{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T14:55:33Z","timestamp":1784300133186,"version":"3.55.0"},"reference-count":42,"publisher":"Association for Computing Machinery (ACM)","issue":"4","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2025,8,1]]},"abstract":"<jats:p>We present Diffuse-CLoC, a guided diffusion framework for physics-based look-ahead control that enables intuitive, steerable, and physically realistic motion generation. While existing kinematics motion generation with diffusion models offer intuitive steering capabilities with inference-time conditioning, they often fail to produce physically viable motions. In contrast, recent diffusion-based control policies have shown promise in generating physically realizable motion sequences, but the lack of kinematics prediction limits their steerability. Diffuse-CLoC addresses these challenges through a key insight: modeling the joint distribution of states and actions within a single diffusion model makes action generation steerable by conditioning it on the predicted states. This approach allows us to leverage established conditioning techniques from kinematic motion generation while producing physically realistic motions. As a result, we achieve planning capabilities without the need for a high-level planner. Our method handles a diverse set of unseen long-horizon downstream tasks through a single pre-trained model, including static and dynamic obstacle avoidance, motion in-betweening, and task-space control. Experimental results show that our method significantly outperforms the traditional hierarchical framework of high-level motion diffusion and low-level tracking.<\/jats:p>","DOI":"10.1145\/3731206","type":"journal-article","created":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T04:02:22Z","timestamp":1753588942000},"page":"1-12","update-policy":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Diffuse-CLoC: Guided Diffusion for Physics-based Character Look-ahead Control"],"prefix":"10.1145","volume":"44","author":[{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0009-0005-0714-3711","authenticated-orcid":false,"given":"Xiaoyu","family":"Huang","sequence":"first","affiliation":[{"name":"University of California Berkeley, Berkeley, USA"},{"name":"Robotics and AI Institute, Boston, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0001-9252-2428","authenticated-orcid":false,"given":"Takara","family":"Truong","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, USA"},{"name":"Robotics and AI Institute, Boston, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0009-0009-3612-1203","authenticated-orcid":false,"given":"Yunbo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Robotics and AI Institute, Boston, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0009-0006-6671-3240","authenticated-orcid":false,"given":"Fangzhou","family":"Yu","sequence":"additional","affiliation":[{"name":"Robotics and AI Institute, Boston, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0002-9935-8787","authenticated-orcid":false,"given":"Jean Pierre","family":"Sleiman","sequence":"additional","affiliation":[{"name":"Robotics and AI Institute, Boston, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0002-1778-883X","authenticated-orcid":false,"given":"Jessica","family":"Hodgins","sequence":"additional","affiliation":[{"name":"Robotics and AI Institute, Boston, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0002-5346-3637","authenticated-orcid":false,"given":"Koushil","family":"Sreenath","sequence":"additional","affiliation":[{"name":"Robotics and AI Institute, Boston, USA"},{"name":"University of California Berkeley, Boston, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0001-8269-6272","authenticated-orcid":false,"given":"Farbod","family":"Farshidian","sequence":"additional","affiliation":[{"name":"Robotics and AI Institute, Boston, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,7,27]]},"reference":[{"key":"e_1_2_2_1_1","unstructured":"Anurag Ajay Yilun Du Abhi Gupta Joshua Tenenbaum Tommi Jaakkola and Pulkit Agrawal. 2023. Is Conditional Generative Modeling all you need for Decision-Making? https:\/\/2.zoppoz.workers.dev:443\/https\/openreview.net\/forum?id=sP1fo2K9DFG"},{"key":"e_1_2_2_2_1","doi-asserted-by":"crossref","unstructured":"Joao Carvalho An T. Le Mark Baierl Dorothea Koert and Jan Peters. 2023. Motion Planning Diffusion: Learning and Planning of Robot Motions with Diffusion Models. 1916\u20131923 pages.","DOI":"10.1109\/IROS55552.2023.10342382"},{"key":"e_1_2_2_3_1","volume-title":"Yilun Du, Max Simchowitz, Russ Tedrake, and Vincent Sitzmann.","author":"Chen Boyuan","year":"2024","unstructured":"Boyuan Chen, Diego Marti Monso, Yilun Du, Max Simchowitz, Russ Tedrake, and Vincent Sitzmann. 2024. Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion. arXiv:2407.01392 [cs.LG] https:\/\/2.zoppoz.workers.dev:443\/https\/arxiv.org\/abs\/2407.01392"},{"key":"e_1_2_2_4_1","volume-title":"Diffusion policy: Visuomotor policy learning via action diffusion. The International Journal of Robotics Research","author":"Chi Cheng","year":"2023","unstructured":"Cheng Chi, Zhenjia Xu, Siyuan Feng, Eric Cousineau, Yilun Du, Benjamin Burchfiel, Russ Tedrake, and Shuran Song. 2023. Diffusion policy: Visuomotor policy learning via action diffusion. The International Journal of Robotics Research (2023), 02783649241273668."},{"key":"e_1_2_2_5_1","volume-title":"ACM SIGGRAPH 2024 Conference Papers. 1\u20139.","author":"Cohan Setareh","unstructured":"Setareh Cohan, Guy Tevet, Daniele Reda, Xue Bin Peng, and Michiel van de Panne. 2024. Flexible motion in-betweening with diffusion models. In ACM SIGGRAPH 2024 Conference Papers. 1\u20139."},{"key":"e_1_2_2_6_1","volume-title":"Proceedings of the 35th International Conference on Neural Information Processing Systems (NIPS '21)","author":"Dhariwal Prafulla","year":"2024","unstructured":"Prafulla Dhariwal and Alex Nichol. 2024. Diffusion models beat GANs on image synthesis. In Proceedings of the 35th International Conference on Neural Information Processing Systems (NIPS '21). Curran Associates Inc., Red Hook, NY, USA, Article 672, 15 pages."},{"key":"e_1_2_2_7_1","unstructured":"Gaoge Han Mingjiang Liang Jinglei Tang Yongkang Cheng Wei Liu and Shaoli Huang. 2024. ReinDiffuse: Crafting Physically Plausible Motions with Reinforced Diffusion Model. arXiv:2410.07296 [cs.CV] https:\/\/2.zoppoz.workers.dev:443\/https\/arxiv.org\/abs\/2410.07296"},{"key":"e_1_2_2_8_1","volume-title":"Denoising diffusion probabilistic models. Advances in neural information processing systems 33","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems 33 (2020), 6840\u20136851."},{"key":"e_1_2_2_9_1","volume-title":"Constrained Diffusion with Trust Sampling. In The Thirty-eighth Annual Conference on Neural Information Processing Systems.","author":"Ho Jonathan","year":"2021","unstructured":"Jonathan Ho and Tim Salimans. 2021. Classifier-Free Diffusion Guidance. https:\/\/2.zoppoz.workers.dev:443\/https\/openreview.net\/forum?id=qw8AKxfYbI William Huang, Yifeng Jiang, Tom Van Wouwe, and Karen Liu. 2024b. Constrained Diffusion with Trust Sampling. In The Thirty-eighth Annual Conference on Neural Information Processing Systems."},{"key":"e_1_2_2_10_1","volume-title":"8th Annual Conference on Robot Learning. https:\/\/2.zoppoz.workers.dev:443\/https\/openreview.net\/forum?id=nVJm2RdPDu","author":"Huang Xiaoyu","year":"2024","unstructured":"Xiaoyu Huang, Yufeng Chi, Ruofeng Wang, Zhongyu Li, Xue Bin Peng, Sophia Shao, Borivoje Nikolic, and Koushil Sreenath. 2024a. DiffuseLoco: Real-Time Legged Locomotion Control with Diffusion from Offline Datasets. In 8th Annual Conference on Robot Learning. https:\/\/2.zoppoz.workers.dev:443\/https\/openreview.net\/forum?id=nVJm2RdPDu"},{"key":"e_1_2_2_11_1","unstructured":"Sigmund H. H\u00f8eg Yilun Du and Olav Egeland. 2024. Streaming Diffusion Policy: Fast Policy Synthesis with Variable Noise Diffusion Models. arXiv:2406.04806 [cs.RO] https:\/\/2.zoppoz.workers.dev:443\/https\/arxiv.org\/abs\/2406.04806"},{"key":"e_1_2_2_12_1","volume-title":"Planning with Diffusion for Flexible Behavior Synthesis. 162 (17\u201323","author":"Janner Michael","year":"2022","unstructured":"Michael Janner, Yilun Du, Joshua Tenenbaum, and Sergey Levine. 2022. Planning with Diffusion for Flexible Behavior Synthesis. 162 (17\u201323 Jul 2022), 9902\u20139915. https:\/\/2.zoppoz.workers.dev:443\/https\/proceedings.mlr.press\/v162\/janner22a.html"},{"key":"e_1_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00205"},{"key":"e_1_2_2_14_1","volume-title":"AAMDM: Accelerated Auto-regressive Motion Diffusion Model. 1813\u20131823 pages.","author":"Li Tianyu","year":"2024","unstructured":"Tianyu Li, Calvin Qiao, Guanqiao Ren, KangKang Yin, and Sehoon Ha. 2024b. AAMDM: Accelerated Auto-regressive Motion Diffusion Model. 1813\u20131823 pages."},{"key":"e_1_2_2_15_1","volume-title":"Morph: A Motion-free Physics Optimization Framework for Human Motion Generation. arXiv preprint arXiv:2411.14951","author":"Li Zhuo","year":"2024","unstructured":"Zhuo Li, Mingshuang Luo, Ruibing Hou, Xin Zhao, Hao Liu, Hong Chang, Zimo Liu, and Chen Li. 2024a. Morph: A Motion-free Physics Optimization Framework for Human Motion Generation. arXiv preprint arXiv:2411.14951 (2024)."},{"key":"e_1_2_2_16_1","volume-title":"Universal Humanoid Motion Representations for Physics-Based Control. In The Twelfth International Conference on Learning Representations.","author":"Luo Zhengyi","year":"2024","unstructured":"Zhengyi Luo, Jinkun Cao, Josh Merel, Alexander Winkler, Jing Huang, Kris M Kitani, and Weipeng Xu. 2024. Universal Humanoid Motion Representations for Physics-Based Control. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01000"},{"key":"e_1_2_2_18_1","volume-title":"International Conference on Computer Vision. 5442\u20135451","author":"Mahmood Naureen","unstructured":"Naureen Mahmood, Nima Ghorbani, Nikolaus F. Troje, Gerard Pons-Moll, and Michael J. Black. 2019. AMASS: Archive of Motion Capture as Surface Shapes. In International Conference on Computer Vision. 5442\u20135451."},{"key":"e_1_2_2_19_1","doi-asserted-by":"crossref","unstructured":"GVS Mothish Manan Tayal and Shishir Kolathaya. 2024. BiRoDiff: Diffusion policies for bipedal robot locomotion on unseen terrains. arXiv:2407.05424 [cs.RO] https:\/\/2.zoppoz.workers.dev:443\/https\/arxiv.org\/abs\/2407.05424","DOI":"10.1109\/ICC64753.2024.10883743"},{"key":"e_1_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201311"},{"key":"e_1_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530110"},{"key":"e_1_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459670"},{"key":"e_1_2_2_23_1","unstructured":"Alec Radford. 2018. Improving language understanding by generative pre-training. (2018)."},{"key":"e_1_2_2_24_1","volume-title":"Schoellig","author":"R\u00f6mer Ralf","year":"2024","unstructured":"Ralf R\u00f6mer, Alexander von Rohr, and Angela P. Schoellig. 2024. Diffusion Predictive Control with Constraints. arXiv:2412.09342 [cs.RO] https:\/\/2.zoppoz.workers.dev:443\/https\/arxiv.org\/abs\/2412.09342"},{"key":"e_1_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687626"},{"key":"e_1_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.15175"},{"key":"e_1_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3658140"},{"key":"e_1_2_2_28_1","volume-title":"International Conference on Learning Representations.","author":"Song Yang","year":"2021","unstructured":"Yang Song, Jascha Sohl-Dickstein, Diederik P Kingma, Abhishek Kumar, Stefano Ermon, and Ben Poole. 2021. Score-Based Generative Modeling through Stochastic Differential Equations. In International Conference on Learning Representations."},{"key":"e_1_2_2_29_1","volume-title":"Amit H. Bermano, and Michiel van de Panne.","author":"Tevet Guy","year":"2024","unstructured":"Guy Tevet, Sigal Raab, Setareh Cohan, Daniele Reda, Zhengyi Luo, Xue Bin Peng, Amit H. Bermano, and Michiel van de Panne. 2024. CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character control. arXiv:2410.03441 [cs.CV] https:\/\/2.zoppoz.workers.dev:443\/https\/arxiv.org\/abs\/2410.03441"},{"key":"e_1_2_2_30_1","volume-title":"Human Motion Diffusion Model. In The Eleventh International Conference on Learning Representations.","author":"Tevet Guy","year":"2023","unstructured":"Guy Tevet, Sigal Raab, Brian Gordon, Yoni Shafir, Daniel Cohen-or, and Amit Haim Bermano. 2023. Human Motion Diffusion Model. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687683"},{"key":"e_1_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00051"},{"key":"e_1_2_2_33_1","unstructured":"Zhendong Wang Zhaoshuo Li Ajay Mandlekar Zhenjia Xu Jiaojiao Fan Yashraj Narang Linxi Fan Yuke Zhu Yogesh Balaji Mingyuan Zhou Ming-Yu Liu and Yu Zeng. 2024. One-Step Diffusion Policy: Fast Visuomotor Policies via Diffusion Distillation. arXiv:2410.21257 [cs.RO] https:\/\/2.zoppoz.workers.dev:443\/https\/arxiv.org\/abs\/2410.21257"},{"key":"e_1_2_2_34_1","volume-title":"Proceedings of the 28th international conference on machine learning (ICML-11)","author":"Welling Max","year":"2011","unstructured":"Max Welling and Yee W Teh. 2011. Bayesian learning via stochastic gradient Langevin dynamics. In Proceedings of the 28th international conference on machine learning (ICML-11). 681\u2013688."},{"key":"e_1_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530067"},{"key":"e_1_2_2_36_1","unstructured":"Zhaoming Xie Jonathan Tseng Sebastian Starke Michiel van de Panne and C. Karen Liu. 2023. Hierarchical Planning and Control for Box Loco-Manipulation. 18 pages."},{"key":"e_1_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555434"},{"key":"e_1_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3658137"},{"key":"e_1_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14741"},{"key":"e_1_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657515"},{"key":"e_1_2_2_41_1","doi-asserted-by":"publisher","unstructured":"Tony Z. Zhao Vikash Kumar Sergey Levine and Chelsea Finn. 2023. Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware. 10.15607\/RSS.2023.XIX.016","DOI":"10.15607\/RSS.2023.XIX.016"},{"key":"e_1_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3618397"}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/dl.acm.org\/doi\/pdf\/10.1145\/3731206","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T17:54:24Z","timestamp":1774634064000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/dl.acm.org\/doi\/10.1145\/3731206"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,27]]},"references-count":42,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,8,1]]}},"alternative-id":["10.1145\/3731206"],"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1145\/3731206","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,27]]},"assertion":[{"value":"2025-07-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}