Active Semantic Mapping with Mobile Manipulator in Horticultural Environments

TL;DR

This paper presents an efficient active semantic mapping approach for mobile robots in horticultural environments, improving runtime and map quality by leveraging probabilistic maps, novel information metrics, and strategic viewpoint planning.

Contribution

It introduces a scalable, probabilistic semantic mapping method with a new information utility function and ray-casting strategy tailored for horticultural settings.

Findings

Reduces runtime by 8% compared to baselines.

Improves multi-class entropy reduction and surface coverage.

Validated through real-world experiments with noted challenges.

Abstract

Semantic maps are fundamental for robotics tasks such as navigation and manipulation. They also enable yield prediction and phenotyping in agricultural settings. In this paper, we introduce an efficient and scalable approach for active semantic mapping in horticultural environments, employing a mobile robot manipulator equipped with an RGB-D camera. Our method leverages probabilistic semantic maps to detect semantic targets, generate candidate viewpoints, and compute corresponding information gain. We present an efficient ray-casting strategy and a novel information utility function that accounts for both semantics and occlusions. The proposed approach reduces total runtime by 8% compared to previous baselines. Furthermore, our information metric surpasses other metrics in reducing multi-class entropy and improving surface coverage, particularly in the presence of segmentation noise. Real-world experiments validate our method's effectiveness but also reveal challenges such as depth sensor noise and varying environmental conditions, requiring further research.