Timezone: »

Regression Planning Networks
Danfei Xu · Roberto Martín-Martín · De-An Huang · Yuke Zhu · Silvio Savarese · Li Fei-Fei

Thu Dec 12 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #219

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 --including 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 horizon, and show that it achieves near-optimal performance in completely new task instances.

Author Information

Danfei Xu (Stanford University)
Roberto Martín-Martín (Stanford University)
De-An Huang (Stanford University)
Yuke Zhu (University of Texas - Austin)
Silvio Savarese (Stanford University)
Li Fei-Fei (Stanford University)

More from the Same Authors