To improve the efficiency of deep reinforcement learning (DRL)-based methods for robotic trajectory planning in the unstructured working environment with obstacles. Different from the traditional sparse reward function, this paper presents two brand-new dense reward functions. First, the azimuth reward function is proposed to accelerate the learning process locally with a more reasonable trajectory by modeling the position and orientation constraints, which can reduce the blindness of exploration dramatically. To further improve the efficiency, a reward function at subtask-level is proposed to provide global guidance for the agent in the DRL. The subtask-level reward function is designed under the assumption that the task can be divided into several subtasks, which reduces the invalid exploration greatly. The extensive experiments show that the proposed reward functions are able to improve the convergence rate by up to three times with the state-of-the-art DRL methods. The percentage increase in convergence means is 2.25%-13.22% and the percentage decreases with respect to standard deviation by 10.8%-74.5%.

The traditional Denavit–Hatenberg method is a relatively mature method for modeling the kinematics of robots. However, it has an obvious drawback, in that the parameters of the Denavit–Hatenberg model are discontinuous, resulting in singularity when the adjacent joint axes are parallel or close to parallel. As a result, this model is not suitable for kinematic calibration. In this article, to avoid the problem of singularity, the product of exponentials method based on screw theory is employed for kinematics modeling. In addition, the inverse kinematics of the 6R robot manipulator is solved by adopting analytical, geometric, and algebraic methods combined with the Paden–Kahan subproblem as well as matrix theory. Moreover, the kinematic parameters of the Denavit–Hatenberg and the product of exponentials-based models are analyzed, and the singularity of the two models is illustrated. Finally, eight solutions of inverse kinematics are obtained, and the correctness and high level of accuracy of the algorithm proposed in this article are verified. This algorithm provides a reference for the inverse kinematics of robots with three adjacent parallel joints.

To improve the efficiency of surgical trajectory segmentation for surgical assessment and robot learning in robot-assisted minimally invasive surgery, this paper presents a fast unsupervised method using video and kinematic data, followed by a promoting procedure to address the over-segmentation issue. An unsupervised deep learning network called dense convolutional encoder–decoder network (DCED-Net) is first proposed to extract more discriminative features from videos in an effective way. DCED-Net has several advantages. It compresses the encoding–decoding structure, strengthens the feature propagation, and avoids the manual annotation. To further improve the accuracy of segmentation, on one hand, a modified transition state clustering model is employed with a strategy of reducing the redundancy of transition points. On the other hand, the segmentation results are promoted by identifying the over-segmented trajectories based on predefined similarity measurements. Extensive experiments on the public data set JIGSAWS show that with our method, the percentage increase in accuracy is 20.3% and the percentage decrease in time cost is 92.6%.

Dual-arm coordination is a fundamental problem in humanoid nursing robot. Large language model (LLM)-driven dual-arm collaboration is gradually becoming a research hotspot in this field. However, the single-thread LLM task planner lacks the ability of co-scheduling, which leads to poor efficiency in nursing robot. To cope with the problem, this letter proposed a multi-agent LLM solution for the task planning of nursing robot, named DABICO. The framework constructs dual agent systems (left-arm and right-arm) at the levels of communication and decision-making, as well as ensuring a single robot entity. Moreover, we construct corresponding communication mechanism and dialogue protocol to promote the information exchange between the two agents. Finally, validation feedback system is proposed to ensure that the sub-task of each robot arm can be executed successfully. A large set of experiments show that, compared to the single-thread LLM task planner, the DABICO framework is more advantageous when dealing with the bimanual coordination tasks. DABICO is able of accomplishes reasoning rapidly, reducing Replan metrics by $\mathbf{90\%}$ on average, and the improvement with respect to Success rate is $\mathbf{11\%}$ on average. Finally we demonstrate DABICO in real-world medicine organization experiment on a dual-arm nursing robot.

Photorealistic stylization aims to transfer the style of a reference photo onto a content photo in a natural fashion, such that the stylized image looks like a real photo taken by a camera. State-of-the-art methods stylize the image locally within each matched semantic region and are prone to global color inconsistency across semantic objects/parts, making the stylized image less photorealistic. To tackle the challenging issues, we propose a non-local representation scheme, constrained with a mutual affine-transfer network (NL-MAT). Through a dictionary-based decomposition, NL-MAT is able to successfully decouple matched non-local representations and color information of the image pair, such that the context correspondence between the image pair is incorporated naturally, which largely facilitates local style transfer in a global-consistent fashion. To the best of our knowledge, this is the first attempt to address the photorealistic stylization problem with a non-local representation scheme, such that no additional models or steps for semantic matching are required during stylization. Experimental results demonstrate that the proposed method is able to generate photorealistic results with local style transfer while preserving both the spatial structure and global color consistency of the content image.