A Long Horizon Planning Framework for Manipulating Rigid Pointcloud Objects

Abstract

We present a framework for solving long-horizon planning problems involving manipulation of rigid objects that operates directly from a point-cloud observation, i.e. without prior object models. Our method plans in the space of object subgoals and frees the planner from reasoning about robot-object interaction dynamics by relying on a set of generalizable manipulation primitives. We show that for rigid bodies, this abstraction can be realized using low-level manipulation skills that maintain sticking contact with the object and represent subgoals as 3D transformations. To enable generalization to unseen objects and improve planning performance, we propose a novel way of representing subgoals for rigid-body manipulation and a graph-attention based neural network architecture for processing point-cloud inputs. We experimentally validate these choices using simulated and real-world experiments on the YuMi robot. Results demonstrate that our method can successfully manipulate new objects into target configurations requiring long-term planning. Overall, our framework realizes the best of the worlds of task-and-motion planning (TAMP) and learning-based approaches. Project website: https://anthonysimeonov.github.io/rpo-planning-framework/.

Conference on Robot Learning (CoRL 2020): Project website: https://anthonysimeonov.github.io/rpo-planning-framework/

References in corpus (8)

• Adam: A Method for Stochastic Optimization
• Fast Graph Representation Learning with PyTorch Geometric
• Open3D: A Modern Library for 3D Data Processing
• Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metrics
• Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control
• Learning to Poke by Poking: Experiential Learning of Intuitive Physics
• Dynamics Learning with Cascaded Variational Inference for Multi-Step Manipulation
• KETO: Learning Keypoint Representations for Tool Manipulation

Cited by in corpus (4)

• Accelerating Robotic Reinforcement Learning via Parameterized Action Primitives
• Machine Learning for Robotic Manipulation
• Relationship Oriented Affordance Learning through Manipulation Graph Construction
• Hierarchical Policies for Cluttered-Scene Grasping with Latent Plans