Design, Development, and Field Test Analysis of a Multiarm Tomato Harvesting Robot

ABSTRACT Tomato is one of the most widely cultivated vegetables globally; however, traditional hand‐picking methods are inefficient, and thus, automated harvesting systems are becoming increasingly necessary. In response, this paper proposes the design of a multiarm collaborative picking robot system aimed at automating tomato harvesting. The system incorporates a three‐axis grasp‐pick‐place mechanism, enabling asynchronous operation via a single controller, thereby enhancing harvesting efficiency. Additionally, a visual perception system has been developed for tomato recognition and localization, which includes fruit detection and the calculation of optimal picking points. Experimental results demonstrate that the tomato recognition rate exceeds 90%, with an average picking time of 4.62 s per fruit. The efficiency of the three‐arm cooperative operation is 1.96 times greater than that of a single arm, and the overall picking success rate is 91.00%. These findings highlight the system's promising application potential and provide a foundation for future research to advance intelligent harvesting technologies for fruits and vegetables.