Diffusion Meets Options: Hierarchical Generative Skill Composition for Temporally-Extended Tasks

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Feng, Zeyu, Luan, Hao, Ma, Kevin Yuchen, Soh, Harold
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912056747229184
author Feng, Zeyu
Luan, Hao
Ma, Kevin Yuchen
Soh, Harold
author_facet Feng, Zeyu
Luan, Hao
Ma, Kevin Yuchen
Soh, Harold
contents Safe and successful deployment of robots requires not only the ability to generate complex plans but also the capacity to frequently replan and correct execution errors. This paper addresses the challenge of long-horizon trajectory planning under temporally extended objectives in a receding horizon manner. To this end, we propose DOPPLER, a data-driven hierarchical framework that generates and updates plans based on instruction specified by linear temporal logic (LTL). Our method decomposes temporal tasks into chain of options with hierarchical reinforcement learning from offline non-expert datasets. It leverages diffusion models to generate options with low-level actions. We devise a determinantal-guided posterior sampling technique during batch generation, which improves the speed and diversity of diffusion generated options, leading to more efficient querying. Experiments on robot navigation and manipulation tasks demonstrate that DOPPLER can generate sequences of trajectories that progressively satisfy the specified formulae for obstacle avoidance and sequential visitation. Demonstration videos are available online at: https://philiptheother.github.io/doppler/.
format Preprint
id arxiv_https___arxiv_org_abs_2410_02389
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Diffusion Meets Options: Hierarchical Generative Skill Composition for Temporally-Extended Tasks
Feng, Zeyu
Luan, Hao
Ma, Kevin Yuchen
Soh, Harold
Robotics
Artificial Intelligence
Machine Learning
Safe and successful deployment of robots requires not only the ability to generate complex plans but also the capacity to frequently replan and correct execution errors. This paper addresses the challenge of long-horizon trajectory planning under temporally extended objectives in a receding horizon manner. To this end, we propose DOPPLER, a data-driven hierarchical framework that generates and updates plans based on instruction specified by linear temporal logic (LTL). Our method decomposes temporal tasks into chain of options with hierarchical reinforcement learning from offline non-expert datasets. It leverages diffusion models to generate options with low-level actions. We devise a determinantal-guided posterior sampling technique during batch generation, which improves the speed and diversity of diffusion generated options, leading to more efficient querying. Experiments on robot navigation and manipulation tasks demonstrate that DOPPLER can generate sequences of trajectories that progressively satisfy the specified formulae for obstacle avoidance and sequential visitation. Demonstration videos are available online at: https://philiptheother.github.io/doppler/.
title Diffusion Meets Options: Hierarchical Generative Skill Composition for Temporally-Extended Tasks
topic Robotics
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2410.02389