Regression Planning Networks

By Danfei Xu, Roberto Mart'in-Mart'in, De-An Huang, Yuke Zhu, Silvio Savarese, Li Fei-Fei. 2019

68 citations recorded by the source corpus.

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.

Subfields: Reinforcement Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Reinforcement Learning

1. Sergey Levine
2. Chelsea Finn
3. Pieter Abbeel
4. Karol Hausman
5. Dieter Fox
6. Pierre Sermanet
7. Ted Xiao
8. Yuke Zhu

Citations in the corpus

• Do As I Can, Not As I Say: Grounding Language in Robotic Affordances (2022, methodology): “Machine learning has recently been applied to enable abstract task specification, allow general primitives, or relax constraints [67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78].”
• Inner Monologue: Embodied Reasoning through Planning with Language Models (2022, background): “Traditionally, this problem has been solved through optimization [28, 29] or symbolic reasoning [24, 26], but more recently machine learning has been applied to aspects of the problem via learned representations, learned task-primitives, and more [30, 31, 32, 33, 34, 35, 36, 37, 38].”
• Hierarchical Planning for Long-Horizon Manipulation with Geometric and Symbolic Scene Graphs (2020, methodology): “Among these methods, Regression Planning Network (RPN) [38] extended the classical regression planning in symbolic space with deep networks, achieving strong zero-shot generalization to unseen tasks.”
• ProgPrompt: Generating Situated Robot Task Plans using Large Language Models (2022, background): “Recent works have explored learning-based task & motion planning, using methods such as representation learning, hierarchical learning, language as planning space, learning compositional skills and more [14], [15], [16], [17], [18], [19], [20], [21], [22], [23], [24], [25], [26].”
• Large Language Models as Commonsense Knowledge for Large-Scale Task Planning (2023, background): “Recently, researchers have used learning-based methods to learn planning policies directly [22] or to learn search heuristics to accelerate planning [32, 31, 40, 7, 29].”