With continuously increasing requirements for physical human-robot interaction (pHRI), cable-driven parallel robots (CDPRs) have emerged as outstanding systems for its implementation due to the sufficient motion workspace and inherent cable flexibility. In particular, their modular structure facilitates straightforward reconfiguration. Inspired by this, this paper aims to enhance the dynamic characteristics of CDPRs during pHRI through online reconfiguration, so as to achieve the interaction performance improvement based on human intent. A novel metric, the mixed interaction wrench margin (MIWM), is first proposed to determine the optimal reconfiguration. This metric is devised by integrating the interaction force characteristics with CDPR inherent workspace properties, while explicitly considering the leading role of human intent. Subsequently, an adaptive-interaction-based reconfiguration strategy is established that the configuration can be arbitrarily changed by cable anchors, enabling compliant and adaptive pHRI. Informed by the actual interaction frequency, the strategy implements an asynchronous adjustment with different periods for configuration change and platform movement to achieve online optimization for reconfiguration. Finally, simulations and experiments conducted on different CDPR configurations with multiple pHRI tasks indicate that this strategy provides humans with more freedom, allowing them to exert more casual interaction forces, receive a quicker interactive response, and operate in a larger workspace.

Self-balancing lower limb rehabilitation exoskeletons (SLLREs) allow individuals with lower limb dysfunction to walk without the use of crutches. Stable and human-like walking motions are crucial for SLLREs because achieving a close imitation of healthy human walking is a key goal in rehabilitation therapy. Existing SLLREs can realize stable walking but lack human-like features such as knee-stretched, heel-strike and toe-off. This paper designs a walking motion generator based on hierarchical optimization to generate a human-like walking motion with variable hip height, heelstrike, toe-off, and knee-stretched features. This generator consists of a knee-stretched optimizer and a stabilizing filter. Specifically, the knee-stretched optimizer realizes the stretched knee feature by optimizing the hip trajectory with varying heights. And the stabilizing filter realizes stable walking by optimizing the hip trajectory in the sagittal plane direction. To validate the effectiveness of the proposed human-like walking motion generator, walking experiments were conducted on SLLRE AutoLEE-G3 both in a simulation environment and the real world. The experimental results show that the humanlike walking motions look more natural and reduce the required torque for the knee joint compared with knee-bent walking.

The simple and modular structure of cable-driven parallel robots (CDPRs) can enable effective real-time reconfiguration. In this paper, an online reconfiguration strategy is proposed for a 3-DOF point-mass CDPR to adjust the cable anchor positions and enhance its performance in physical human-robot interaction (pHRI). The reconfiguration problem, inclusive of all relevant constraints such as the wrench feasible condition (WFC) and the structural constraint on the cable anchors, is formulated as a non-convex optimization problem to determine the optimal positions of cable anchors. However, such original formulation poses a serious challenge to real-time determination, primarily due to the non-convex constraint imposed by the WFC and the non-convex objective function. To address this issue, the characteristics of the CDPR are considered, and a linear approximation method is employed to simplify the original optimization problem into a linear one, allowing it to be efficiently solved by the dual simplex method. Additionally, an artificial potential field (APF) is designed, considering both the inherent workspace properties and the interaction force, to adjust the solution of the linear optimization problem, which ensures that the optimal solution remains within a safe distance from the boundary of the solution space. Simulations validate the effectiveness of the strategy in improving the interaction metric while satisfying constraints.

Low stiffness in 7-DOF cable-driven humanoid manipulators limits their precision, posing a significant challenge in complex human-robot interaction (HRI) scenarios. This paper presents a motion planning framework to enhance manipulator stiffness for both single and dual-arm configurations. For a single arm, we introduce a novel method that integrates dynamic obstacle avoidance with posture optimization to maximize end-effector stiffness. For dual-arm systems, we develop a coupled stiffness model that addresses inter-arm dynamics to improve performance in coordinated tasks. Experimental results on prototypes confirm that the proposed methods significantly reduce end-effector deviation under load, thereby improving the precision and reliability of these manipulators in sophisticated collaborative applications.

Owing to their lightweight design and structural flexibility, cable-driven dual-arm manipulators offer significant advantages in collaborative tasks. However, practical applications pose several challenges. The existence of environmental obstacles and the closed kinematic chain considerably increase the complexity of path planning. Furthermore, the inherently low stiffness of cable-driven systems can result in end-effector deformation, thereby reducing precision during path-following tasks. This paper proposes an adaptive, sampling-based path planning algorithm that addresses obstacle avoidance and closed kinematic chain constraint, facilitating efficient path planning in diverse operational environments. Additionally, an evaluation metric for the Cartesian stiffness of cable-driven dual-arm manipulators is introduced and incorporated into the proposed algorithm for optimization. This approach enhances both Cartesian stiffness and end-effector precision, thereby improving the reliability and accuracy of cable-driven dual-arm manipulators in practical applications.

In chemical laboratories, robot operation of instruments often relies on structured auxiliary positioning and teaching methods, which are complicated and laborious. Moreover, the single color, sparse textures, and uneven scales of instruments make the accuracy and robustness of existing visual 6-Dof pose estimation methods difficult to meet the requirement of robot operation. Therefore, we propose a novel pose estimation approach for automatic chemical laboratories using multi-level template matching to assist robots in operating instruments. This approach matches the query image with templates step by step from three levels: template, image, and pixel. During the matching processes from global to local, it achieves prediction of 2D key-point coordinates to accurately estimate instrument pose. At the same time, a template searching method based on the distribution pattern of feature points is proposed to ensure the accuracy of template searching in the real world. The experimental results show that our approach has good robustness and accuracy and meets the requirement of robot operation in automatic chemical laboratories. Note to Practitioners—This paper was motivated by the positioning problem of robot operation for instruments in automatic chemical laboratories. Structured auxiliary positioning methods are complicated and most of the pose estimation works are not suitable for practical applications at present. This paper suggests a novel template searching method and a pose estimation approach using multi-level matching for instruments. We calculate the distances, angles and point number of feature points to construct a new feature searching the best matched template with the input image. Then the predefined key pixels of the template are transformed into the input image from coarse to fine matching to ensure the accuracy and robustness. Due to the instrument CAD model, we can obtain the 2D-3D correspondences and calculate pose of the instrument by the PnP method. The experiment results validate that our method is suitable for practical robot operation in automatic chemical laboratories.

Natural language processing models are vulnerable to adversarial examples. Previous textual adversarial attacks adopt model internal information (gradients or confidence scores) to generate adversarial examples. However, this information is unavailable in the real world. Therefore, we focus on a more realistic and challenging setting, named hard-label attack, in which the attacker can only query the model and obtain a discrete prediction label. Existing hard-label attack algorithms tend to initialize adversarial examples by random substitution and then utilize complex heuristic algorithms to optimize the adversarial perturbation. These methods require a lot of model queries and the attack success rate is restricted by adversary initialization. In this paper, we propose a novel hard-label attack algorithm named LimeAttack, which leverages a local explainable method to approximate word importance ranking, and then adopts beam search to find the optimal solution. Extensive experiments show that LimeAttack achieves the better attacking performance compared with existing hard-label attack under the same query budget. In addition, we evaluate the effectiveness of LimeAttack on large language models and some defense methods, and results indicate that adversarial examples remain a significant threat to large language models. The adversarial examples crafted by LimeAttack are highly transferable and effectively improve model robustness in adversarial training.

This paper proposes an error state classifier based on the Gaussian Mixture Model (GMM) and a compliance controller for the peg-in-hole assembly task. The concepts of error states and error responses are introduced, and the mapping relationship between them is demonstrated. The GMM-based error state classifier maps the contact forces and torques generated in the assembly process to the probability of different error states. Furthermore, a new compliance controller based on error state probability is proposed to precisely adjust the pose error of the peg and hole. To validate the proposed method, a comparison with Admittance Control (ADC), Variable Compliance Center Control (VCC) and Feature-based Compliance Control (FBCC) is conducted in the task of inserting the vial into the centrifugal hole in the chemical experiment. The results show that the proposed method has a higher insertion success rate and less completion time and can significantly reduce the contact forces and torques during the insertion process.Note to Practitioners—This paper presents a novel error state classifier and a compliance controller for peg-in-hole assembly tasks. Compared to traditional methods, the proposed method can significantly reduce the forces and torques during the assembly process. The error state classifier is obtained by fitting the distribution of contact forces and torques under different error states using the GMM via offline training. During assembly, the classifier calculates the probability of different error states according to the forces and torques, and the proposed compliance controller then uses the error state probability and forces and torques to accurately adjust the pose error, thus ensuring assembly success and quality.

Five-hundred-meter aperture spherical radio telescope (FAST) is a very famous large-scale scientific facility with excellent performance for astronomical observation in the world, but it currently fails to observe the center of the Milky Way Galaxy due to the limited observation angle that is affected by the heavy weight of the feed cabin. To improve this problem, an upgraded feed mechanism (UFM) with a lighter cable structure is designed and employed to replace the existing heavy rigid A-B rotator and Stewart platform in the feed cabin of FAST. The structural dimension of the UFM is analyzed and optimized under cable tension constraints to meet the requirements of the observation angle. Then, a novel disturbance increment method is proposed to analyze the anti-disturbance ability of the UFM, where a gradually increased disturbance wrench is applied to the UFM with the stiffness matrix iteratively updated. Through the dimensional optimization and further anti-disturbance analysis, the newly-designed UFM can indeed meet the higher demand for astronomical observation with the larger observation angle, which benefits from the lightweight cable structure. Besides, the UFM also has the appreciable anti-disturbance ability for long-term stable operation of FAST.

Flame detection is a key module of fire-fighting robots, especially for autonomous fire suppression. To effectively tackle the fire-fighting tasks, fire-fighting robots are usually equipped with multimodal vision systems. On the one hand, cameras of different modalities can provide complementary visual information. On the other hand, the differences in installation position and resolution between different cameras also result in weakly aligned image pairs, that is, the positions of the same object in different modal images are inconsistent. Directly fusing the image features of different modalities is difficult to meet the accuracy and false alarm requirements of fire-fighting robots. Therefore, we propose a multimodal flame detection model based on projection and attention guidance. First, we use projection to obtain the approximate position of the flame in the thermal image and employ a neighbor sampling module to detect flames around it. Second, we design an attention guidance module based on index matching, which applies the attention map generated by the thermal modality to optimize the regional feature of the color modality. Experiments on multimodal datasets collected by an actual fire-fighting robot validate that the proposed method is effective in both fire and nonfire environments.

Dynamic movement primitives (DMPs) are a flexible trajectory learning scheme widely used in motion generation of robotic systems. However, existing DMP-based methods mainly focus on simple go-to-goal tasks. Motivated to handle tasks beyond point-to-point motion planning, this work presents temporal logic guided optimization of motion primitives, namely$\mathbf{PI}^{\mathbf{BB}-\mathbf{TL}}$algorithm, for complex manipulation tasks with user preferences. In particular, weighted truncated linear temporal logic (wTLTL) is incorporated in the$\mathbf{PI}^{\mathbf{BB}-\mathbf{TL}}$algorithm, which not only enables the encoding of complex tasks that involve a sequence of logically organized action plans with user preferences, but also provides a convenient and efficient means to design the cost function. The black-box optimization is then adapted to identify optimal shape parameters of DMPs to enable motion planning of robotic systems. The effectiveness of the$\mathbf{PI}^{\mathbf{BB}-\mathbf{TL}}$algorithm is demonstrated via simulation and experiment.

Robotic grasping ability lags far behind human skills and poses a significant challenge in the robotics research area. According to the grasping part of an object, humans can select the appropriate grasping postures of their fingers. When humans grasp the same part of an object, different poses of the palm will cause them to select different grasping postures. Inspired by these human skills, in this article, we propose new grasping posture prediction networks (GPPNs) with multiple inputs, which acquire information from the object image and the palm pose of the dexterous hand to predict appropriate grasping postures. The GPPNs are further combined with grasping rectangle detection networks (GRDNs) to construct multilevel convolutional neural networks (ML-CNNs). In this study, a force-closure index was designed to analyze the grasping quality, and force-closure grasping postures were generated in the GraspIt! environment. Depth images of objects were captured in the Gazebo environment to construct the dataset for the GPPNs. Herein, we describe simulation experiments conducted in the GraspIt! environment, and present our study of the influences of the image input and the palm pose input on the GPPNs using a variable-controlling approach. In addition, the ML-CNNs were compared with the existing grasp detection methods. The simulation results verify that the ML-CNNs have a high grasping quality. The grasping experiments were implemented on the Shadow hand platform, and the results show that the ML-CNNs can accurately complete grasping of novel objects with good performance.

Achieving high-precision position control while maintaining positive cable tensions is the most challenging issue for the motion control of cable-driven parallel robots, which should be considered significantly. Different from the existing control schemes with online tension distribution that needs real-time computing in each control cycle, a novel dual-loop dynamic control scheme is proposed in this article, where a paralleled dual-loop tracking strategy is introduced to provide a more compatible scheme, which consists of two tracking loops: 1) the tension control loop and 2) the position control loop. In the former loop, the offline tension distribution is adopted to avoid cable hanging loosely and the real-time feasibility of the distribution method is no longer a necessary demand. In the latter loop, due to the complex dynamics characterized by the cable-driven form, the cooperative motion relation among multiple cables and inevitable external disturbances are investigated comprehensively, and the robust synchronization method is included to guarantee the high-precision position control. Afterward, the Lyapunov method is adopted to analyze the strict stability of the whole closed-loop system with both the position and tension control feedback. The experiments indicate that by synthesizing the two control loops, the proposed scheme can dramatically reduce the tracking errors in the trajectory tracking while avoiding the cable relaxation, and particularly, has a satisfactory control effect when the velocity and acceleration of the trajectory have significant oscillations. Additionally, the strong disturbance rejection ability is also validated via robustness experiments.

To achieve high-accuracy grasping of unknown objects, we present novel multilevel convolutional neural networks (CNNs) for robotic grasping with a parallel gripper or multifingered dexterous hand. The multilevel CNNs include four levels with different structures and functions. The first level is constructed to get the approximate position of the grasped object. The second level aims to obtain the preselected grasping rectangles. The third level is constructed to re-evaluate the preselected grasping rectangles and obtain substantially detailed features with quite a large network, so as to assess each preselected grasping rectangle exactly. By using a selection algorithm, the optimal grasping rectangle can be determined and unknown object grasping can be achieved with a parallel gripper. The purpose of the fourth level is to obtain the finger position distribution to complete the accurate grasping of unknown objects with a multifingered dexterous hand. The test results indicate that, compared to state-of-the-art methods, the proposed multilevel CNNs can greatly increase the precision of the grasping rectangle. Grasping experiments were implemented on a Youbot arm with five degrees of freedom and a Shadow four-fingered dexterous hand. The results show that the multilevel CNNs can determine the optimal grasping rectangle and finger position distribution, thereby achieving high-accuracy grasping of various unknown objects, even under several complex environmental conditions.Note to Practitioners—Robot grasping of objects lags far behind human experiences and poses a significant challenge in the robotics area. To solve it, we present new multilevel convolutional neural networks (CNNs) to process red green blue-depth (RGB-D) images and realize optimal grasping detection of unknown objects. Moreover, we provide details of the network structure, network training, and network testing. The testing results obtained from the open grasping data set show that the multilevel CNNs can significantly increase the accuracy of the grasping rectangle compared to state-of-the-art methods. Experiments were implemented on different robotic platforms, including a five-degrees-of-freedom Youbot arm with a parallel gripper and a UR5 robot arm with a Shadow multifingered dexterous hand. The results validate that the multilevel CNNs offer excellent generalization and robustness for handling different sizes and shapes of unknown objects, as well as background disturbances, which are key problems in robotic manipulation.

Cable-driven parallel robots (CDPRs) are a new type of parallel robots that use cables to control a mobile platform. They possess several advantages, including large workspace, low inertia, and high payload capacity. However, there are several problems in the high-precision trajectory tracking control of CDPRs. On the one hand, all the cables must remain in tension during the entire motion process. On the other hand, the controller design is subjected to model uncertainties and external disturbances. Accordingly, this article proposes a robust synchronization control (RSC) scheme in the cable length space to achieve high-precision trajectory tracking. The synchronization control ensures motion coordination among all the cables and prevents cable relaxation, whereas the robust control eliminates modeling errors and restrains external disturbances. The uniformly ultimate boundedness of the tracking and synchronization errors in the closed-loop system equation was proved using the Lyapunov theory. Simulations and experiments of the trajectory tracking control were both implemented on a three-degree-of-freedom CDPR. Compared with the adaptive robust control scheme and the augmented proportional derivative scheme on the premise of the approximate energy consumption, the proposed RSC scheme could reduce not only the tracking errors of the cables but also the synchronization errors between adjacent cables. Moreover, the RSC scheme could significantly improve the trajectory tracking accuracy of the mobile platform. The robustness of this scheme was verified using load experiments and torque-disturbance experiments.

We propose a novel trajectory planning algorithm to avoid obstacles in robotic manipulation by using imitation learning method. It focuses on how to plan feasible trajectories in the manipulation environment by imitating human experience. The main components of our algorithm include a path point prediction network and a trajectory generation strategy. The network is primarily composed of several Long Short-Term Memory (LSTM) layers and a Mixture Density Network (MDN) layer with Gaussian functions, thus it can cope with sequential information and fit the multimodal dataset well. To improve the smoothness of the trajectories generated by the networks, trajectory points are sampled from the Gaussian function which has the minimal change in the configuration space. Besides, multiple trajectories are generated for a given input and the best one can be selected to accomplish the task by improving the precision of the planning algorithm. Finally, simulation experiments conducted in Gazebo simulator verify that our planning algorithm has good performance in robotic manipulation with obstacle avoidance.

This paper addresses the dynamic trajectory planning of a spatial cable-suspended parallel robot with three cables and three-degree-of-freedom. A new s - s̈ plane (a is the path parameter) method is presented to devise dynamically feasible point-to-point trajectories and periodic trajectories that are not fully located in the static workspace (SW) of the robot. First, the unilateral cable tension constraints are explicitly converted into geometry constraints in the s - s̈ plane. Then, a set of reachable workspaces is defined, which can be obtained analytically and the volumes of which are all much larger than the volume of the SW. By designing dynamic point-to-point trajectories directly in the s - s̈ plane, any points in the reachable workspaces can be reached in sequence via some intermediate points in the SW. The s - s̈ plane method also offers insights into planning periodic circular trajectory and transition trajectory for oscillations along a straight line, which is considered to be more efficient than the algebraic method provided in the literature. The proposed method always guarantees positive and continuous cable tensions and yields analytical results. The performance of the method is evaluated through numerical simulations and experiments.

This paper presents a task space coordination controller for the parallel manipulators with actuation redundancy to improve the motion relation between multiple kinematic chains. According to the mechanism characteristic of multiple kinematic chains, two different types of synchronization error are developed in the joint space of active joints and in the task space of end-effector, respectively. The coordination controller is designed by using the synchronization error, and it is proved to guarantee asymptotic convergence to zero of both tracking error and synchronization error with the Barbalat's Lemma. The trajectory tracking experiments are carried out on an actual parallel manipulator with actuation redundancy, and the superiority of the coordination controller over the traditional augmented PD (APD) controller is studied.