{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:58:38Z","timestamp":1773802718213,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"22","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>Diffusion policies have recently shown great promise for generating actions in robotic manipulation. However, existing approaches often rely on global instructions to produce short-term control signals, which can result in misalignment in action generation. We conjecture that the primitive skills, referred to as fine-grained, short-horizon manipulations, such as \"move up\" and \"open the gripper\", provide a more intuitive and effective interface for robot learning. To bridge this gap, we propose SDP, a skill-conditioned diffusion policy that integrates interpretable skill learning with conditional action planning. SDP abstracts eight reusable primitive skills across tasks and employs a vision-language model to extract discrete representations from visual observations and language instructions. Based on the representations, a lightweight router network is designed to assign a desired primitive skill for each state, which helps construct a single-skill policy to generate skill-aligned actions. By decomposing complex tasks into a sequence of primitive skills and selecting a single-skill policy, the proposed SDP ensures skill-consistent behavior across diverse tasks.\nExtensive experiments on two challenging simulation benchmarks and real-world robot deployments demonstrate that SDP consistently outperforms state-of-the-art methods, providing a new paradigm for skill-based robot learning with diffusion policies.<\/jats:p>","DOI":"10.1609\/aaai.v40i22.38889","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:58:52Z","timestamp":1773795532000},"page":"18262-18270","source":"Crossref","is-referenced-by-count":0,"title":["Learning Diffusion Policy from Primitive Skills for Robot Manipulation"],"prefix":"10.1609","volume":"40","author":[{"given":"Zhihao","family":"Gu","sequence":"first","affiliation":[]},{"given":"Ming","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Difan","family":"Zou","sequence":"additional","affiliation":[]},{"given":"Dong","family":"Xu","sequence":"additional","affiliation":[]}],"member":"9382","published-online":{"date-parts":[[2026,3,14]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/38889\/42851","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/38889\/42851","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:58:52Z","timestamp":1773795532000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/38889"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"22","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i22.38889","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,14]]}}}