In this article, we present a new path planning algorithm based on the rapidly exploring random tree-fixed node (RRT*FN) algorithm for manipulators. It addresses the problem that RRT*FN complex environment processing is not fast enough to meet real-time requirements, and RRT*FN is basically impossible to search for an effective manipulator path in a narrow-channel environment. In the new path planning algorithm, a heuristic sampling method is adopted and the leaf nodes outside the ellipsoids are preferentially deleted to address the node removal problem, resulting in better search paths and faster search speeds. When the nodes are expanded, new nodes are generated due to goal gravity and random point gravity, with the weight values dynamically adjusted via dichotomy, and the new nodes are expanded to the goal point twice to more rapidly obtain a tree extension direction that is closer to the goal point. For boundary points, the issues of narrow channels and stepped obstacles can be effectively solved by extending the local environment sampling boundaries. To optimize the paths, the redundant intermediate nodes are simplified based on the triangle inequality. Simulation analyses show that the proposed planner can adapt to a variety of scenarios in real time while satisfying optimal path conditions.

Robotic grasping has been widely used in various industries. How to meet the requirements of grasping accuracy and grasping speed at the same time is a challenging problem in real-time grasping tasks. In this paper, aiming at the real-time grasping task in retail warehousing, a lightweight grasping pose estimation model for retail warehousing is proposed. The model first uses the Focus module to perform lossless double downsampling, and learns each feature map of the upper layer through the dilated convolution block to expand the receptive field; then, the R-Resblock structure is improved to perform multi-scale feature fusion, and a lightweight RFB-SE module is designed to enrich feature information and reduce the number of parameters. Finally, after upsampling and restoring the image, the grasping quality, grasping angle, and grasping width of the target are regressed to obtain the optimal grasping pose of the target item. Experiments are carried out in the Cornell dataset, Jacquard dataset, and simulation environment respectively. The experimental results show that the method has a grasping accuracy of 97.8% and a grasping speed of 78FPS on the Cornell dataset. The success rate is 91.5%, and the grasping task in a retail warehouse environment is simulated in grasping simulation experiments.