This paper proposes an online robust self-learning terminal sliding mode control (RS-TSMC) with stability guarantee for balancing control of reaction wheel bicycle robots (RWBR) under model uncertainties and disturbances, which improves the balancing control performance of RWBR by optimising the constrained output of TSMC. The TSMC is designed for a second-order mathematical model of RWBR. Then robust adaptive dynamic programming based on an actor-critic algorithm is used to optimise the TSMC only by data sampled online. The system closed-loop stability and convergence of the neural network weights are guaranteed based on the Lyapunov analysis. The effectiveness of the proposed algorithm is demonstrated through simulations and experiments.

Elbow, with complex physiological structure, plays an important role in upper limb motion which can be assisted with exoskeleton in rehabilitation. However, the stiffness of elbow changes while training which decline the comfort and effect of rehabilitation. Moreover, the rotation axis of elbow is changing which will cause secondary injuries. In this paper, we design an elbow exoskeleton with a variable stiffness actuator and a deviation compensation unit to assist elbow rehabilitation. Firstly, we design a variable stiffness actuator by symmetric actuation principle to adapt the change of elbow stiffness. The parameters of the variable stiffness actuator are optimized by motion simulation. Next, we design a deviation compensation unit to follow the rotation axis deviation outside the horizontal plane. The compensation area is simulated to cover the deviation. Finally, simulation and experiments are carried out to show the performance of our elbow exoskeleton. The workspace can meet the need of daily elbow motion while the variable stiffness actuator can adjust the exoskeleton stiffness as expectation.

Soft robots show an advantage when conducting tasks in complex environments due to their enormous flexibility and adaptability. However, soft robots suffer interactions and nonlinear deformation when interacting with soft and fluid materials. The reason behind is the free boundary interactions, which refers to undetermined contact between soft materials, specifically containing nonlinear deformation in air and nonlinear interactions in fluid for soft robot simulation. Therefore, we propose a new approach using material point method (MPM), which can solve the free boundary interactions problem, to simulate soft robots under such environments. The proposed approach can autonomously predict the flexible and versatile behaviors of soft robots. Our approach entails incorporating automatic differentiation into the algorithm of MPM to simplify the computation and implement an efficient implicit time integration algorithm. We perform two groups of experiments with an ordinary pneumatic soft finger in different free boundary interactions. The results indicate that it is possible to simulate soft robots with nonlinear interactions and deformation, and such environmental effects on soft robots can be restored.

Robot pick-and-place for unknown objects is still a very challenging research topic. This paper proposes a multi-modal learning method for robot one-shot imitation of pick-and-place tasks. This method aims to enhance the generality of industrial robots while reducing the amount of data and training costs the one-shot imitation method relies on. The method first categorizes human demonstration videos into different tasks, and these tasks are classified into six types to symbolize as many types of pick-and-place tasks as possible. Second, the method generates multi-modal prompts and finally predicts the action of the robot and completes the symbolic pick-and-place task in industrial production. A carefully curated dataset is created to complement the method. The dataset consists of human demonstration videos and instance images focused on real-world scenes and industrial tasks, which fosters adaptable and efficient learning. Experimental results demonstrate favorable success rates and loss results both in simulation environments and real-world experiments, confirming its effectiveness and practicality.

In numerous applications, extracting a single rotation component (termed “planar rotation”) from a 3D rotation is of significant interest. In biomechanics, for example, the analysis of joint angles within anatomical planes offers better clinical interpretability than spatial rotations. Moreover, in parallel kinematics robotic machines, unwished rotations about an axis – termed “parasitic motions” – need to be excluded. However, due to the non-Abelian nature of spatial rotations, these components cannot be extracted by simple projections as in a vector space. Despite extensive discussion in the literature about the non-uniqueness and distortion of the results due to the nonlinearity of the SO(3) group, they continue to be used due to the absence of alternatives. This paper reviews the existing methods for planar-rotation extraction from 3D rotations, showing their similarities and differences as well as inconsistencies by mathematical analysis as well as two application cases, one of them from biomechanics (flexural knee angle in the sagittal plane). Moreover, a novel, simple, and efficient method based on a pseudo-projection of the Quaternion rotation vector is introduced, which circumvents the ambiguity and distortion problems of existing approaches. In this respect, a novel method for determining the orientation of a box from camera recordings based on a two-plane projection is also proposed, which yields more precise results than the existing Perspective 3-Point Problem from the literature. This paper focuses exclusively on the case of finite rotations, as infinitesimal rotations within a single plane are non-holonomic and, through integration, produce rotation components orthogonal to the plane.

This paper introduces a sophisticated trajectory capture and playback mechanism for collaborative robots, aimed at enhancing accuracy and operational efficiency through several innovative techniques. The Ju-Gibbs attitude quaternion is utilized for enhanced kinematic modeling across multi-axis systems, which simplifies variables, reduces dimensions, and enhances symbolic clarity, thus surpassing the limitations of traditional rotation vectors and unit quaternions. A new sliding filter is developed to effectively reduce noise and optimize trajectory details more efficiently. Additionally, an automated mechanism is implemented for adjusting the sampling rate and removing static data points at the trajectory’s start and end, further refining data collection accuracy. These advancements have been successfully replicated on the Kuka robot LBR iiwa 7 R800, demonstrating the practical applicability of the solutions in real-world settings.

Remote center-of-motion (RCM) manipulators are a key issue in minimally invasive surgeries (MIS). The existing RCM parallel mechanisms (PMs) can only generate RCM motion based on the invariant RCM. To provide mobility for RCM, this paper designed a new family of RCM PMs with movable RCM that features a double-stage topological structure. Drawing mainly on configuration evolution and Lie-group, a general approach is proposed to design double-stage PMs with movable RCM. Feasible limbs for 2R1T RCM motion are enumerated and used to construct the secondary PM. Type synthesis of the primary PMs that realize movable RCM is accomplished based on the method presented. Different connection styles between the two stages that ensure the geometrical conditions of RCM motion are designed. Using different connection styles, double-stage PMs with movable RCM are constructed. These new RCM PMs can realize precise positioning of RCM by taking advantage of the primary PMs, which indicates their potential application prospects in MIS.

The path planning and obstacle-crossing motion planning of cable trench inspection robots are essential for achieving automated inspection. To improve path planning efficiency and obstacle navigation in complex environments, an enhanced global path planning algorithm based on the A* algorithm has been developed, combined with an improved Dynamic Window Approach (DWA) for local path planning. For unavoidable obstacles, a specific obstacle-crossing motion planning strategy has been formulated. The enhanced A* algorithm improves efficiency and safety through adaptive neighborhood expansion and the elimination of redundant path points. The improved DWA algorithm enables real-time dynamic obstacle avoidance in local path planning. The simulation results on a $20 \times 20$ grid map indicate that the improved A* algorithm reduces the number of nodes by 58.4% and shortens the path length by 6.1% compared to the traditional A* algorithm, demonstrating significant advantages over other conventional path planning algorithms. In the simulation experiments integrating global and local path planning, the enhanced A* algorithm combined with the improved DWA algorithm reduces the path length by 3.2% on the $20 \times 20$ grid map compared to the integration with the traditional DWA algorithm. On the $30 \times 30$ grid maps with different obstacle configurations, the path lengths are reduced by 3.5% and 3.6%, respectively. In the obstacle-crossing experiments, the robot successfully overcame obstacles of 10 cm and 20 cm in height. The proposed path planning algorithm and obstacle-crossing motion planning strategy hold substantial application potential in complex environments, offering reliable technical support for cable trench inspection robots.

The article introduces a novel class of 4R1H mechanisms, where 4R indicates four revolute joints and 1H indicates one helical joint. The paper starts with the type synthesis of these mechanisms, which involves combining two kinematic chains with planar and cylindrical motion types into a single closed-loop kinematic chain. If we fix any link in such a chain, we get a workable mechanism. The synthesis procedure considers two options for the relative arrangement of these two kinematic chains. Adding an H joint to the kinematic chain allows us to design mechanisms whose output link performs spatial motion. Using the proposed synthesis procedure, we develop a family of 4R1H mechanisms. Next, we choose one mechanism as a representative example and consider its mobility, singularity, kinematic, and dynamic analysis. Using screw theory, we confirm the mechanism has one degree of freedom and determine its singular configurations. Kinematic analysis provides closed-form expressions to calculate displacements, velocities, and accelerations of all the mechanism links. Dynamic analysis uses these results to compute the motor torque required for one motion cycle. To verify the suggested analytical algorithms and obtained results, we use computer-aided design tools, which allow us to develop virtual and physical prototypes.

This paper presents Hybrid Modified A* (HMA*) algorithm which is used to control an omnidirectional mecanum wheel automated guided vehicle (AGV). HMA* employs Modified A* and PSO to determine the best AGV path. The HMA* overcomes the A* technique’s drawbacks, including a large number of nodes, imprecise trajectories, long calculation times, and expensive path initialization. Repetitive point removal refines Modified A*’s path to locate more important nodes. Real-time hardware control experiments and extensive simulations using Matlab software prove the HMA* technique works well. To evaluate the practicability and efficiency of HMA* in route planning and control for AGVs, various algorithms are introduced like A*, Probabilistic Roadmap (PRM), Rapidly-exploring Random Tree (RRT), and bidirectional RRT (Bi-RRT). Simulations and real-time testing show that HMA* path planning algorithm reduces AGV running time and path length compared to the other algorithms. The HMA* algorithm shows promising results, providing an enhancement and outperforming A*, PRM, RRT, and Bi-RRT in the average length of the path by 12.08%, 10.26%, 7.82%, and 4.69%, and in average motion time by 21.88%, 14.84%, 12.62%, and 8.23%, respectively. With an average deviation of 4.34% in path length and 3% in motion time between simulation and experiments, HMA* closely approximates real-world conditions. Thus, the proposed HMA* algorithm is ideal for omnidirectional mecanum wheel AGV’s static as well as dynamic movements, making it a reliable and efficient alternative for sophisticated AGV control systems.

Optical microrobots are activated by a laser in a liquid medium using optical tweezers. To create visual control loops for robotic automation, this work describes a deep learning-based method for orientation estimation of optical microrobots, focusing on detecting 3-D rotational movements and localizing microrobots and trapping points (TPs). We integrated and fine-tuned You Only Look Once (YOLOv7) and Deep Simple Online Real-time Tracking (DeepSORT) algorithms, improving microrobot and TP detection accuracy by $\sim 3$% and $\sim 11$%, respectively, at the 0.95 Intersection over Union (IoU) threshold in our test set. Additionally, it increased mean average precision (mAP) by 3% at the 0.5:0.95 IoU threshold during training. Our results showed a 99% success rate in trapping events with no false-positive detection. We introduced a model that employs EfficientNet as a feature extractor combined with custom convolutional neural networks (CNNs) and feature fusion layers. To demonstrate its generalization ability, we evaluated the model on an independent in-house dataset comprising 4,757 image frames, where microrobots executed simultaneous rotations across all three axes. Our method provided mean rotation angle errors of $1.871^\circ$, $2.308^\circ$, and $2.808^\circ$ for X (yaw), Y (roll), and Z (pitch) axes, respectively. Compared to pre-trained models, our model provided the lowest error in the Y and Z axes while offering competitive results for X-axis. Finally, we demonstrated the explainability and transparency of the model’s decision-making process. Our work contributes to the field of microrobotics by providing an efficient 3-axis orientation estimation pipeline, with a clear focus on automation.

Precise pose estimation is crucial to various robots. In this paper, we present a localization method using correlative scan matching (CSM) technique for indoor mobile robots equipped with 2D-LiDAR to provide precise and fast pose estimation based on the common occupancy map. A pose tracking module and a global localization module are included in our method. On the one hand, the pose tracking module corrects accumulated odometry errors by CSM in the classical Bayesian filtering framework. A low-pass filter associating the predictive pose from odometer with the corrected pose by CSM is applied to improve precision and smoothness of the pose tracking module. On the other hand, our localization method can autonomously detect localization failures with several designed trigger criteria. Once a localization failure occurs, the global localization module can recover correct robot pose quickly by leveraging branch-and-bound method that can minimize the volume of CSM-evaluated candidates. Our localization method has been validated extensively in simulated, public dataset-based, and real environments. The experimental results reveal that the proposed method achieves high-precision, real-time pose estimation, and quick pose retrieve and outperforms other compared methods.

In this study, a novel kinematic modeling method of parallel mechanism is proposed. It can obtain position and posture space simultaneously in a single model. Compared with the traditional method only based on inverse kinematics, the novel method can significantly improve computational performance. The original evaluation metric $\mathfrak{R}$ is proposed to evaluate the performance of the two modeling methods. Three groups of experiments with different calculation times are carried out for the classical PPU-3RUS parallel mechanism, and the new RS-3UPRU parallel mechanism after the effectiveness and wide applicability of the novel modeling method is proved. The calculation time and output rate are recorded, respectively, and then the respective $\mathfrak{R}$ values are obtained by weighting. The results show that the novel modeling method has better performance.

Expert drivers possess the ability to execute high sideslip angle maneuvers, commonly known as drifting, during racing to navigate sharp corners and execute rapid turns. However, existing model-based controllers encounter challenges in handling the highly nonlinear dynamics associated with drifting along general paths. While reinforcement learning-based methods alleviate the reliance on explicit vehicle models, training a policy directly for autonomous drifting remains difficult due to multiple objectives. In this paper, we propose a control framework for autonomous drifting in the general case, based on curriculum reinforcement learning. The framework empowers the vehicle to follow paths with varying curvature at high speeds, while executing drifting maneuvers during sharp corners. Specifically, we consider the vehicle’s dynamics to decompose the overall task and employ curriculum learning to break down the training process into three stages of increasing complexity. Additionally, to enhance the generalization ability of the learned policies, we introduce randomization into sensor observation noise, actuator action noise, and physical parameters. The proposed framework is validated using the CARLA simulator, encompassing various vehicle types and parameters. Experimental results demonstrate the effectiveness and efficiency of our framework in achieving autonomous drifting along general paths. The code is available at https://github.com/BIT-KaiYu/drifting.

Extensible continuum robots (ECRs) offer distinct advantages over conventional continuum robots due to their ability to enhance workspace adaptability through length adjustments. This makes ECRs particularly promising for applications that require variable lengths involving the manipulation of objects in challenging environments, such as risky, cluttered, or confined. The development of ECRs necessitates careful consideration of mechanical structures, actuation methods, methods of stiffness variability, and control methods. The selection of papers is based on their relevance to ECRs within the period of 2010 to 2023 in the databases of Scopus and Web of Science. Distinguishing itself from other review papers, this paper aims to deliver a comprehensive and critical discussion about the advantages and disadvantages of ECRs concerning their mechanical structures, actuation methods, stiffness variability, and control methods. It is a beneficial resource for researchers and engineers interested in ECRs, providing essential insights to guide future developments in this field. Based on the literature, existing ECRs exhibit an inherent trade-off between flexibility and structural strength due to the absence of systematic design methods. Additionally, there is a lack of intelligent and effective controllers for achieving complex control performance and autonomous stiffness variability.

The large number of patients with ankle injuries and the high incidence make ankle rehabilitation an urgent health problem. However, there is a certain degree of difference between the motion of most ankle rehabilitation robots and the actual axis of the human ankle. To achieve more precise ankle joint rehabilitation training, this paper proposes a novel 3-PUU/R parallel ankle rehabilitation mechanism that integrates with the human ankle joint axis. Moreover, it provides comprehensive ankle joint motion necessary for effective rehabilitation. The mechanism has four degrees of freedom (DOFs), enabling plantarflexion/dorsiflexion, eversion/inversion, internal rotation/external rotation, and dorsal extension of the ankle joint. First, based on the DOFs of the human ankle joint and the variation pattern of the joint axes, a 3-PUU/R parallel ankle joint rehabilitation mechanism is designed. Based on the screw theory, the inverse kinematics inverse, complete Jacobian matrix, singular characteristics, and workspace analysis of the mechanism are conducted. Subsequently, the motion performance of the mechanism is analyzed based on the motion/force transmission indices and the constraint indices. Then, the performance of the mechanism is optimized according to human physiological characteristics, with the motion/force transmission ratio and workspace range as optimization objectives. Finally, a physical prototype of the proposed robot was developed, and experimental tests were performed to evaluate the above performance of the proposed robot. This study provides a good prospect for improving the comfort and safety of ankle joint rehabilitation from the perspective of human-machine axis matching.

To meet the high-precision positioning requirements for hybrid machining units, this article presents a geometric error modeling and source error identification methodology for a serial–parallel hybrid kinematic machining unit (HKMU) with five axis. A minimal kinematic error modeling of the serial–parallel HKMU is established with screw-based method after elimination of redundant errors. A set of composite error indices is formulated to describe the terminal accuracy distribution characteristics in a quantitative manner. A modified projection method is proposed to determine the actual compensable and noncompensable source errors of the HKMU by identifying such transformable source errors. Based on this, the error compensation and comparison analysis are carried out on the exemplary HKMU to numerically verify the effectiveness of the proposed modified projection method. The geometric error evaluations reveal that the parallel module has a larger impacts on the terminal accuracy of the platform of the HKMU than the serial module. The error compensation results manifest that the modified projection method can find additional compensable source errors and significantly reduce the average and maximum values of geometric errors of the HKMU. Hence, the proposed methodology can be applied to improve the accuracy of kinematic calibration of the compensable source errors and can reduce the difficulty and workload of tolerance design for noncompensable source errors of such serial–parallel hybrid mechanism.

In order to make a fast and accurate response to gas leakage event, e.g. gas leakage in hydrogen storage station, it is very important to identify and locate the leakage source accurately and quickly. Due to the flexibility and the adaptability of robots to harsh environments, leakage source tracing based on mobile robots has attracted more and more attention. However, the existing ground robots are limited by the ground environment and thus it is difficult to trace and locate the leakage in the complex environment with ground robots. Although unmanned aerial vehicle (UAV) can overcome the limitation of ground obstacles, there are still some problems in the accuracy and reliability of gas sampling due to the interference of flow field caused by UAV rotors to the surrounding gases. Based on computational fluid dynamic simulation, a simulation model of UAV with four rotors was established. Combined with test experiments, the influence of flow field around UAV on gas sampling under different UAV speeds, rotors assembly structures, leakage, and sampling conditions was analyzed and investigated. The optimized UAV assembly structure and gas sensor installation position were determined and verified by the simulations and experiments. The results showed that the sensor was less affected by the rotor airflow when the UAV rotor was reversely assembled and the gases were sampled above the UAV. This research can provide a guidance for gas sampling for emission source tracing with UAV for process safety management of energy gas storage.

Precise and efficient grasping detection is vital for robotic arms to execute stable grasping tasks in industrial and household applications. However, existing methods fail to consider refining different scale features and detecting critical regions, resulting in coarse grasping rectangles. To address these issues, we propose a real-time coarse and fine granularity residual attention (CFRA) grasping detection network. First, to enable the network to detect different sizes of objects, we extract and fuse the coarse and fine granularity features. Then, we refine these fused features by introducing a feature refinement module, which enables the network to distinguish between object and background features effectively. Finally, we introduce a residual attention module that handles different shapes of objects adaptively, achieving refined grasping detection. We complete training and testing on both Cornell and Jacquard datasets, achieving detection accuracy of 98.7% and 94.2%, respectively. Moreover, the grasping success rate on the real-world UR3e robot achieves 98%. These results demonstrate the effectiveness and superiority of CFRA.

This article addresses the localization problem in robotic autonomous luggage trolley collection at airports and provides a systematic evaluation of different methods to solve it. The robotic autonomous luggage trolley collection is a complex system that involves object detection, localization, motion planning and control, manipulation, etc. Among these components, effective localization is essential for the robot to employ subsequent motion planning and end-effector manipulation because it can provide a correct goal position. This article explores four popular and representative localization methods for object localization in luggage trolley collection: radio frequency identification (RFID), Keypoints, ultrawideband (UWB), and Reflectors. A qualitative evaluation framework is constructed to assess performance, encompassing Localization Accuracy, Mobile Power Supplies, Coverage Area, Cost, and Scalability. Furthermore, a series of quantitative experiments concerning Localization Accuracy and Success Rate have been conducted on a real-world robotic autonomous luggage trolley collection system. The performance of various localization methods is further analyzed based on experimental results, indicating that the Keypoints method is optimally suited for indoor environments to facilitate luggage trolley collection. Significantly, these experiment results provide a valuable reference point, extending the application of indoor localization methods across diverse scenarios. A website about this work is available at https://sites.google.com/view/localization-evaluation/.