Object SLAM-Based Active Mapping and Robotic Grasping

TL;DR

This paper introduces a novel active object mapping framework that integrates object SLAM with multi-object pose estimation and an exploration strategy, significantly improving robotic grasping accuracy and autonomous perception capabilities.

Contribution

The framework is the first to combine active object mapping with high-precision pose estimation and exploration for complex robotic manipulation tasks.

Findings

High mapping accuracy demonstrated in quantitative evaluations.

Effective in robotic grasping and placement tasks.

Enhances autonomous perception for manipulation and augmented reality.

Abstract

This paper presents the first active object mapping framework for complex robotic manipulation and autonomous perception tasks. The framework is built on an object SLAM system integrated with a simultaneous multi-object pose estimation process that is optimized for robotic grasping. Aiming to reduce the observation uncertainty on target objects and increase their pose estimation accuracy, we also design an object-driven exploration strategy to guide the object mapping process, enabling autonomous mapping and high-level perception. Combining the mapping module and the exploration strategy, an accurate object map that is compatible with robotic grasping can be generated. Additionally, quantitative evaluations also indicate that the proposed framework has a very high mapping accuracy. Experiments with manipulation (including object grasping and placement) and augmented reality significantly demonstrate the effectiveness and advantages of our proposed framework.