Robust Quadrupedal Locomotion on Sloped Terrains: A Linear Policy Approach
In this paper, with a view toward fast deployment of locomotion gaits in low-cost hardware, we use a linear policy for realizing end-foot trajectories in the quadruped robot, Stoch $2$. In particular, the parameters of the end-foot trajectories are shaped via a linear feedback policy that takes the...
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 | Paigwar, Kartik Krishna, Lokesh Tirumala, Sashank Khetan, Naman Sagi, Aditya Joglekar, Ashish Bhatnagar, Shalabh Ghosal, Ashitava Amrutur, Bharadwaj Kolathaya, Shishir |
| description | In this paper, with a view toward fast deployment of locomotion gaits in
low-cost hardware, we use a linear policy for realizing end-foot trajectories
in the quadruped robot, Stoch $2$. In particular, the parameters of the
end-foot trajectories are shaped via a linear feedback policy that takes the
torso orientation and the terrain slope as inputs. The corresponding desired
joint angles are obtained via an inverse kinematics solver and tracked via a
PID control law. Augmented Random Search, a model-free and a gradient-free
learning algorithm is used to train this linear policy. Simulation results show
that the resulting walking is robust to terrain slope variations and external
pushes. This methodology is not only computationally light-weight but also uses
minimal sensing and actuation capabilities in the robot, thereby justifying the
approach. |
| doi_str_mv | 10.48550/arxiv.2010.16342 |
| format | Article |
| fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2010_16342</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2010_16342</sourcerecordid><originalsourceid>FETCH-LOGICAL-a672-19ad3e3498408860bf0de974b6457b1e56c1c1026d713d4373381d9a9adab2913</originalsourceid><addsrcrecordid>eNotj8lqwzAYhHXJoaR9gJ6iF3CizVp6M6Erhiap7-bXEipwLCPHpXn7umlhYOCDGfgQuqdkLXRZkg3k7_i1ZmQGVHLBbtDbIdlpPOP9BD5PQ_DQ4Tq5dErnmHo856NLM8ZNyBliPz7gCtexD5DxLnXRXXA1DDmB-7xFiyN0Y7j77yVqnh6b7UtRvz-_bqu6AKlYQQ14HrgwWhCtJbFH4oNRwkpRKktDKR11lDDpFeVecMW5pt7APAPLDOVLtPq7vcq0Q44nyJf2V6q9SvEf2jtGMQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Robust Quadrupedal Locomotion on Sloped Terrains: A Linear Policy Approach</title><source>arXiv.org</source><creator>Paigwar, Kartik ; Krishna, Lokesh ; Tirumala, Sashank ; Khetan, Naman ; Sagi, Aditya ; Joglekar, Ashish ; Bhatnagar, Shalabh ; Ghosal, Ashitava ; Amrutur, Bharadwaj ; Kolathaya, Shishir</creator><creatorcontrib>Paigwar, Kartik ; Krishna, Lokesh ; Tirumala, Sashank ; Khetan, Naman ; Sagi, Aditya ; Joglekar, Ashish ; Bhatnagar, Shalabh ; Ghosal, Ashitava ; Amrutur, Bharadwaj ; Kolathaya, Shishir</creatorcontrib><description>In this paper, with a view toward fast deployment of locomotion gaits in
low-cost hardware, we use a linear policy for realizing end-foot trajectories
in the quadruped robot, Stoch $2$. In particular, the parameters of the
end-foot trajectories are shaped via a linear feedback policy that takes the
torso orientation and the terrain slope as inputs. The corresponding desired
joint angles are obtained via an inverse kinematics solver and tracked via a
PID control law. Augmented Random Search, a model-free and a gradient-free
learning algorithm is used to train this linear policy. Simulation results show
that the resulting walking is robust to terrain slope variations and external
pushes. This methodology is not only computationally light-weight but also uses
minimal sensing and actuation capabilities in the robot, thereby justifying the
approach.</description><identifier>DOI: 10.48550/arxiv.2010.16342</identifier><language>eng</language><subject>Computer Science - Artificial Intelligence ; Computer Science - Learning ; Computer Science - Robotics ; Computer Science - Systems and Control</subject><creationdate>2020-10</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,777,882</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2010.16342$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2010.16342$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Paigwar, Kartik</creatorcontrib><creatorcontrib>Krishna, Lokesh</creatorcontrib><creatorcontrib>Tirumala, Sashank</creatorcontrib><creatorcontrib>Khetan, Naman</creatorcontrib><creatorcontrib>Sagi, Aditya</creatorcontrib><creatorcontrib>Joglekar, Ashish</creatorcontrib><creatorcontrib>Bhatnagar, Shalabh</creatorcontrib><creatorcontrib>Ghosal, Ashitava</creatorcontrib><creatorcontrib>Amrutur, Bharadwaj</creatorcontrib><creatorcontrib>Kolathaya, Shishir</creatorcontrib><title>Robust Quadrupedal Locomotion on Sloped Terrains: A Linear Policy Approach</title><description>In this paper, with a view toward fast deployment of locomotion gaits in
low-cost hardware, we use a linear policy for realizing end-foot trajectories
in the quadruped robot, Stoch $2$. In particular, the parameters of the
end-foot trajectories are shaped via a linear feedback policy that takes the
torso orientation and the terrain slope as inputs. The corresponding desired
joint angles are obtained via an inverse kinematics solver and tracked via a
PID control law. Augmented Random Search, a model-free and a gradient-free
learning algorithm is used to train this linear policy. Simulation results show
that the resulting walking is robust to terrain slope variations and external
pushes. This methodology is not only computationally light-weight but also uses
minimal sensing and actuation capabilities in the robot, thereby justifying the
approach.</description><subject>Computer Science - Artificial Intelligence</subject><subject>Computer Science - Learning</subject><subject>Computer Science - Robotics</subject><subject>Computer Science - Systems and Control</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj8lqwzAYhHXJoaR9gJ6iF3CizVp6M6Erhiap7-bXEipwLCPHpXn7umlhYOCDGfgQuqdkLXRZkg3k7_i1ZmQGVHLBbtDbIdlpPOP9BD5PQ_DQ4Tq5dErnmHo856NLM8ZNyBliPz7gCtexD5DxLnXRXXA1DDmB-7xFiyN0Y7j77yVqnh6b7UtRvz-_bqu6AKlYQQ14HrgwWhCtJbFH4oNRwkpRKktDKR11lDDpFeVecMW5pt7APAPLDOVLtPq7vcq0Q44nyJf2V6q9SvEf2jtGMQ</recordid><startdate>20201030</startdate><enddate>20201030</enddate><creator>Paigwar, Kartik</creator><creator>Krishna, Lokesh</creator><creator>Tirumala, Sashank</creator><creator>Khetan, Naman</creator><creator>Sagi, Aditya</creator><creator>Joglekar, Ashish</creator><creator>Bhatnagar, Shalabh</creator><creator>Ghosal, Ashitava</creator><creator>Amrutur, Bharadwaj</creator><creator>Kolathaya, Shishir</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20201030</creationdate><title>Robust Quadrupedal Locomotion on Sloped Terrains: A Linear Policy Approach</title><author>Paigwar, Kartik ; Krishna, Lokesh ; Tirumala, Sashank ; Khetan, Naman ; Sagi, Aditya ; Joglekar, Ashish ; Bhatnagar, Shalabh ; Ghosal, Ashitava ; Amrutur, Bharadwaj ; Kolathaya, Shishir</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a672-19ad3e3498408860bf0de974b6457b1e56c1c1026d713d4373381d9a9adab2913</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Computer Science - Artificial Intelligence</topic><topic>Computer Science - Learning</topic><topic>Computer Science - Robotics</topic><topic>Computer Science - Systems and Control</topic><toplevel>online_resources</toplevel><creatorcontrib>Paigwar, Kartik</creatorcontrib><creatorcontrib>Krishna, Lokesh</creatorcontrib><creatorcontrib>Tirumala, Sashank</creatorcontrib><creatorcontrib>Khetan, Naman</creatorcontrib><creatorcontrib>Sagi, Aditya</creatorcontrib><creatorcontrib>Joglekar, Ashish</creatorcontrib><creatorcontrib>Bhatnagar, Shalabh</creatorcontrib><creatorcontrib>Ghosal, Ashitava</creatorcontrib><creatorcontrib>Amrutur, Bharadwaj</creatorcontrib><creatorcontrib>Kolathaya, Shishir</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Paigwar, Kartik</au><au>Krishna, Lokesh</au><au>Tirumala, Sashank</au><au>Khetan, Naman</au><au>Sagi, Aditya</au><au>Joglekar, Ashish</au><au>Bhatnagar, Shalabh</au><au>Ghosal, Ashitava</au><au>Amrutur, Bharadwaj</au><au>Kolathaya, Shishir</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Robust Quadrupedal Locomotion on Sloped Terrains: A Linear Policy Approach</atitle><date>2020-10-30</date><risdate>2020</risdate><abstract>In this paper, with a view toward fast deployment of locomotion gaits in
low-cost hardware, we use a linear policy for realizing end-foot trajectories
in the quadruped robot, Stoch $2$. In particular, the parameters of the
end-foot trajectories are shaped via a linear feedback policy that takes the
torso orientation and the terrain slope as inputs. The corresponding desired
joint angles are obtained via an inverse kinematics solver and tracked via a
PID control law. Augmented Random Search, a model-free and a gradient-free
learning algorithm is used to train this linear policy. Simulation results show
that the resulting walking is robust to terrain slope variations and external
pushes. This methodology is not only computationally light-weight but also uses
minimal sensing and actuation capabilities in the robot, thereby justifying the
approach.</abstract><doi>10.48550/arxiv.2010.16342</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | DOI: 10.48550/arxiv.2010.16342 |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_arxiv_primary_2010_16342 |
| source | arXiv.org |
| subjects | Computer Science - Artificial Intelligence Computer Science - Learning Computer Science - Robotics Computer Science - Systems and Control |
| title | Robust Quadrupedal Locomotion on Sloped Terrains: A Linear Policy Approach |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-19T10%3A48%3A29IST&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=Robust%20Quadrupedal%20Locomotion%20on%20Sloped%20Terrains:%20A%20Linear%20Policy%20Approach&rft.au=Paigwar,%20Kartik&rft.date=2020-10-30&rft_id=info:doi/10.48550/arxiv.2010.16342&rft_dat=%3Carxiv_GOX%3E2010_16342%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 |