Toward Precise Robotic Weed Flaming Using a Mobile Manipulator with a Flamethrower

TL;DR

This paper presents a novel robotic system using a mobile manipulator with a flamethrower for precise weed flaming, incorporating a real-time dynamic flame coverage model based on infrared imaging to improve accuracy.

Contribution

The paper introduces a new system and algorithm for real-time prediction of flame coverage in robotic weed flaming, addressing environmental variability and deformable end effectors.

Findings

Achieved over 76% mean average precision in online flame coverage prediction.

Developed a dynamic flame coverage model using infrared images and pose data.

Demonstrated effective integration of hardware and software for precise weed flaming.

Abstract

Robotic weed flaming is a new and environmentally friendly approach to weed removal in the agricultural field. Using a mobile manipulator equipped with a flamethrower, we design a new system and algorithm to enable effective weed flaming, which requires robotic manipulation with a soft and deformable end effector, as the thermal coverage of the flame is affected by dynamic or unknown environmental factors such as gravity, wind, atmospheric pressure, fuel tank pressure, and pose of the nozzle. System development includes overall design, hardware integration, and software pipeline. To enable precise weed removal, the greatest challenge is to detect and predict dynamic flame coverage in real time before motion planning, which is quite different from a conventional rigid gripper in grasping or a spray gun in painting. Based on the images from two onboard infrared cameras and the pose information of the flamethrower nozzle on a mobile manipulator, we propose a new dynamic flame coverage model. The flame model uses a center-arc curve with a Gaussian cross-section model to describe the flame coverage in real time. The experiments have demonstrated the working system and shown that our model and algorithm can achieve a mean average precision (mAP) of more than 76\% in the reprojected images during online prediction.