In the production process from green beans to coffee bean packages, the defective bean removal (or in short, defect removal) is one of most labor-consuming stages, and many companies investigate the automation of this stage for minimizing human efforts. In this paper, we propose a deep-learning-based defective bean inspection scheme (DL-DBIS), together with a GAN (generative-adversarial network)-structured automated labeled data augmentation method (GALDAM) for enhancing the proposed scheme, so that the automation degree of bean removal with robotic arms can be further improved for coffee industries. The proposed scheme is aimed at providing an effective model to a deep-learning-based object detection module for accurately identifying defects among dense beans. The proposed GALDAM can be used to greatly reduce labor costs, since the data labeling is the most labor-intensive work in this sort of solutions. Our proposed scheme brings two main impacts to intelligent agriculture. First, our proposed scheme is can be easily adopted by industries as human effort in labeling coffee beans are minimized. The users can easily customize their own defective bean model without spending a great amount of time on labeling small and dense objects. Second, our scheme can inspect all classes of defective beans categorized by the SCAA (Specialty Coffee Association of America) at the same time and can be easily extended if more classes of defective beans are added. These two advantages increase the degree of automation in the coffee industry. The prototype of the proposed scheme was developed for studying integrated tests. Testing results of a case study reveal that the proposed scheme can efficiently and effectively generate models for identifying defective beans with accuracy and precision values up to 80 % .

No abstract

No abstract

No abstract

An essential consideration in the development of any control algorithm for a multilegged vehicle is to maintain stability. If at any point during locomotion the vehicle becomes unstable, there is a possibility that the vehicle will overturn. In this research, we propose to include body sway motion into the motion planning of a quadruped's wave gait, such that its stability margin can be substantially increased. Two sway motions are proposed: Y-Sway and E-Sway. The Y-Sway motion is simple. It drives the center of gravity (CG) of the vehicle to approach the y-component of the geometric center of the contact points of the supporting legs. The E-Sway motion drives the CG to approach the desired CG locus for equal Energy Stability Levels. Both sway motions may be implemented in real time. Of them, the E-Sway motion can achieve a better stability margin. When sloped terrains are encountered, body-tilt compensation is also considered in the initialization phase to improve the stability margin. Simulation results show that body sway motions and tilt compensation are not mutually exclusive. Therefore, we may combine both actions to further increase the stability margin.