New perception pipeline aims to automate mining rock-breakers

Researchers have developed a real-time RGB-D perception pipeline to automate the operation of hydraulic impact hammers, commonly known as rock-breakers, in mining. This system integrates image-based instance segmentation with geometric point cloud processing to generate feasible rock-breaking poses and a 3D representation of the workspace. Operating at approximately 10 Hz with low latency, the pipeline is designed for embedded hardware and aims to improve efficiency in secondary reduction tasks, particularly in underground mining where teleoperation is currently standard. AI

IMPACT Could improve efficiency and safety in mining operations through automation.

RANK_REASON Paper published on arXiv detailing a new perception pipeline for robotics. [lever_c_demoted from research: ic=1 ai=0.7]

Read on arXiv cs.CV →

• alphaXiv
• arXiv
• CatalyzeX
• computer science
• CORE Recommender
• DagsHub
• Francisco Leiva
• Gotit.pub
• Hugging Face
• Influence Flower
• RGB-D Visual Simultaneous Localization and Mapping (SLAM) Application
• robotics
• ScienceCast

• paper
• product
• infra

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →