Learning a Generative Transition Model for Uncertainty-Aware Robotic Manipulation

TL;DR

This paper introduces a generative transition model for robotic manipulation that predicts future states and their uncertainties, enabling faster bin-picking and optimized action planning, resulting in significant efficiency improvements.

Contribution

The paper presents a novel image-to-image transition model trained on real-world data that enhances manipulation speed and planning in robotic bin-picking tasks.

Findings

Increased picks per hour by around 15% using the model.

Achieved over 700 PPH in the YCB Box and Blocks Test.

Enabled planning of action sequences to minimize total actions.

Abstract

Robot learning of real-world manipulation tasks remains challenging and time consuming, even though actions are often simplified by single-step manipulation primitives. In order to compensate the removed time dependency, we additionally learn an image-to-image transition model that is able to predict a next state including its uncertainty. We apply this approach to bin picking, the task of emptying a bin using grasping as well as pre-grasping manipulation as fast as possible. The transition model is trained with up to 42000 pairs of real-world images before and after a manipulation action. Our approach enables two important skills: First, for applications with flange-mounted cameras, picks per hours (PPH) can be increased by around 15% by skipping image measurements. Second, we use the model to plan action sequences ahead of time and optimize time-dependent rewards, e.g. to minimize the number of actions required to empty the bin. We evaluate both improvements with real-robot experiments and achieve over 700 PPH in the YCB Box and Blocks Test.