A probabilistic framework for tracking uncertainties in robotic manipulation

TL;DR

This paper introduces a probabilistic framework to accurately track and manage uncertainties during robotic manipulation, enhancing safety and effectiveness in unstructured environments.

Contribution

It proposes a stage-specific uncertainty representation and conversion method, improving uncertainty management throughout the manipulation process.

Findings

Improved uncertainty tracking during perception and interaction stages

Enhanced safety and success rates in robotic assembly tasks

Effective uncertainty initialization and updating techniques

Abstract

Precisely tracking uncertainties is crucial for robots to successfully and safely operate in unstructured and dynamic environments. We present a probabilistic framework to precisely keep track of uncertainties throughout the entire manipulation process. In agreement with common manipulation pipelines, we decompose the process into two subsequent stages, namely perception and physical interaction. Each stage is associated with different sources and types of uncertainties, requiring different techniques. We discuss which representation of uncertainties is the most appropriate for each stage (e.g. as probability distributions in SE(3) during perception, as weighted particles during physical interactions), how to convert from one representation to another, and how to initialize or update the uncertainties at each step of the process (camera calibration, image processing, pushing, grasping, etc.). Finally, we demonstrate the benefit of this fine-grained knowledge of uncertainties in an actual assembly task.