Vision systems for harvesting robots: Produce detection and localization

In the last few years, the use of artificial intelligence and technological advances such as deep learning, new 3D-capable sensors, and edge computing embedded systems have increased produce detection and localization performance for harvesting robots. Unfortunately, this performance increase often requires large datasets that must be manually labeled, large periods for training, increased processing time and power for inference, and a high cost of powerful hardware to run the detection models. This work focuses on providing up-to-date information regarding the state of harvesting robots' vision subsystems, focusing on produce detection and localization research with special attention to the new technology that is being used. A description and analysis of the challenges of introducing this technology to produce detection and localization methodologies are also present in this review. Finally, future trends for harvesting robots' vision subsystems are described and discussed.

Automated summary

In recent years, artificial intelligence and technological advances have improved the detection and localization performance of harvesting robots for agricultural produce. However, this improvement also brings challenges such as manual labeling of large datasets, lengthy training periods, and high costs of hardware. This study provides up-to-date information on the vision subsystems of harvesting robots, analyzes the challenges of introducing new technology, and discusses future trends.