{"work":{"id":"d3bc3e2f-d4e7-4a55-8dea-d3ab39f1959b","openalex_id":null,"doi":null,"arxiv_id":"2503.02881","raw_key":null,"title":"Reactive Diffusion Policy: Slow-Fast Visual-Tactile Policy Learning for Contact-Rich Manipulation","authors":null,"authors_text":"Han Xue, Jieji Ren, Wendi Chen, Gu Zhang, Yuan Fang, Guoying Gu, Huazhe Xu, and Cewu Lu","year":2025,"venue":"cs.RO","abstract":"Humans can accomplish complex contact-rich tasks using vision and touch, with highly reactive capabilities such as fast response to external changes and adaptive control of contact forces; however, this remains challenging for robots. Existing visual imitation learning (IL) approaches rely on action chunking to model complex behaviors, which lacks the ability to respond instantly to real-time tactile feedback during the chunk execution. Furthermore, most teleoperation systems struggle to provide fine-grained tactile / force feedback, which limits the range of tasks that can be performed. To address these challenges, we introduce TactAR, a low-cost teleoperation system that provides real-time tactile feedback through Augmented Reality (AR), along with Reactive Diffusion Policy (RDP), a novel slow-fast visual-tactile imitation learning algorithm for learning contact-rich manipulation skills. RDP employs a two-level hierarchy: (1) a slow latent diffusion policy for predicting high-level action chunks in latent space at low frequency, (2) a fast asymmetric tokenizer for closed-loop tactile feedback control at high frequency. This design enables both complex trajectory modeling and quick reactive behavior within a unified framework. Through extensive evaluation across three challenging contact-rich tasks, RDP significantly improves performance compared to state-of-the-art visual IL baselines. Furthermore, experiments show that RDP is applicable across different tactile / force sensors. Code and videos are available on https://reactive-diffusion-policy.github.io.","external_url":"https://arxiv.org/abs/2503.02881","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-07-10T19:47:32.633838+00:00","pith_arxiv_id":"2503.02881","created_at":"2026-05-09T06:30:42.674302+00:00","updated_at":"2026-07-10T19:47:32.633838+00:00","title_quality_ok":true,"display_title":"Reactive diffusion policy: Slow-fast visual-tactile policy learning for contact-rich manipulation","render_title":"Reactive diffusion policy: Slow-fast visual-tactile policy learning for contact-rich manipulation"},"hub":{"state":{"work_id":"d3bc3e2f-d4e7-4a55-8dea-d3ab39f1959b","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":25,"external_cited_by_count":null,"distinct_field_count":2,"first_pith_cited_at":"2025-04-18T10:48:46+00:00","last_pith_cited_at":"2026-07-08T11:28:13+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-08-21T20:39:44.305501+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":3},{"context_role":"baseline","n":1}],"polarity_counts":[{"context_polarity":"background","n":3},{"context_polarity":"baseline","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}