2023

Poster Presentation at IEEE/RSI International Conference on Intelligent Robots and Systems (IROS) Workshop

less than 1 minute read

Published:

Topic: Walnut Detection Through Deep Learning Enhanced by Multispectral Synthetic Images

The accurate identification of walnuts within orchards brings forth a plethora of advantages, profoundly amplifying the efficiency and productivity of walnut orchard management. In this study, we present a novel approach to improve walnut detection efficiency, utilizing YOLOv5 trained on an enriched image set that incorporates both real and synthetic RGB and NIR images.

Poster Presentation at IEEE/RSI International Conference on Intelligent Robots and Systems (IROS) Workshop

less than 1 minute read

Published:

Topic: Fusion-Driven Tree Reconstruction and Fruit Localization: Advancing Precision in Agriculture

Fruit distribution is pivotal in shaping the future of both agriculture and agricultural robotics, paving the way for a streamlined supply chain. This study introduces an innovative methodology that harnesses the synergy of RGB imagery, LiDAR, and IMU data, to achieve intricate tree reconstructions and the pinpoint localization of fruits.

Poster Presentation at International Forum for Agricultural Robotics (FIRA USA)

less than 1 minute read

Published:

Topic: Human-following Robot for Crop Transportation

The problem addressed by our robot is to reduce the human effort involved in transporting heavy trays filled with fruits/vegetables, thus allowing human energy to be focused on the actual harvesting task. Our proposed solution is to develop a harvesting assistant robot that can follow the human operators in real-time and transport the harvested crops to storage locations, eliminating the need for manual transport by a tractor. The robot will also have the capability to monitor worker posture and provide real-time feedback on posture quality.

2022

“Inceptio-Tsinghua AIR Cup” Autonomous Driving Challenge

less than 1 minute read

Published:

“Inceptio & Tsinghua AIR Cup” is the first competition in China that covers both trunk logistics and urban road. The first competition focuses on decision planning algorithms, inviting global autonomous driving enthusiasts to solve real-world technical problems and challenge the limits of algorithms under the constraints of mass production.

Oral Presentation at ASABE Annual International Meeting

less than 1 minute read

Published:

Topic: Computer-aided Design and Optimization of a Shake-catch Soft Fruit Harvester

Tree fruit harvesting is both time-sensitive and demanding, leaving tree fruit growers susceptible to seasonal labor shortages. To minimize fruit damage during shake-catch harvesting, we suggest employing multi-level fruit catching (MFC) systems. These systems consist of closely spaced, soft rods arranged at multiple heights. Across various mechanical design applications, computer-aided design (CAD) modeling tools have proven invaluable for rapid design refinement and cost-effective prototyping. In this study, we introduce an innovative CAD approach to determine the ideal number of layers that maximizes marketable fruit collection efficiency in MFC systems, defined as the percentage of collected fruits with acceptable bruising levels.