{"ID":2869961,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.14159","arxiv_id":"2509.14159","title":"MIMIC-D: Multi-modal Imitation for MultI-agent Coordination with Decentralized Diffusion Policies","abstract":"As robots become more integrated in society, their ability to coordinate with other robots and humans on multi-modal tasks (those with multiple valid solutions) is crucial. Such behaviors can be learned from expert demonstrations via imitation learning (IL), but when expert demonstrations are multi-modal, standard IL approaches usually average across modes or collapse to a single mode, preventing effective coordination. Being inspired by diffusion models' ability to capture complex multi-modal trajectory distributions in single-agent settings, we develop a diffusion-based framework for coordinated multi-modal behavior in multi-agent systems. However, existing multi-agent diffusion approaches typically require a centralized planner or explicit communication among agents. This assumption can fail in real-world scenarios where robots must operate independently or with agents like humans that they cannot directly communicate with. Therefore, we propose MIMIC-D, a joint training with decentralized execution paradigm for multi-modal multi-agent IL via diffusion. We jointly train all agents' policies with only local information to achieve implicit coordination. In simulation and hardware experiments, our method exhibits robust multi-modal coordination behavior in various tasks and environments, improving upon state-of-the-art baselines.","short_abstract":"As robots become more integrated in society, their ability to coordinate with other robots and humans on multi-modal tasks (those with multiple valid solutions) is crucial. Such behaviors can be learned from expert demonstrations via imitation learning (IL), but when expert demonstrations are multi-modal, standard IL a...","url_abs":"https://arxiv.org/abs/2509.14159","url_pdf":"https://arxiv.org/pdf/2509.14159v3","authors":"[\"Dayi Dong\",\"Maulik Bhatt\",\"Seoyeon Choi\",\"Negar Mehr\"]","published":"2025-09-17T16:41:00Z","proceeding":"cs.RO","tasks":"[\"cs.RO\"]","methods":"[\"Diffusion Model\"]","has_code":false}