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.
From: Dayi Dong [view email]
[v1]
Wed, 17 Sep 2025 16:41:00 UTC (3,137 KB)
[v2]
Thu, 19 Feb 2026 19:37:29 UTC (3,111 KB)
[v3]
Wed, 13 May 2026 22:10:40 UTC (3,111 KB)
[v4]
Wed, 9 Sep 2026 20:50:59 UTC (3,111 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。