arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.13072cs.AIcs.CVcs.LGcs.RO
收藏

回归规划网络

Regression Planning Networks

Stanford University(斯坦福大学)

Danfei Xu, Roberto Martín-Martín, De-An Huang, Yuke Zhu, Silvio Savarese, Li Fei-Fei

摘要:

最近的学习规划方法已经显示出有前途的结果规划直接从观察空间。然而,他们计划长期任务的能力受到预测模型准确性的限制。另一方面,经典的符号规划器在解决长期任务方面表现出卓越的能力,但它们需要预定义的符号规则和符号状态,限制了它们在现实世界中的适用性。在这项工作中,我们结合了这两种模式的好处,并提出了一种学习计划的方法,可以直接生成一个长期的象征性的计划条件下的高维观测。我们从经典规划文献中借用回归(向后)规划的思想,并引入回归规划网络(RPN),这是一种神经网络架构,它从任务目标开始向后规划,并生成一系列达到当前观察的中间目标。我们表明,我们的模型不仅继承了象征性规划的许多有利特征,例如,解决以前看不见的任务的能力,但也可以以端到端的方式从视觉输入中学习。我们评估了RPN在网格世界环境和模拟3D厨房环境中的能力,这些环境具有复杂的视觉场景和长任务范围,并表明它在全新的任务实例中实现了接近最佳的性能。

英文摘要:

Recent learning-to-plan methods have shown promising results on planning directly from observation space. Yet, their ability to plan for long-horizon tasks is limited by the accuracy of the prediction model. On the other hand, classical symbolic planners show remarkable capabilities in solving long-horizon tasks, but they require predefined symbolic rules and symbolic states, restricting their real-world applicability. In this work, we combine the benefits of these two paradigms and propose a learning-to-plan method that can directly generate a long-term symbolic plan conditioned on high-dimensional observations. We borrow the idea of regression (backward) planning from classical planning literature and introduce Regression Planning Networks (RPN), a neural network architecture that plans backward starting at a task goal and generates a sequence of intermediate goals that reaches the current observation. We show that our model not only inherits many favorable traits from symbolic planning, e.g., the ability to solve previously unseen tasks but also can learn from visual inputs in an end-to-end manner. We evaluate the capabilities of RPN in a grid world environment and a simulated 3D kitchen environment featuring complex visual scenes and long task horizons, and show that it achieves near-optimal performance in completely new task instances.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑