Machine Vision
Orchard scenes contain overlapping plants, shadows, and changing viewpoints. I developed a vision pipeline combining weed segmentation, identity tracking, and spatial analysis to locate individual weeds and estimate intra-row density.
Agricultural robotics · Computer vision · Precision agriculture
Lawrence Arthur
I am a doctoral researcher in Agricultural and Biological Engineering at Penn State, working with Dr. Long He in the Ag Robotics & Sensing Lab. My research focuses on robotic and precision weed management, combining computer vision, machine learning, and robotic control to develop automated spraying systems for apple orchards.
Previously, I earned a B.Sc. in Agriculture and an M.Phil. in Agricultural Mechanization from the University of Cape Coast, Ghana. I also worked as a field officer with the Ghana Cocoa Board.
Research Interests
- Perception and sensingComputer vision and sensing to understand agricultural environments.
- Robotics and automationAutonomous navigation, mechatronics, and control for agricultural tasks.
- Data-informed decisionsPlant measurements and experimental evidence to guide agricultural interventions.
Education
- Ph.D. · Agricultural and Biological EngineeringPennsylvania State University, US2023–present · Advisor: Dr. Long He
- M.Phil. · Agricultural MechanizationUniversity of Cape Coast, Ghana2018
- B.Sc. · AgricultureUniversity of Cape Coast, Ghana2015
Selected Research
Connecting what robots see, how they act, and how treatment decisions are made.
Mechatronics & Control
A detected weed must become a physical spray target. I designed and evaluated a three-nozzle servo-controlled system that translates target locations into nozzle assignments, steering commands, and spray timing, with laboratory validation of actuator and targeting performance.
Decision Intelligence
Weeds differ in canopy size and growth habit. I developed a calibrated imaging workflow to measure plant morphology and used controlled spray-deposition experiments to examine how plant and nozzle characteristics affect coverage and off-target deposition.
Systems Integration
Perception and spraying must work together while the robot moves. I integrated target localization, spray decisions, and nozzle operation on a Farm-ng Amiga platform, with orchard field tests and an interface for live monitoring and control.
Selected Publications
YOLOv7-CBAM and DeepSORT with pixel grid analysis for real-time weed localization and intra-row density estimation
Arthur, L., Mahnan, S., He, L., Hussain, M., Heinemann, P., & Brunharo, C.
Computers and Electronics in Agriculture, 239, 111071 · 2025
Read article ↗Development of a decision-making algorithm to identify picking strategies for robotic mushroom harvesting
Mahnan, S., Arthur, L., He, L., Ghatrehsamani, S., Heinemann, P., & Pecchia, J.
Computers and Electronics in Agriculture, 247, 111753 · 2026
Read article ↗Advanced technologies for precision tree fruit disease management: A review
Yang, Y., Mali, P., Arthur, L., Molaei, F., Atsyo, S., Geng, J., He, L., & Ghatrehsamani, S.
Computers and Electronics in Agriculture, 229, 109704 · 2025
Read article ↗Teaching & Mentoring
As a Teaching Assistant at Penn State and the University of Cape Coast, I supported hands-on electronics laboratories, introductory engineering and quantitative courses, and student project work.
Teaching experience →Media & Engagement
I share agricultural robotics research through field demonstrations, grower events, school outreach, and media interviews, connecting technical work with the people who may use it.
Media coverage & outreach →