This paper proposes a model-free control framework for the path planning of the rigid and soft robotic manipulator using an intelligent algorithm called Weighted Jacobian Rapidly-exploring Random Tree (WJRRT). The optimization approach is used to model the path planning problem, which is independent of the robotic model, and then used the WJRRT algorithm to solve it. WJRRT algorithm not only explores the cartesian space for the end-effector of the robotic manipulator randomly but also directs it towards the goal-position when required. It is robust enough to tackle the uncertainties in the manipulator and make the computation of path planning more efficient. WJRRT assigned a fitness value to each node of the tree. Based on the fitness values algorithm computes the final path, which is a trade-off between efficiency and safety of the path. The simulation results of two, three, and seven degrees of freedom (DOF) robotic manipulators are presented and compared with JT-RRT, Bi-RRT, and TB-RRT algorithms. Experimental results are verified using a soft manipulator made from flexible materials, i.e., polypropylene and polychloroprene. Their flexible structure makes their control complex and creates uncertainties in the model. The simulation and experimental results demonstrate that WJRRT can efficiently and accurately control the motion of manipulators.

In this brief, we presented a framework for the trajectory optimization of the 5-link Biped Robot using the Beetle Antennae Search (BAS) algorithm. The biped robot is highly non-linear and has complex dynamical modeling. It is challenging to obtain a closed-form solution for the Robot. The robot modeling has two stages, i.e., the optimal trajectory generation and the robust control of a robot. The conventional methodologies treat both problems separately and are computationally expensive. This brief presented an optimization problem that combines the trajectory generation and control problem of a 5-link biped robot. We employed Beetle Antennae Search (BAS) for the problem’s online-solution, an intelligent online optimization approach. BAS is a single-particle searching algorithm, which makes it robust, computationally, and memory-wise efficient. We applied BAS on two non-linear systems, i.e., inverted pendulum and 5-link biped robot, and convincing results are obtained with BAS.

Accurate leaf segmentation and counting are critical for advancing crop phenotyping and improving breeding programs in agriculture. This study evaluates YOLOv11-based models for automated leaf detection and segmentation across spring barley, spring wheat, winter wheat, winter rye, and winter triticale. The key focus is assessing whether a unified model trained on a combined multi-crop dataset can outperform crop-specific models. Results show that the unified model achieves superior performance in bounding box tasks, with mAP@50 exceeding 0.85 for spring crops and 0.7 for winter crops. Segmentation tasks, however, reveal mixed results, with individual models occasionally excelling in recall for winter crops. These findings highlight the benefits of dataset diversity in improving generalization, while emphasizing the need for larger annotated datasets to address variability in real-world conditions. While the combined dataset improves generalization, the unique characteristics of individual crops may still benefit from specialized training.