In view of the large randomness, redundant path nodes, and low search efficiency of RRT-connect in a complex obstacle environment, this study intends to develop a path-planning method combining RRT-connect and Informed RRT*. First, to solve the problem of large sampling randomness, the Informed RRT* algorithm is combined to adopt a simpler rectangle and limit the sampling range to the rectangle. Second, for the poor quality of the search path, the dynamic step size is used for growth extension, the reverse greedy algorithm is used to delete redundant nodes, the spline curve is used to smooth the path such that the position meets the cubic spline curve and the speed meets the quadratic spline curve, and the final path is optimized. Finally, the proposed algorithm is verified in the simulation and real world using a self-developed quadrupedal robot. Compared with the original RRT-connect algorithm, the first solution time, total number of nodes, and initial path cost were reduced by more than 11%, 8.5%, and 2.5%, respectively.

To improve the performance of the image semantic segmentation algorithm and make the algorithm achieve a better balance between accuracy and real-time performance when segmenting images, this paper proposes a real-time image semantic segmentation model based on an improved DeepLabv3+ network. First, the MobileNetV2 model with less computational overhead and number of parameters is selected as the backbone network to improve the segmentation speed; then, the Feature Enhancement Module (FEM) is introduced to several shallow features with different scale sizes in MobileNetV2, and then these shallow features are fused to improve the utilization rate of the model encoder on the edge information, to retain more detailed information and to improve the network’s feature representation ability for complex scenes; finally, to address the problem that the output feature maps of Atrous Spatial Pyramid Pooling (ASPP) module do not pay enough attention to detailed information after merging, the FEM attention mechanism is introduced on the feature maps processed by the ASPP module. The algorithm in this study achieves 76.45% for mean intersection over union (mIoU) accuracy with 29.18 FPS real-time performance in the PASCAL VOC2012 Augmented dataset; and 37.31% mIoU accuracy with 23.31 FPS real-time performance in the ADE20K dataset. The experimental results show that the algorithm in this study achieves a good balance between accuracy and real-time performance, and its image semantic segmentation performance is significantly improved compared to DeepLabv3+ and other existing algorithms.

Autonomous tractor–trailer robots possess a broad spectrum of applications but pose significant challenges in control due to their nonlinear and underactuated dynamics. Unlike the tractor, the motion of the trailer cannot be directly actuated, which often results in a deviation from the intended path. In this study, we introduce a novel method for generating and following trajectories that circumvent obstacles, tailored for a tractor–trailer robotic system constrained by multiple factors. Firstly, leveraging the state information of both the obstacles and the desired trajectory, we formulate an improved trajectory for obstacle avoidance using the nonlinear least squares method. Subsequently, we propose an innovative tracking controller that integrates a universal barrier function with a state transformation strategy. This amalgamation facilitates the accurate tracking of the prescribed trajectory. Our theoretical analysis substantiates that the proposed control methodology ensures exponential convergence of the line-of-sight (LOS) distance and angle tracking errors, while enhancing the transient performance. To validate the efficacy of our approach, we present a series of simulation results, which demonstrate the applicability of the developed control strategy in managing the complex dynamics of tractor–trailer robots.

The hybrid space of robots is divided into task space and joint space, with task space focused on trajectory-tracking accuracy, while joint space considers dynamic responsiveness and synchronization. Therefore, the robot-motion control systems need to effectively integrate both aspects, ensuring precision in task trajectory while promptly responding to unforeseen environmental events. Hence, this paper proposes an online trajectory-generation method for robots in both joint and task spaces. In task space, a planning approach is presented for high-precision NURBS curves. The global NURBS curve is segmented into several rational Bezier curves, establishing local coordinate systems for control points. This ensures that all local control points meet the chord error constraint, guaranteeing trajectory accuracy. To address the feed rate dynamic planning issue for segmented curves, an improved online S-shape feed-rate scheduling framework is introduced. This framework dynamically adjusts the current execution speed to meet task requirements. In joint space, an offline velocity planning based on a time synchronization scheme and a multi-dimensional synchronization technique based on the principle of spatial-coordinate system projection are proposed. Building upon the offline scheme, it allows for the modification of the target state for any sub-dimension during the motion process, with the remaining dimensions adapting accordingly. Simulation and experimentation demonstrate that the two proposed online trajectory generations for robot motion spaces, while ensuring task trajectory accuracy, effectively handle external unexpected events. They ensure joint synchronization and smoothness, carrying significant practical implications and application value for the stability of robot systems.

A multi-objective grasshopper optimization algorithm (MOGOA) with an adaptive curve c(t) and the enhanced Levy fight strategy (CLMOGOA) was proposed to optimize the process parameters of rotary screen coating, setting the thickness and uniformity of the adhesive layer on the structural plates in spacecraft as its optimization objectives. The adaptive curve strikes a balance between global exploration and local development and accelerates the convergence speed. The enhanced Levy strategy helps the algorithm to escape local optimizations, increases the population diversity, and possesses dual searching capabilities. After multiple runs, the average values of the CLMOGOA’s reverse generation distance were 0.0288, 0.0233, and 0.1810 on the test sets, which were less than those of the MOGOA. The best Pareto-optimal front obtained by the CLMOGOA had a higher accuracy and better coverage compared to that of the MOGOA. Thus, it is indicated that the CLMOGOA managed to outperform the MOGOA on the test functions. In order to solve the optimization problem, 108 sets of process experiments were designed, and then the experimental data were used to train a Back Propagation Neural Network (BPNN), a Least Squares Support Vector Machine (LSSVM), and Random Forest (RF) to obtain the best prediction model for the process parameters. Considering the thickness and uniformity of the adhesive layer as the objectives, the improved algorithm was used to optimize the prediction model to obtain the optimal process parameters. The actual coating effect showed that the optimization algorithm improved the efficiency and qualification rate of the product.