In this article, an event-triggered adaptive dynamic programming (ETADP) method is proposed for the robust optimal tracking control problem of an uncertain continuous-time nonlinear system with asymmetric input constraints and external disturbances. First, an event-triggered integral reinforcement learning (ETIRL) algorithm is proposed to address the zero-sum game problem for partially unknown dynamical systems. A triggering condition with an interference attenuation level is designed to optimize the process. Second, a single-critic neural network structure is employed to approximate the optimal control law. The control and disturbance laws are updated non-periodically by the event-triggered. The asymptotic stability of the closed-loop system and the uniform ultimate boundedness (UUB) of the critic neural network weights are proven theoretically using the Lyapunov stability theorem. Finally, the feasibility of the algorithm is assessed through pneumatic muscle antagonistic joint experiments.

Remote controlled soft actuators have attracted ever-increasing interest in industrial, medical, robotics, and engineering fields. Soft actuators are charming than normal tools in executing dedicate tasks due to small volume and flexible body they have. However, it remains a challenge to design soft actuator that can adapt to multi-environments under remote stimuli with promising nano materials. Herein, we have developed a kind of near-infrared laser driven soft actuators with multi locomotive modes based on WSe₂ and graphene nanosheets heterojunction. Different locomotion modes are driven by photothermal effect induced deformation to adapt to different working conditions. Moreover, the specially designed gripper driven by pulsed laser can lift a heavy load which is four times of its weight. This work broadens the choice of advanced nanomaterials for photothermal conversion of soft actuators. It is promising to realize applications including photothermal therapy and complex environment detection through the combination of the intelligent robot design and optical fiber system.

Aiming at the problems of slow convergence and easy fall into local optimal solution of the classic ant colony algorithm in path planning, an improved ant colony algorithm is proposed. Firstly, the Floyd algorithm is introduced to generate the guiding path, and increase the pheromone content on the guiding path. Through the difference in initial pheromone, the ant colony is guided to quickly find the target node. Secondly, the fallback strategy is applied to reduce the number of ants who die due to falling into the trap to increase the probability of ants finding the target node. Thirdly, the gravity concept in the artificial potential field method and the concept of distance from the optional node to the target node are introduced to improve the heuristic function to make up for the fallback strategy on the convergence speed of the algorithm. Fourthly, a multi-objective optimization function is proposed, which comprehensively considers the three indexes of path length, security, and energy consumption and combines the dynamic optimization idea to optimize the pheromone update method, to avoid the algorithm falling into the local optimal solution and improve the comprehensive quality of the path. Finally, according to the connectivity principle and quadratic B-spline curve optimization method, the path nodes are optimized to shorten the path length effectively.

When intelligent mobile robots perform global path planning in complex and narrow environments, several issues often arise, including low search efficiency, node redundancy, non-smooth paths, and high costs. This paper proposes an improved path planning algorithm based on the rapidly exploring random tree (RRT) approach. Firstly, the target bias sampling method is employed to screen and eliminate redundant sampling points. Secondly, the adaptive step size strategy is introduced to address the limitations of the traditional RRT algorithm. The mobile robot is then modeled and analyzed to ensure that the path adheres to angle and collision constraints during movement. Finally, the initial path is pruned, and the path is smoothed using a cubic B-spline curve, resulting in a smoother path with reduced costs. The evaluation metrics employed include search time, path length, and the number of sampling nodes. To evaluate the effectiveness of the proposed algorithm, simulations of the RRT algorithm, RRT-connect algorithm, RRT* algorithm, and the improved RRT algorithm are conducted in various environments. The results demonstrate that the improved RRT algorithm reduces the generated path length by 25.32% compared to the RRT algorithm, 26.42% compared to the RRT-connect algorithm, and 4.99% compared to the RRT* algorithm. Moreover, the improved RRT algorithm significantly improves the demand for reducing path costs. The planning time of the improved RRT algorithm is reduced by 64.96% compared to that of the RRT algorithm, 40.83% compared to that of the RRT-connect algorithm, and 27.34% compared to that of the RRT* algorithm, leading to improved speed. These findings indicate that the proposed method exhibits a notable improvement in the three crucial evaluation metrics: sampling time, number of nodes, and path length. Additionally, the algorithm performed well after undergoing physical verification with an insect-like mobile robot in a real environment featuring narrow elevator entrances.

Today’s garbage classification is not fully automated and mostly relies on manual labor. In order to efficiently classify garbage and increase resource re-usability, society needs a modern solution. The development of artificial intelligence, especially in object detection, provides an excellent opportunity to develop real-time accurate garbage detection. This project is about real-time garbage detection using YOLOX and is used to detect seventeen categories of garbage. After the camera detects the garbage, it will automatically identify and analyze the type and specific the position of the garbage, which will be automatically picked up by a mechanical jaws. The datasets used in this paper consists of 5000 images with label. With the officially supported TensorRT optimization and acceleration technology, the model can be used in low-cost embedded devices and can detect garbage in near real-time without the need for a stable Internet connection. Our evaluation and comparison of these models includes some key metrics such as mean accuracy (mAP), inference time per frame, floating point operations(FLOPs), and the number of parameters of the model. The test results show that YOLOX’s mAP _0.5:0.95 can exceed 97% and the inference speed can exceed 32 fps. The performance far exceeds that of other YOLO series, with high accuracy and speed in complex environments, making it highly applicable to today’s garbage classification needs.