Search

Redundant degree-of-freedom (DOF) manipulators offer increased flexibility and are better suited for obstacle avoidance, yet precise control of these systems remains a significant challenge. This paper addresses the issues of slow training convergence and suboptimal stability that plague current deep reinforcement learning (DRL)-based control strategies for redundant DOF manipulators. We propose a novel DRL-based intelligent control strategy, FK-DRL, which integrates the manipulator's forward kinematics (FK) model into the control framework. Initially, we conceptualize the control task as a Markov decision process (MDP) and construct the FK model for the manipulator. Subsequently, we expound on the integration principles and training procedures for amalgamating the FK model with existing DRL algorithms. Our experimental analysis, applied to 7-DOF and 4-DOF manipulators in simulated and real-world environments, evaluates the FK-DRL strategy's performance. The results indicate that compared to classical DRL algorithms, the FK-DDPG, FK-TD3, and FK-SAC algorithms improved the success rates of intelligent control tasks for the 7-DOF manipulator by 21%, 87%, and 64%, respectively, and the training convergence speeds increased by 21%, 18%, and 68%, respectively. These outcomes validate the proposed algorithm's effectiveness and advantages in redundant manipulator control using DRL and FK models. [ABSTRACT FROM AUTHOR]

Simple Summary: Coccidiosis is an intestinal parasitic disease caused by Eimeria protozoa, which endangers the health and growth of animals. However, little is known about the intestinal resident microbiota of chickens with different resistance to Eimeria tenella (E. tenella) infection and the changes in the microbiota from infection to recovery periods. The metagenomic sequencing analyses show that many potential differential microbial taxa were identified in different resistant chickens, respectively. Through the comparative analysis from infection to recovery periods, the number of microorganisms with the same trend of change between the control and resistant groups was greater than that between the control and susceptible groups. These findings provide a reference for further research into how E. tenella infection affects the intestinal microbiota and thus the growth, development, and health of chickens. To investigate the effect of Eimeria tenella (E. tenella) infection on the cecal microbiota, resistant and susceptible families were screened out based on the coccidiosis resistance evaluation indexes after E. tenella infection. Subsequently, a comparative analysis of cecal microorganisms among control, resistant, and susceptible groups as well as between different periods following the E. tenella challenge was conducted using metagenomic sequencing technology. The results showed that the abundance of opportunistic pathogens, such as Pantoea, Sporomusa, and Pasteurella in the susceptible group and Helicobacter and Sutterella in the resistant group, was significantly higher on day 27 post-inoculation (PI) (the recovery period) than on day 5 PI (the infection period). Additionally, the abundance of Alistipes, Butyricicoccus, and Eubacterium in the susceptible group and Coprococcus, Roseburia, Butyricicoccus, and Lactobacillus in the resistant group showed a significant upward trend during the infection period compared with that in the recovery period. On day 5 PI, the abundance of Faecalibacterium and Lactobacillus was decreased in both the resistant and susceptible groups when compared with that in the control group and was greater in the resistant group than in the susceptible group, while Alistipes in the susceptible group had a relatively higher abundance than that in other groups. A total of 49 biomarker taxa were identified using the linear discriminant analysis (LDA) effect size (LEfSe) method. Of these, the relative abundance of Lactobacillus aviarius, Lactobacillus salivarius, Roseburia, and Ruminococcus gauvreauii was increased in the resistant group, while Bacteroides _AGMB03916, Fusobacterium_mortiferum, Alistipes _An31A, and Alistipes _Marseille_P5061 were enriched in the susceptible group. On day 27 PI, LDA scores identified 43 biomarkers, among which the relative abundance of Elusimicrobium _An273 and Desulfovibrio _An276 was increased in the resistant group, while that of Bacteroides _43_108, Chlamydiia, Chlamydiales, and Sutterella _AM11 39 was augmented in the susceptible group. Our results indicated that E. tenella infection affects the structure of the cecal microbiota during both the challenge and recovery periods. These findings will enhance the understanding of the effects of changes in the cecal microbiota on chickens after coccidia infection and provide a reference for further research on the mechanisms underlying how the intestinal microbiota influence the growth and health of chickens. [ABSTRACT FROM AUTHOR]

An inertial micro-switch with multi-threshold acceleration detection capability has been proposed, taking advantage of electromechanical coupling behavior. A mathematical model of electromechanical coupling behavior was established to display the dependence of highly sensitivity on pull-in characteristic and show the ability to detect threshold acceleration by controlling the voltage applied to the inertial micro-switch. The capability of sensitivity and detection that was described in mathematical model was implemented to occur at the inertial switch and showed agreement with that of a simulation. Inertia switches that were comprised of various microstructures with dimensions ranging 3.5 µm from 180 µm were manufactured by means of the micro-electro-mechanical system (MEMS) manufacturing process, and their functions were evaluated by a dropping system. The control method related to the manufacturing of inertial switches was obtained by analyzing the effect of the structural parameters of the inertial switch on threshold voltage and threshold acceleration, resulting in a relatively small error between simulation and experiment. The inertial micro-switch showed high sensitivity to achieving the pull-in effect at 30 V, sense multi-threshold acceleration ranging from 500 g to 2000 g in 2.46 ms and provided enough time for outputting the acceleration signal. Furthermore, the multi-threshold acceleration can be adjusted by controlling the voltage applied to inertial micro-switches. In addition, other functions of inertial micro-switches, such as lower residual stress, high recoverability, and repeatability, have been displayed. [ABSTRACT FROM AUTHOR]

With advancements in photoelectric technology and computer image processing technology, the visual measurement method based on point clouds is gradually being applied to the 3D measurement of large workpieces. Point cloud registration is a key step in 3D measurement, and its registration accuracy directly affects the accuracy of 3D measurements. In this study, we designed a novel MPCR-Net for multiple partial point cloud registration networks. First, an ideal point cloud was extracted from the CAD model of the workpiece and used as the global template. Next, a deep neural network was used to search for the corresponding point groups between each partial point cloud and the global template point cloud. Then, the rigid body transformation matrix was learned according to these correspondence point groups to realize the registration of each partial point cloud. Finally, the iterative closest point algorithm was used to optimize the registration results to obtain the final point cloud model of the workpiece. We conducted point cloud registration experiments on untrained models and actual workpieces, and by comparing them with existing point cloud registration methods, we verified that the MPCR-Net could improve the accuracy and robustness of the 3D point cloud registration. [ABSTRACT FROM AUTHOR]