hierarchical framework that combines optimal control and reinforcement learning to learn continuous jumping motions for quadrupedal robots. The core of our framework is a stance controller, which combines a manually designed acceleration controller with a learned residual policy. As the acceleration controller warm starts policy for efficient training, the trained policy overcomes the limitation of the acceleration controller and improves the jumping stability. In addition, a low-level whole-body controller converts the body pose command from the stance controller to motor commands. After training in simulation, our framework can be deployed directly to the real robot, and perform versatile, continuous jumping motions, including omni-directional jumps at up to 50cm high, 60cm forward, and jump-turning at up to 90 degrees. Please visit our website for more results: https://sites.google.com/view/learning-to-jump. Comment: To be presented at L4DC 2023 |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2304.08663 |
| رقم الانضمام: | edsarx.2304.08663 |
| قاعدة البيانات: | arXiv |
| ResultId |
1 |
|---|---|
| Header |
edsarx arXiv edsarx.2304.08663 1057 3 Report report 1057.31762695313 |
| PLink |
https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&scope=site&db=edsarx&AN=edsarx.2304.08663&custid=s6537998&authtype=sso |
| FullText |
Array
(
[Availability] => 0
)
Array ( [0] => Array ( [Url] => http://arxiv.org/abs/2304.08663 [Name] => EDS - Arxiv [Category] => fullText [Text] => View record in Arxiv [MouseOverText] => View record in Arxiv ) ) |
| Items |
Array
(
[Name] => Title
[Label] => Title
[Group] => Ti
[Data] => Continuous Versatile Jumping Using Learned Action Residuals
)
Array ( [Name] => Author [Label] => Authors [Group] => Au [Data] => <searchLink fieldCode="AR" term="%22Yang%2C+Yuxiang%22">Yang, Yuxiang</searchLink><br /><searchLink fieldCode="AR" term="%22Meng%2C+Xiangyun%22">Meng, Xiangyun</searchLink><br /><searchLink fieldCode="AR" term="%22Yu%2C+Wenhao%22">Yu, Wenhao</searchLink><br /><searchLink fieldCode="AR" term="%22Zhang%2C+Tingnan%22">Zhang, Tingnan</searchLink><br /><searchLink fieldCode="AR" term="%22Tan%2C+Jie%22">Tan, Jie</searchLink><br /><searchLink fieldCode="AR" term="%22Boots%2C+Byron%22">Boots, Byron</searchLink> ) Array ( [Name] => DatePubCY [Label] => Publication Year [Group] => Date [Data] => 2023 ) Array ( [Name] => Subset [Label] => Collection [Group] => HoldingsInfo [Data] => Computer Science ) Array ( [Name] => Subject [Label] => Subject Terms [Group] => Su [Data] => <searchLink fieldCode="DE" term="%22Computer+Science+-+Robotics%22">Computer Science - Robotics</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+Science+-+Artificial+Intelligence%22">Computer Science - Artificial Intelligence</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+Science+-+Machine+Learning%22">Computer Science - Machine Learning</searchLink> ) Array ( [Name] => Abstract [Label] => Description [Group] => Ab [Data] => Jumping is essential for legged robots to traverse through difficult terrains. In this work, we propose a hierarchical framework that combines optimal control and reinforcement learning to learn continuous jumping motions for quadrupedal robots. The core of our framework is a stance controller, which combines a manually designed acceleration controller with a learned residual policy. As the acceleration controller warm starts policy for efficient training, the trained policy overcomes the limitation of the acceleration controller and improves the jumping stability. In addition, a low-level whole-body controller converts the body pose command from the stance controller to motor commands. After training in simulation, our framework can be deployed directly to the real robot, and perform versatile, continuous jumping motions, including omni-directional jumps at up to 50cm high, 60cm forward, and jump-turning at up to 90 degrees. Please visit our website for more results: https://sites.google.com/view/learning-to-jump.<br />Comment: To be presented at L4DC 2023 ) Array ( [Name] => TypeDocument [Label] => Document Type [Group] => TypDoc [Data] => Working Paper ) Array ( [Name] => URL [Label] => Access URL [Group] => URL [Data] => <link linkTarget="URL" linkTerm="http://arxiv.org/abs/2304.08663" linkWindow="_blank">http://arxiv.org/abs/2304.08663</link> ) Array ( [Name] => AN [Label] => Accession Number [Group] => ID [Data] => edsarx.2304.08663 ) |
| RecordInfo |
Array
(
[BibEntity] => Array
(
[Subjects] => Array
(
[0] => Array
(
[SubjectFull] => Computer Science - Robotics
[Type] => general
)
[1] => Array
(
[SubjectFull] => Computer Science - Artificial Intelligence
[Type] => general
)
[2] => Array
(
[SubjectFull] => Computer Science - Machine Learning
[Type] => general
)
)
[Titles] => Array
(
[0] => Array
(
[TitleFull] => Continuous Versatile Jumping Using Learned Action Residuals
[Type] => main
)
)
)
[BibRelationships] => Array
(
[HasContributorRelationships] => Array
(
[0] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => Yang, Yuxiang
)
)
)
[1] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => Meng, Xiangyun
)
)
)
[2] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => Yu, Wenhao
)
)
)
[3] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => Zhang, Tingnan
)
)
)
[4] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => Tan, Jie
)
)
)
[5] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => Boots, Byron
)
)
)
)
[IsPartOfRelationships] => Array
(
[0] => Array
(
[BibEntity] => Array
(
[Dates] => Array
(
[0] => Array
(
[D] => 17
[M] => 04
[Type] => published
[Y] => 2023
)
)
)
)
)
)
)
|
| IllustrationInfo |