Predictive Sampling: Real-time Behaviour Synthesis with MuJoCo
We introduce MuJoCo MPC (MJPC), an open-source, interactive application and software framework for real-time predictive control, based on MuJoCo physics. MJPC allows the user to easily author and solve complex robotics tasks, and currently supports three shooting-based planners: derivative-based iLQ...
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | |
| container_volume | |
| creator | Howell, Taylor Gileadi, Nimrod Tunyasuvunakool, Saran Zakka, Kevin Erez, Tom Tassa, Yuval |
| description | We introduce MuJoCo MPC (MJPC), an open-source, interactive application and
software framework for real-time predictive control, based on MuJoCo physics.
MJPC allows the user to easily author and solve complex robotics tasks, and
currently supports three shooting-based planners: derivative-based iLQG and
Gradient Descent, and a simple derivative-free method we call Predictive
Sampling. Predictive Sampling was designed as an elementary baseline, mostly
for its pedagogical value, but turned out to be surprisingly competitive with
the more established algorithms. This work does not present algorithmic
advances, and instead, prioritises performant algorithms, simple code, and
accessibility of model-based methods via intuitive and interactive software.
MJPC is available at: github.com/deepmind/mujoco_mpc, a video summary can be
viewed at: dpmd.ai/mjpc. |
| doi_str_mv | 10.48550/arxiv.2212.00541 |
| format | Article |
| fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2212_00541</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2212_00541</sourcerecordid><originalsourceid>FETCH-LOGICAL-a671-d6e6f08e452fad606a3b7c95152b51506788d43991b6d602c3ffa7c687f14d233</originalsourceid><addsrcrecordid>eNotz8tOwzAUBFBvWKDCB7DCP5Dgtx0WSBDxVBGIdh_dxNfEUtJUThro31MKm5nFSCMdQi44y5XTml1B-o5zLgQXOWNa8VNy857Qx2aKM9IV9Nsubj6v6QdCl02xR3qHLcxx2CW62m-mFsc40q84tfR19zKUwxk5CdCNeP7fC7J-uF-XT9ny7fG5vF1mYCzPvEETmEOlRQBvmAFZ26bQXIv6EMxY57ySRcFrc5hFI0MA2xhnA1deSLkgl3-3R0C1TbGHtK9-IdURIn8AI4pCIA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Predictive Sampling: Real-time Behaviour Synthesis with MuJoCo</title><source>arXiv.org</source><creator>Howell, Taylor ; Gileadi, Nimrod ; Tunyasuvunakool, Saran ; Zakka, Kevin ; Erez, Tom ; Tassa, Yuval</creator><creatorcontrib>Howell, Taylor ; Gileadi, Nimrod ; Tunyasuvunakool, Saran ; Zakka, Kevin ; Erez, Tom ; Tassa, Yuval</creatorcontrib><description>We introduce MuJoCo MPC (MJPC), an open-source, interactive application and
software framework for real-time predictive control, based on MuJoCo physics.
MJPC allows the user to easily author and solve complex robotics tasks, and
currently supports three shooting-based planners: derivative-based iLQG and
Gradient Descent, and a simple derivative-free method we call Predictive
Sampling. Predictive Sampling was designed as an elementary baseline, mostly
for its pedagogical value, but turned out to be surprisingly competitive with
the more established algorithms. This work does not present algorithmic
advances, and instead, prioritises performant algorithms, simple code, and
accessibility of model-based methods via intuitive and interactive software.
MJPC is available at: github.com/deepmind/mujoco_mpc, a video summary can be
viewed at: dpmd.ai/mjpc.</description><identifier>DOI: 10.48550/arxiv.2212.00541</identifier><language>eng</language><subject>Computer Science - Robotics ; Computer Science - Systems and Control</subject><creationdate>2022-12</creationdate><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2212.00541$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2212.00541$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Howell, Taylor</creatorcontrib><creatorcontrib>Gileadi, Nimrod</creatorcontrib><creatorcontrib>Tunyasuvunakool, Saran</creatorcontrib><creatorcontrib>Zakka, Kevin</creatorcontrib><creatorcontrib>Erez, Tom</creatorcontrib><creatorcontrib>Tassa, Yuval</creatorcontrib><title>Predictive Sampling: Real-time Behaviour Synthesis with MuJoCo</title><description>We introduce MuJoCo MPC (MJPC), an open-source, interactive application and
software framework for real-time predictive control, based on MuJoCo physics.
MJPC allows the user to easily author and solve complex robotics tasks, and
currently supports three shooting-based planners: derivative-based iLQG and
Gradient Descent, and a simple derivative-free method we call Predictive
Sampling. Predictive Sampling was designed as an elementary baseline, mostly
for its pedagogical value, but turned out to be surprisingly competitive with
the more established algorithms. This work does not present algorithmic
advances, and instead, prioritises performant algorithms, simple code, and
accessibility of model-based methods via intuitive and interactive software.
MJPC is available at: github.com/deepmind/mujoco_mpc, a video summary can be
viewed at: dpmd.ai/mjpc.</description><subject>Computer Science - Robotics</subject><subject>Computer Science - Systems and Control</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotz8tOwzAUBFBvWKDCB7DCP5Dgtx0WSBDxVBGIdh_dxNfEUtJUThro31MKm5nFSCMdQi44y5XTml1B-o5zLgQXOWNa8VNy857Qx2aKM9IV9Nsubj6v6QdCl02xR3qHLcxx2CW62m-mFsc40q84tfR19zKUwxk5CdCNeP7fC7J-uF-XT9ny7fG5vF1mYCzPvEETmEOlRQBvmAFZ26bQXIv6EMxY57ySRcFrc5hFI0MA2xhnA1deSLkgl3-3R0C1TbGHtK9-IdURIn8AI4pCIA</recordid><startdate>20221201</startdate><enddate>20221201</enddate><creator>Howell, Taylor</creator><creator>Gileadi, Nimrod</creator><creator>Tunyasuvunakool, Saran</creator><creator>Zakka, Kevin</creator><creator>Erez, Tom</creator><creator>Tassa, Yuval</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20221201</creationdate><title>Predictive Sampling: Real-time Behaviour Synthesis with MuJoCo</title><author>Howell, Taylor ; Gileadi, Nimrod ; Tunyasuvunakool, Saran ; Zakka, Kevin ; Erez, Tom ; Tassa, Yuval</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a671-d6e6f08e452fad606a3b7c95152b51506788d43991b6d602c3ffa7c687f14d233</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Computer Science - Robotics</topic><topic>Computer Science - Systems and Control</topic><toplevel>online_resources</toplevel><creatorcontrib>Howell, Taylor</creatorcontrib><creatorcontrib>Gileadi, Nimrod</creatorcontrib><creatorcontrib>Tunyasuvunakool, Saran</creatorcontrib><creatorcontrib>Zakka, Kevin</creatorcontrib><creatorcontrib>Erez, Tom</creatorcontrib><creatorcontrib>Tassa, Yuval</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Howell, Taylor</au><au>Gileadi, Nimrod</au><au>Tunyasuvunakool, Saran</au><au>Zakka, Kevin</au><au>Erez, Tom</au><au>Tassa, Yuval</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Predictive Sampling: Real-time Behaviour Synthesis with MuJoCo</atitle><date>2022-12-01</date><risdate>2022</risdate><abstract>We introduce MuJoCo MPC (MJPC), an open-source, interactive application and
software framework for real-time predictive control, based on MuJoCo physics.
MJPC allows the user to easily author and solve complex robotics tasks, and
currently supports three shooting-based planners: derivative-based iLQG and
Gradient Descent, and a simple derivative-free method we call Predictive
Sampling. Predictive Sampling was designed as an elementary baseline, mostly
for its pedagogical value, but turned out to be surprisingly competitive with
the more established algorithms. This work does not present algorithmic
advances, and instead, prioritises performant algorithms, simple code, and
accessibility of model-based methods via intuitive and interactive software.
MJPC is available at: github.com/deepmind/mujoco_mpc, a video summary can be
viewed at: dpmd.ai/mjpc.</abstract><doi>10.48550/arxiv.2212.00541</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | DOI: 10.48550/arxiv.2212.00541 |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_arxiv_primary_2212_00541 |
| source | arXiv.org |
| subjects | Computer Science - Robotics Computer Science - Systems and Control |
| title | Predictive Sampling: Real-time Behaviour Synthesis with MuJoCo |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-08T21%3A46%3A44IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Predictive%20Sampling:%20Real-time%20Behaviour%20Synthesis%20with%20MuJoCo&rft.au=Howell,%20Taylor&rft.date=2022-12-01&rft_id=info:doi/10.48550/arxiv.2212.00541&rft_dat=%3Carxiv_GOX%3E2212_00541%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |