This paper presents an example of how a differential pressure sensor can be used to improve grasping of in-mold-labelling (IML) robots. In order to minimize mold-open time on injection molding machines, shorter operation time is desirable. To achieve this goal, an analysis of grasping labels using the in-mold-labelling robots was done with different approaches to improving the grasping process by measuring pressure in the chambers of the cylinder which carries the tool for grasping labels. The approach that uses the differential pressure sensor has proved best.

The suspension system of a vehicle is one of the most important parts which is involved in the process of vehicle designing. When a vehicle suspension system is designed, the evaluation of its performance against the road disturbances such as shocks and bumps are very important. The most commonly used systems consist of four hydraulic Jacks with mobility in vertical line with low speed and low exactitude. This paper offers a new mechanism for inspecting the suspension system of a vehicle using a parallel robot called Stewart. This robot is a special kind of parallel robots with capability of movements in different directions with high speed, accuracy and repeatability. In this paper the suspension system is evaluated on a quarter model of a simulated vehicle with control and guidance of Stewart robot using PID controller. The Stewart robot simulates the isolated and uneven bumps on a flat road in order to evaluate the given suspension system, and to investigate some criteria such as comforting of the passengers and remaining of the vehicle on the road. The results of the simulations show that the proposed method has a high accuracy, applicability and flexibility as well as simplicity, compared to currently used mechanisms.

In this article, a new hybrid feedback system is introduced, which integrates the behavior-based planning by reactive agent-based control scheme through subsumption architecture. At first, subsumption protocol studies the interactions of the robot with its environment which cover problems including translating of agent action into an outcome, interactions with the environment, and cooperative actions. Second considers deliberative behavior given the prevailing protocol. It determines the best and quickest response for each agent and tunes the actions based on an objective function obtained by a leader agent. More specifically, tasks are arranged as a hierarchy, where the high-level task is obstacle avoidance. Conflicting lower level tasks are removed by the leader agent decisions. Indeed, the leader agent can adjust the priority of all action to provide optimal behavior. In other words, our new agent-based method optimizes the subsumption architecture by producing an approximating objective function that made not only behaviors but also optimization done in the incremental procedure. We also define an emergency avoidance factor that made higher speed still stable and better interaction of robot in the presence of obstacles. For obstacles avoidance, the leader agent projects a plane to investigate the space ahead and continues. Finally, the leader agent makes a basic stand by task sharing behaviors in a decentralized manner using subsumption architecture to draw an optimal path. Simulation results show that although the proposed approach has little knowledge about the unexpected and ad-hoc situation in the robot’ s environment, it can provide suitable performance.

Background and Objectives: Signage is everywhere, and a robot should be able to take advantage of signs to help it localize (including Visual Place Recognition (VPR)) and map. Robust text detection & recognition in the wild is challenging due to pose, irregular text instances, illumination variations, viewpoint changes, and occlusion factors.Methods: This paper proposes an end-to-end scene text spotting model that simultaneously outputs the text string and bounding boxes. The proposed model leverages a pre-trained Vision Transformer based (ViT) architecture combined with a multi-task transformer-based text detector more suitable for the VPR task. Our central contribution is introducing an end-to-end scene text spotting framework to adequately capture the irregular and occluded text regions in different challenging places. We first equip the ViT backbone using a masked autoencoder (MAE) to capture partially occluded characters to address the occlusion problem. Then, we use a multi-task prediction head for the proposed model to handle arbitrary shapes of text instances with polygon bounding boxes.Results: The evaluation of the proposed architecture's performance for VPR involved conducting several experiments on the challenging Self-Collected Text Place (SCTP) benchmark dataset. The well-known evaluation metric, Precision-Recall, was employed to measure the performance of the proposed pipeline. The final model achieved the following performances, Recall = 0.93 and Precision = 0.8, upon testing on this benchmark.Conclusion: The initial experimental results show that the proposed model outperforms the state-of-the-art (SOTA) methods in comparison to the SCTP dataset, which confirms the robustness of the proposed end-to-end scene text detection and recognition model.