{"id":4043,"date":"2022-07-15T15:49:50","date_gmt":"2022-07-15T07:49:50","guid":{"rendered":"https:\/\/inventec2.mjitec.tw\/?page_id=4043"},"modified":"2023-07-18T14:07:26","modified_gmt":"2023-07-18T06:07:26","slug":"carl","status":"publish","type":"page","link":"https:\/\/inventec2.mjitec.tw\/zh-hans\/ai\/carl\/","title":{"rendered":"CARL"},"content":{"rendered":"

[vc_row full_width=”stretch_row”][vc_column]

\r\n
<\/div>\t\t\t\r\n\t\t\t<\/div>[vc_row_inner el_class=”md-full-col”][vc_column_inner el_class=”m_p” width=”1\/2″]\n
\n \t
\n \t\t\n\t \n\t

CARL: Controllable Agent with Reinforcement Learning for Quadruped Locomotion <\/h2>\n\t <\/div><\/div>[vc_column_text css=”.vc_custom_1660543437732{margin-bottom: 20px !important;}”]<\/p>\n
\n

ACM Transactions on Graphics (Proceedings of SIGGRAPH 2020)<\/p>\n<\/div>\n

[\/vc_column_text][vc_column_text css=”.vc_custom_1660543444964{margin-bottom: 5px !important;}”]<\/p>\n

\n
\u4f5c\u8005<\/h6>\n<\/div>\n

[\/vc_column_text][vc_column_text css=”.vc_custom_1660543451981{margin-bottom: 20px !important;}”]<\/p>\n

\n

Luo, Ying-Sheng* and Soeseno, Jonathan Hans* and Chen, Trista Pei-Chun and Chen, Wei-Chao (*denotes joint first authors)<\/p>\n<\/div>\n

[\/vc_column_text][vc_column_text css=”.vc_custom_1660543458515{margin-bottom: 5px !important;}”]<\/p>\n

\n
\u53d1\u8868\u65e5\u671f<\/h6>\n<\/div>\n

[\/vc_column_text][vc_column_text]<\/p>\n

\n

Jul-20<\/p>\n<\/div>\n

[\/vc_column_text][\/vc_column_inner][vc_column_inner el_class=”m_p” width=”1\/2″][vc_single_image image=”2519″ img_size=”full”][\/vc_column_inner][\/vc_row_inner][\/vc_column][\/vc_row][vc_row][vc_column]

\r\n
<\/div>\t\t\t\r\n\t\t\t<\/div>[\/vc_column][\/vc_row][vc_row full_width=”stretch_row”][vc_column][vc_row_inner content_placement=”top” css=”.vc_custom_1657794580528{margin-bottom: 20px !important;}”][vc_column_inner el_class=”m_p paragraph_title” width=”1\/3″]\n
\n \t
\n \t\t\n\t \n\t

\u6982\u8981 <\/h2>\n\t <\/div><\/div>[\/vc_column_inner][vc_column_inner el_class=”m_p” width=”2\/3″][vc_column_text]Motion synthesis in a dynamic environment has been a long-standing problem for character animation. Methods using motion capture data tend to scale poorly in complex environments because of their larger capturing and labeling requirement.<\/p>\n

Physics-based controllers are effective in this regard, albeit less controllable. In this paper, we present CARL, a quadruped agent that can be controlled with high-level directives and react naturally to dynamic environments. Starting with an agent that can imitate individual animation clips, we use Generative Adversarial Networks to adapt high-level controls, such as speed and heading, to action distributions that correspond to the original animations.<\/p>\n

Further fine-tuning through the deep reinforcement learning enables the agent to recover from unseen external perturbations while producing smooth transitions. It then becomes straightforward to create autonomous agents in dynamic environments by adding navigation modules over the entire process. We evaluate our approach by measuring the agent\u2019s ability to follow user control and provide a visual analysis of the generated motion to show its effectiveness.[\/vc_column_text][\/vc_column_inner][\/vc_row_inner][vc_row_inner content_placement=”middle” el_class=”md-full-col video_wrap”][vc_column_inner el_class=”m_p”][vc_raw_html]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[\/vc_raw_html][\/vc_column_inner][\/vc_row_inner][\/vc_column][\/vc_row][vc_row][vc_column]

\r\n
<\/div>\t\t\t\r\n\t\t\t<\/div>[\/vc_column][\/vc_row][vc_row][vc_column width=”1\/3″ el_class=”m_p keyword_title”][vc_column_text]<\/p>\n

\u5173\u952e\u5b57<\/h2>\n

[\/vc_column_text][\/vc_column][vc_column width=”2\/3″ el_class=”m_p keyword”][vc_row_inner content_placement=”middle”][vc_column_inner width=”1\/3″][vc_raw_html]JTNDdWwlMjBjbGFzcyUzRCUyMnN0eWxlbGlzdGluZyUyMiUzRSUwQSUyMCUwOSUzQ2xpJTIwc3R5bGUlM0QlMjJsaW5lLWhlaWdodCUzQTM0cHglM0IlMjIlM0VQaHlzaWNhbCUyMFNpbXVsYXRpb24lM0MlMkZsaSUzRSUwQSUzQyUyRnVsJTNF[\/vc_raw_html][\/vc_column_inner][vc_column_inner width=”1\/3″][vc_raw_html]JTNDdWwlMjBjbGFzcyUzRCUyMnN0eWxlbGlzdGluZyUyMiUzRSUwQSUyMCUwOSUzQ2xpJTIwc3R5bGUlM0QlMjJsaW5lLWhlaWdodCUzQTM0cHglM0IlMjIlM0VSZWluZm9yY2VtZW50JTIwTGVhcm5pbmclM0MlMkZsaSUzRSUwQSUzQyUyRnVsJTNF[\/vc_raw_html][\/vc_column_inner][vc_column_inner width=”1\/3″][vc_raw_html]JTNDdWwlMjBjbGFzcyUzRCUyMnN0eWxlbGlzdGluZyUyMiUzRSUwQSUyMCUwOSUwQSUzQyUyRnVsJTNF[\/vc_raw_html][\/vc_column_inner][\/vc_row_inner][\/vc_column][\/vc_row][vc_row][vc_column]

\r\n
<\/div>\t\t\t\r\n\t\t\t<\/div>[\/vc_column][\/vc_row][vc_row full_width=”stretch_row” el_class=”bg” css=”.vc_custom_1657248474326{padding-top: 50px !important;padding-bottom: 50px !important;}”][vc_column][vc_column_text css=”.vc_custom_1660027019904{margin-bottom: 20px !important;}”]<\/p>\n

\u4e0b\u8f7d\u4e0e\u5206\u4eab<\/h3>\n

[\/vc_column_text][vc_row_inner content_placement=”middle”][vc_column_inner el_class=”download_btn_wrap”][vc_btn title=”PDF” style=”flat” color=”white” align=”center” link=”url:https%3A%2F%2Farxiv.org%2Fpdf%2F2005.03288.pdf|target:_blank” el_class=”download_btn”][vc_btn title=”\u539f\u59cb\u7801” style=”flat” color=”white” align=”center” link=”url:https%3A%2F%2Fgithub.com%2Finventec-ai-center%2Fcarl-siggraph2020|target:_blank” el_class=”download_btn”][\/vc_column_inner][\/vc_row_inner][\/vc_column][\/vc_row]<\/p>\n<\/div>","protected":false},"excerpt":{"rendered":"

[vc_row full_width=”stretch_row”][vc_column…<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":4976,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-4043","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/inventec2.mjitec.tw\/zh-hans\/wp-json\/wp\/v2\/pages\/4043","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/inventec2.mjitec.tw\/zh-hans\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/inventec2.mjitec.tw\/zh-hans\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/inventec2.mjitec.tw\/zh-hans\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/inventec2.mjitec.tw\/zh-hans\/wp-json\/wp\/v2\/comments?post=4043"}],"version-history":[{"count":0,"href":"https:\/\/inventec2.mjitec.tw\/zh-hans\/wp-json\/wp\/v2\/pages\/4043\/revisions"}],"up":[{"embeddable":true,"href":"https:\/\/inventec2.mjitec.tw\/zh-hans\/wp-json\/wp\/v2\/pages\/4976"}],"wp:attachment":[{"href":"https:\/\/inventec2.mjitec.tw\/zh-hans\/wp-json\/wp\/v2\/media?parent=4043"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}