Anticipation-VLA: Solving Long-Horizon Embodied Tasks via Anticipation-based Subgoal Generation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910187292459008 |
|---|---|
| author | Zhang, Zhilong Luo, Wenyu Wang, Haonan Sheng, Yifei Wang, Yidi Guo, Hanyuan Ren, Haoxiang Du, Xinghao Che, Yuhan Cao, Tongtong Yuan, Lei Yu, Yang |
| author_facet | Zhang, Zhilong Luo, Wenyu Wang, Haonan Sheng, Yifei Wang, Yidi Guo, Hanyuan Ren, Haoxiang Du, Xinghao Che, Yuhan Cao, Tongtong Yuan, Lei Yu, Yang |
| contents | Vision-Language-Action (VLA) models have emerged as a powerful paradigm for embodied intelligence, enabling robots to perform tasks based on natural language instructions and current visual input. However, existing VLA models struggle with long-horizon tasks due to compounding errors. Prior methods decompose tasks into subtasks of fixed granularity, which cannot adapt to the varying complexity of execution states, limiting their robustness in long-horizon tasks. To overcome this, we introduce Anticipation Model, which adaptively and recursively generates future subgoals. This model continuously adapts as the task unfolds, adjusting future subgoals in response to evolving dynamics, facilitating more reliable planning paths. Building on this concept, we propose Anticipation-VLA, a hierarchical VLA model that leverages the anticipation model to generate actionable subgoals that guide VLA policy execution. We implement Anticipation-VLA with finetuning a Unified Multimodal Model (UMM) for high-level subgoal generation and a goal-conditioned VLA policy for low-level action execution. Experiments in both simulated and real-world robotic tasks demonstrate the effectiveness of Anticipation-VLA, highlighting the importance of adaptive and recursive subgoal generation for robust policy execution. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_01772 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Anticipation-VLA: Solving Long-Horizon Embodied Tasks via Anticipation-based Subgoal Generation Zhang, Zhilong Luo, Wenyu Wang, Haonan Sheng, Yifei Wang, Yidi Guo, Hanyuan Ren, Haoxiang Du, Xinghao Che, Yuhan Cao, Tongtong Yuan, Lei Yu, Yang Robotics Machine Learning Vision-Language-Action (VLA) models have emerged as a powerful paradigm for embodied intelligence, enabling robots to perform tasks based on natural language instructions and current visual input. However, existing VLA models struggle with long-horizon tasks due to compounding errors. Prior methods decompose tasks into subtasks of fixed granularity, which cannot adapt to the varying complexity of execution states, limiting their robustness in long-horizon tasks. To overcome this, we introduce Anticipation Model, which adaptively and recursively generates future subgoals. This model continuously adapts as the task unfolds, adjusting future subgoals in response to evolving dynamics, facilitating more reliable planning paths. Building on this concept, we propose Anticipation-VLA, a hierarchical VLA model that leverages the anticipation model to generate actionable subgoals that guide VLA policy execution. We implement Anticipation-VLA with finetuning a Unified Multimodal Model (UMM) for high-level subgoal generation and a goal-conditioned VLA policy for low-level action execution. Experiments in both simulated and real-world robotic tasks demonstrate the effectiveness of Anticipation-VLA, highlighting the importance of adaptive and recursive subgoal generation for robust policy execution. |
| title | Anticipation-VLA: Solving Long-Horizon Embodied Tasks via Anticipation-based Subgoal Generation |
| topic | Robotics Machine Learning |
| url | https://arxiv.org/abs/2605.01772 |