CHD: Coupled Hierarchical Diffusion for Long-Horizon Tasks

Diffusion-based planners have shown strong performance in short-horizon tasks but often fail in complex, long-horizon settings. We trace the failure to loose coupling between high-level (HL) sub-goal selection and low-level (LL) trajectory generation, which leads to incoherent plans and degraded performance. We propose Coupled Hierarchical Diffusion (CHD), a framework that models HL sub-goals and LL trajectories jointly within a unified diffusion process. A shared classifier passes LL feedback upstream so that sub-goals self-correct while sampling proceeds. This tight HL-LL coupling improves trajectory coherence and enables scalable long-horizon diffusion planning. Experiments across maze navigation, tabletop manipulation, and household environments show that CHD consistently outperforms both flat and hierarchical diffusion baselines. Our website is:this https URL

@article{hao2025_2505.07261,
  title={ CHD: Coupled Hierarchical Diffusion for Long-Horizon Tasks },
  author={ Ce Hao and Anxing Xiao and Zhiwei Xue and Harold Soh },
  journal={arXiv preprint arXiv:2505.07261},
  year={ 2025 }
}