Dynamic-Resolution Model Learning for Object Pile Manipulation

Yixuan Wang, Yunzhu Li, Katherine Driggs-Campbell, Li Fei-Fei, Jiajun Wu

Research output: Contribution to conferencePaperpeer-review

Abstract

Dynamics models learned from visual observations have shown to be effective in various robotic manipulation tasks. One of the key questions for learning such dynamics models is what scene representation to use. Prior works typically assume representation at a fixed dimension or resolution, which may be inefficient for simple tasks and ineffective for more complicated tasks. In this work, we investigate how to learn dynamic and adaptive representations at different levels of abstraction to achieve the optimal trade-off between efficiency and effectiveness. Specifically, we construct dynamic-resolution particle representations of the environment and learn a unified dynamics model using graph neural networks (GNNs) that allows continuous selection of the abstraction level. During test time, the agent can adaptively determine the optimal resolution at each model-predictive control (MPC) step. We evaluate our method in object pile manipulation, a task we commonly encounter in cooking, agriculture, manufacturing, and pharmaceutical applications. Through comprehensive evaluations both in the simulation and the real world, we show that our method achieves significantly better performance than state-of-the-art fixed-resolution baselines at the gathering, sorting, and redistribution of granular object piles made with various instances like coffee beans, almonds, corn, etc.
Original languageEnglish (US)
DOIs
StatePublished - Jul 10 2023
EventRobotics: Science and Systems XIX - Daegu, Korea, Republic of
Duration: Jul 10 2023Jul 14 2023

Conference

ConferenceRobotics: Science and Systems XIX
Country/TerritoryKorea, Republic of
CityDaegu
Period7/10/237/14/23

Fingerprint

Dive into the research topics of 'Dynamic-Resolution Model Learning for Object Pile Manipulation'. Together they form a unique fingerprint.

Cite this