{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T02:58:36Z","timestamp":1777604316764,"version":"3.51.4"},"reference-count":55,"publisher":"Association for Computing Machinery (ACM)","issue":"4","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. ACM Comput. Graph. Interact. Tech."],"published-print":{"date-parts":[[2025,8,31]]},"abstract":"<jats:p>\n            Physics-based characters need to plan their movements over-and-around obstacles. Diffusion models offer a possible solution, as they allow a motion planner to sample from a potentially diverse distribution of possible futures. However, they may also generate flawed plans because some samples may not satisfy hard constraints that exist only implicitly in the training data, e.g., guaranteeing balance or obstacle clearance. We propose learned\n            <jats:italic toggle=\"yes\">viability filters<\/jats:italic>\n            that can efficiently predict the future success of a given plan, i.e., diffusion sample, and thereby enforce an implicit future-success constraint. Multiple viability filters can also be composed together at run-time to take multiple potential constraints into consideration. We demonstrate the approach on detailed footstep planning for 3D human locomotion tasks, showing the effectiveness of the viability filters in performing online planning for box-climbing, step-over walls, and obstacle avoidance. We compare to a number of alternative planning methods including reinforcement learning and return-conditioned diffusion, and further show that using viability filters is significantly faster than guidance-based diffusion prediction.\n          <\/jats:p>","DOI":"10.1145\/3747864","type":"journal-article","created":{"date-parts":[[2025,8,8]],"date-time":"2025-08-08T15:33:31Z","timestamp":1754667211000},"page":"1-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Diffusion-based Planning with Learned Viability Filters 62"],"prefix":"10.1145","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-4172-6151","authenticated-orcid":false,"given":"Nicholas","family":"Ioannidis","sequence":"first","affiliation":[{"name":"Computer Science","place":["Vancouver, Canada"]},{"name":"University of British Columbia","place":["Vancouver, Canada"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7101-0519","authenticated-orcid":false,"given":"Daniele","family":"Reda","sequence":"additional","affiliation":[{"name":"Wayve","place":["Vancouver, Canada"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6381-7698","authenticated-orcid":false,"given":"Setareh","family":"Cohan","sequence":"additional","affiliation":[{"name":"Computer Science","place":["Vancouver, Canada"]},{"name":"University of British Columbia","place":["Vancouver, Canada"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9123-3672","authenticated-orcid":false,"given":"Michiel","family":"van de Panne","sequence":"additional","affiliation":[{"name":"Computer Science","place":["Vancouver, Canada"]},{"name":"University of British Columbia","place":["Vancouver, Canada"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,8,8]]},"reference":[{"key":"e_1_3_2_2_1","unstructured":"Anurag Ajay Yilun Du Abhi Gupta Joshua Tenenbaum Tommi Jaakkola and Pulkit Agrawal. 2022. Is conditional generative modeling all you need for decision-making? arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2211.15657 (2022)."},{"key":"e_1_3_2_3_1","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140223"},{"key":"e_1_3_2_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-16684-6"},{"key":"e_1_3_2_5_1","doi-asserted-by":"crossref","unstructured":"Jan Carius Ren\u00e9 Ranftl Farbod Farshidian and Marco Hutter. 2022. Constrained stochastic optimal control with learned importance sampling: A path integral approach. The International Journal of Robotics Research 41 2 (2022) 189\u2013209.","DOI":"10.1177\/02783649211047890"},{"key":"e_1_3_2_6_1","doi-asserted-by":"crossref","unstructured":"Cheng Chi Siyuan Feng Yilun Du Zhenjia Xu Eric Cousineau Benjamin Burchfiel and Shuran Song. 2023. Diffusion Policy: Visuomotor Policy Learning via Action Diffusion. arxiv:https:\/\/arXiv.org\/abs\/2303.04137\u00a0[cs.RO]","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"e_1_3_2_7_1","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Christopher Jacob\u00a0K","year":"2024","unstructured":"Jacob\u00a0K Christopher, Stephen Baek, and Ferdinando Fioretto. 2024. Constrained synthesis with projected diffusion models. In The Thirty-eighth Annual Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_8_1","unstructured":"Prafulla Dhariwal and Alexander Nichol. 2021. Diffusion models beat gans on image synthesis. Advances in neural information processing systems 34 (2021) 8780\u20138794."},{"key":"e_1_3_2_9_1","unstructured":"Nic Fishman Leo Klarner Emile Mathieu Michael Hutchinson and Valentin De\u00a0Bortoli. 2024. Metropolis sampling for constrained diffusion models. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_2_10_1","unstructured":"William Harvey Saeid Naderiparizi Vaden Masrani Christian Weilbach and Frank Wood. 2022. Flexible diffusion modeling of long videos. Advances in Neural Information Processing Systems 35 (2022) 27953\u201327965."},{"key":"e_1_3_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_12_1","unstructured":"Jonathan Ho Ajay Jain and Pieter Abbeel. 2020. Denoising Diffusion Probabilistic Models. arXiv preprint arxiv:https:\/\/arXiv.org\/abs\/2006.11239 (2020)."},{"key":"e_1_3_2_13_1","unstructured":"Jonathan Ho and Tim Salimans. 2022. Classifier-free diffusion guidance. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2207.12598 (2022)."},{"key":"e_1_3_2_14_1","unstructured":"Jonathan Ho Tim Salimans Alexey Gritsenko William Chan Mohammad Norouzi and David\u00a0J Fleet. 2022. Video diffusion models. Advances in Neural Information Processing Systems 35 (2022) 8633\u20138646."},{"key":"e_1_3_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611316"},{"key":"e_1_3_2_16_1","unstructured":"Taylor Howell Nimrod Gileadi Saran Tunyasuvunakool Kevin Zakka Tom Erez and Yuval Tassa. 2022. Predictive sampling: Real-time behaviour synthesis with mujoco. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2212.00541 (2022)."},{"key":"e_1_3_2_17_1","unstructured":"Xiaoyu Huang Yufeng Chi Ruofeng Wang Zhongyu Li Xue\u00a0Bin Peng Sophia Shao Borivoje Nikolic and Koushil Sreenath. 2024a. DiffuseLoco: Real-Time Legged Locomotion Control with Diffusion from Offline Datasets. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.19264 (2024)."},{"key":"e_1_3_2_18_1","unstructured":"Zhiyu Huang Xinshuo Weng Maximilian Igl Yuxiao Chen Yulong Cao Boris Ivanovic Marco Pavone and Chen Lv. 2024b. Gen-Drive: Enhancing Diffusion Generative Driving Policies with Reward Modeling and Reinforcement Learning Fine-tuning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.05582 (2024)."},{"key":"e_1_3_2_19_1","volume-title":"International Conference on Machine Learning","author":"Janner Michael","year":"2022","unstructured":"Michael Janner, Yilun Du, Joshua Tenenbaum, and Sergey Levine. 2022. Planning with Diffusion for Flexible Behavior Synthesis. In International Conference on Machine Learning."},{"key":"e_1_3_2_20_1","doi-asserted-by":"crossref","unstructured":"Seunghun Jeon Moonkyu Jung Suyoung Choi Beomjoon Kim and Jemin Hwangbo. 2023. Learning whole-body manipulation for quadrupedal robot. IEEE Robotics and Automation Letters 9 1 (2023) 699\u2013706.","DOI":"10.1109\/LRA.2023.3335777"},{"key":"e_1_3_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00205"},{"key":"e_1_3_2_22_1","unstructured":"Diederik\u00a0P Kingma. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1412.6980 (2014)."},{"key":"e_1_3_2_23_1","unstructured":"Zhifeng Kong Wei Ping Jiaji Huang Kexin Zhao and Bryan Catanzaro. 2020. Diffwave: A versatile diffusion model for audio synthesis. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2009.09761 (2020)."},{"key":"e_1_3_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/1073368.1073408"},{"key":"e_1_3_2_25_1","first-page":"299","volume-title":"Proceedings of the 2006 ACM SIGGRAPH\/Eurographics symposium on Computer animation","author":"Lau Manfred","year":"2006","unstructured":"Manfred Lau and James\u00a0J Kuffner. 2006. Precomputed search trees: Planning for interactive goal-driven animation. In Proceedings of the 2006 ACM SIGGRAPH\/Eurographics symposium on Computer animation. 299\u2013308."},{"key":"e_1_3_2_26_1","unstructured":"Guan-Horng Liu Tianrong Chen Evangelos Theodorou and Molei Tao. 2024. Mirror diffusion models for constrained and watermarked generation. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_2_27_1","volume-title":"international conference on learning representations (ICLR)","author":"Liu Xingchao","year":"2023","unstructured":"Xingchao Liu and Lemeng Wu. 2023. Learning diffusion bridges on constrained domains. In international conference on learning representations (ICLR)."},{"key":"e_1_3_2_28_1","first-page":"22675","volume-title":"International Conference on Machine Learning","author":"Lou Aaron","year":"2023","unstructured":"Aaron Lou and Stefano Ermon. 2023. Reflected diffusion models. In International Conference on Machine Learning. PMLR, 22675\u201322701."},{"key":"e_1_3_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"e_1_3_2_30_1","volume-title":"Seventeenth European Workshop on Reinforcement Learning","author":"Massiani Pierre-Fran\u00e7ois","year":"2024","unstructured":"Pierre-Fran\u00e7ois Massiani, Alexander von Rohr, Lukas Haverbeck, and Sebastian Trimpe. 2024. Viability of Future Actions: Robust Reinforcement Learning via Entropy Regularization. In Seventeenth European Workshop on Reinforcement Learning. https:\/\/openreview.net\/forum?id=zP9hpDEzPq"},{"key":"e_1_3_2_31_1","unstructured":"Chenlin Meng Yutong He Yang Song Jiaming Song Jiajun Wu Jun-Yan Zhu and Stefano Ermon. 2021. Sdedit: Guided image synthesis and editing with stochastic differential equations. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2108.01073 (2021)."},{"key":"e_1_3_2_32_1","unstructured":"Volodymyr Mnih. 2013. Playing atari with deep reinforcement learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1312.5602 (2013)."},{"key":"e_1_3_2_33_1","doi-asserted-by":"publisher","DOI":"10.5555\/3692070.3693578"},{"key":"e_1_3_2_34_1","first-page":"8162","volume-title":"International conference on machine learning","author":"Nichol Alexander\u00a0Quinn","year":"2021","unstructured":"Alexander\u00a0Quinn Nichol and Prafulla Dhariwal. 2021. Improved denoising diffusion probabilistic models. In International conference on machine learning. PMLR, 8162\u20138171."},{"key":"e_1_3_2_35_1","unstructured":"Matthew Niedoba Jonathan Lavington Yunpeng Liu Vasileios Lioutas Justice Sefas Xiaoxuan Liang Dylan Green Setareh Dabiri Berend Zwartsenberg Adam Scibior et\u00a0al. 2024. A diffusion-model of joint interactive navigation. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_2_36_1","doi-asserted-by":"crossref","unstructured":"Andreas Orthey Constantinos Chamzas and Lydia\u00a0E Kavraki. 2023. Sampling-based motion planning: A comparative review. Annual Review of Control Robotics and Autonomous Systems 7 (2023).","DOI":"10.1146\/annurev-control-061623-094742"},{"key":"e_1_3_2_37_1","unstructured":"Jaehyun Park Yunho Kim Sejin Kim Byung-Jun Lee and Sundong Kim. 2024. DIAR: Diffusion-model-guided Implicit Q-learning with Adaptive Revaluation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.11338 (2024)."},{"key":"e_1_3_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591513"},{"key":"e_1_3_2_39_1","doi-asserted-by":"crossref","unstructured":"Xue\u00a0Bin Peng Glen Berseth KangKang Yin and Michiel Van De\u00a0Panne. 2017. Deeploco: Dynamic locomotion skills using hierarchical deep reinforcement learning. Acm transactions on graphics (tog) 36 4 (2017) 1\u201313.","DOI":"10.1145\/3072959.3073602"},{"key":"e_1_3_2_40_1","doi-asserted-by":"crossref","unstructured":"Corrado Pezzato Chadi Salmi Elia Trevisan Max Spahn Javier Alonso-Mora and Carlos\u00a0Hern\u00e1ndez Corbato. 2025. Sampling-based model predictive control leveraging parallelizable physics simulations. IEEE Robotics and Automation Letters (2025).","DOI":"10.1109\/LRA.2025.3535185"},{"key":"e_1_3_2_41_1","volume-title":"Markov decision processes: discrete stochastic dynamic programming","author":"Puterman Martin\u00a0L","year":"2014","unstructured":"Martin\u00a0L Puterman. 2014. Markov decision processes: discrete stochastic dynamic programming. John Wiley & Sons."},{"key":"e_1_3_2_42_1","unstructured":"Aditya Ramesh Prafulla Dhariwal Alex Nichol Casey Chu and Mark Chen. 2022. Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2204.06125 1 2 (2022) 3."},{"key":"e_1_3_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01322"},{"key":"e_1_3_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_45_1","unstructured":"John Schulman Filip Wolski Prafulla Dhariwal Alec Radford and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1707.06347 (2017)."},{"key":"e_1_3_2_46_1","first-page":"2256","volume-title":"International conference on machine learning","author":"Sohl-Dickstein Jascha","year":"2015","unstructured":"Jascha Sohl-Dickstein, Eric Weiss, Niru Maheswaranathan, and Surya Ganguli. 2015. Deep unsupervised learning using nonequilibrium thermodynamics. In International conference on machine learning. PMLR, 2256\u20132265."},{"key":"e_1_3_2_47_1","unstructured":"Jiaming Song Chenlin Meng and Stefano Ermon. 2020. Denoising diffusion implicit models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2010.02502 (2020)."},{"key":"e_1_3_2_48_1","unstructured":"Krishnan Srinivasan Benjamin Eysenbach Sehoon Ha Jie Tan and Chelsea Finn. 2020. Learning to be safe: Deep rl with a safety critic. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2010.14603 (2020)."},{"key":"e_1_3_2_49_1","doi-asserted-by":"crossref","unstructured":"Brijen Thananjeyan Ashwin Balakrishna Suraj Nair Michael Luo Krishnan Srinivasan Minho Hwang Joseph\u00a0E Gonzalez Julian Ibarz Chelsea Finn and Ken Goldberg. 2021. Recovery rl: Safe reinforcement learning with learned recovery zones. IEEE Robotics and Automation Letters 6 3 (2021) 4915\u20134922.","DOI":"10.1109\/LRA.2021.3070252"},{"key":"e_1_3_2_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/1275808.1276386"},{"key":"e_1_3_2_51_1","doi-asserted-by":"crossref","unstructured":"Takara\u00a0E Truong Michael Piseno Zhaoming Xie and C\u00a0Karen Liu. 2024. PDP: Physics-Based Character Animation via Diffusion Policy. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.00960 (2024).","DOI":"10.1145\/3680528.3687683"},{"key":"e_1_3_2_52_1","unstructured":"Siddarth Venkatraman Shivesh Khaitan Ravi\u00a0Tej Akella John Dolan Jeff Schneider and Glen Berseth. 2023. Reasoning with latent diffusion in offline reinforcement learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2309.06599 (2023)."},{"key":"e_1_3_2_53_1","unstructured":"Zhendong Wang Jonathan\u00a0J Hunt and Mingyuan Zhou. 2022. Diffusion policies as an expressive policy class for offline reinforcement learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2208.06193 (2022)."},{"key":"e_1_3_2_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487277"},{"key":"e_1_3_2_55_1","unstructured":"Zhaoming Xie Hung\u00a0Yu Ling Nam\u00a0Hee Kim and Michiel van\u00a0de Panne. 2020. ALLSTEPS: Curriculum-driven Learning of Stepping Stone Skills. Proc. ACM SIGGRAPH \/ Eurographics Symposium on Computer Animation."},{"key":"e_1_3_2_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161463"}],"container-title":["Proceedings of the ACM on Computer Graphics and Interactive Techniques"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3747864","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,8]],"date-time":"2025-08-08T16:25:41Z","timestamp":1754670341000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3747864"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,8]]},"references-count":55,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,8,31]]}},"alternative-id":["10.1145\/3747864"],"URL":"https:\/\/doi.org\/10.1145\/3747864","relation":{},"ISSN":["2577-6193"],"issn-type":[{"value":"2577-6193","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,8]]},"assertion":[{"value":"2025-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}