In this paper, a Pythagorean-Hodograph (PH) curve-based pick-and-place operation trajectory planning method for Delta parallel robots is proposed, which realizes the flexible control of pick-and-place operations to meet the requirements of various practical scenarios. First, according to the geometric relationship of pick-and-place operation path, different pick-and-place operations are classified. Then trajectory planning is carried out for different situations, respectively, and in each case, the different polynomial motion laws adopted by the linear motion segment and the curved motion segment are solved. Trajectory optimization is performed with the motion period as optimization objective. The proposed method is easier to implement, and at the same time satisfies the safety, optimization, mobility, and stability of the robot; that is, the proposed method realizes obstacle avoidance, optimal time, flexible control of the robot trajectory, and stable motion. Simulations and experiments verify the effectiveness of the method proposed in this paper. The proposed method can not only realize the fast, accurate, and safe operation in intelligent manufacturing fields such as rapid classification, palletizing, grasping, warehousing, etc., but its research route can also provide a reference for trajectory planning of intelligent vehicles in logistics system.

The phenomenal growth in the utilization of commercial unmanned aerial vehicles (UAVs) or drones leads to an urgent need for new approaches to ensure safety in the sky. Effective aerial surveillance requires patrolling swarms to react according to the various behaviors demonstrated by intruding swarms, but existing approaches are not practical when dealing with a large number of drones. Specifically, predicting the behaviors or planned paths of the intruding swarms is highly challenging as intruders may perform evasive strategies to avoid detection. Therefore, this work utilizes heuristic search strategies and investigates how various intruder behaviors affect the search performance. To investigate the search performance, a swarm versus swarm simulator is developed. Using the simulator, first, a comparative study is performed to evaluate how intruders’ behaviors can affect the performance of the patrolling swarm. Subsequently, three approaches, including single-objective optimization, multi-objective optimization, and Lévy flight, are compared in terms of their detection performance in a bounded space. The results suggest that multi-objective optimization outperforms both single-objective optimization and Lévy flight-based approaches. Furthermore, our results show that intruders have a lower chance of being tracked when moving in a dense crowd, and this finding reaffirms the schooling behaviors of fish. In a specific simulation scenario, the total percentage of detection is above 90%. However, the detection percentage is highly related to other factors such as search space, number of patrolling UAVs, and the intruders’ behaviors.

This paper presents a mobile robot platform, which performs both indoor and outdoor localization based on an intelligent low-cost depth–inertial fusion approach. The proposed sensor fusion approach uses depth-based localization data to enhance the accuracy obtained by the inertial measurement unit (IMU) pose data through a depth–inertial fusion. The fusion approach is based on feedforward cascade correlation networks (CCNs). The aim of this fusion approach is to correct the drift accompanied by the use of the IMU sensor, using a depth camera. This approach also has the advantage of maintaining the high frequency of the IMU sensor and the accuracy of the depth camera. The estimated mobile robot dynamic states through the proposed approach are deployed and examined through real-time autonomous navigation. It is shown that using both the planned path and the continuous localization approach, the robot successfully controls its movement toward the destination. Several tests were conducted with different numbers of layers and percentages of the training set. It is shown that the best performance is obtained with 12 layers and 80% of the pose data used as a training set for CCN. The proposed framework is then compared to the solution based on fusing the information given by the XSens IMU–GPS sensor and the Kobuki robot built-in odometry solution. As demonstrated in the results, an enhanced performance was achieved with an average Euclidean error of 0.091 m by the CCN, which is lower than the error achieved by the artificial neural network by 56%.

Visual place recognition (VPR) in condition-varying environments is still an open problem. Popular solutions are convolutional neural network (CNN)-based image descriptors, which have been shown to outperform traditional image descriptors based on hand-crafted visual features. However, there are two drawbacks of current CNN-based descriptors: (a) their high dimension and (b) lack of generalization, leading to low efficiency and poor performance in real robotic applications. In this paper, we propose to use a convolutional autoencoder (CAE) to tackle this problem. We employ a high-level layer of a pre-trained CNN to generate features and train a CAE to map the features to a low-dimensional space to improve the condition invariance property of the descriptor and reduce its dimension at the same time. We verify our method in four challenging real-world datasets involving significant illumination changes, and our method is shown to be superior to the state-of-the-art. The code of our work is publicly available at https://github.com/MedlarTea/CAE-VPR.

A force sensorless impedance controller is proposed in this paper for robot manipulators without using force estimators. From the observation of the impedance control law, the force feedback term can be canceled if the inertia matrix in the target impedance is the same as the robot inertia matrix. However, the inertia matrix in the target impedance is almost always a constant matrix, while the robot inertia matrix is a function of the robot configuration, and hence, they may not be identical in general. A modification of the coefficient matrix for the contact force term in the target impedance is suggested in this paper to enable cancelation of the force feedback term in the impedance control law so that a force sensorless impedance controller without using force estimators can be obtained. The tracking performance in the free space phase and the motion trajectory in the compliant motion phase of the new design are almost the same as those in the traditional impedance control. Modification of the inertia matrix in the target impedance will result in small variations of the contact force which is acceptable in practical applications. For robot manipulators containing uncertainties, an adaptive version of the new controller is also developed in this paper to give satisfactory performance without the need for force sensors. Rigorous mathematical justification in closed-loop stability is given in detail, and computer simulations are performed to verify the efficacy of the proposed design.

Contact force is one of the most significant feedback for robots to achieve accurate control and safe interaction with environment. For continuum robots, it is possible to estimate the contact force based on the feedback of robot shapes, which can address the difficulty of mounting dedicated force sensors on the continuum robot body with strict dimension constraints. In this paper, we use local curvatures to estimate the magnitude and location of single or multiple contact forces based on Cosserat rod theory. We validate the proposed method in a thin elastic tube and calculate the curvatures via Fiber Bragg Grating (FBG) sensors or image feedback. For the curvature feedback obtained from multicore FBG sensors, the overall force magnitude estimation error is $0.062 \pm 0.068$ N and the overall location estimation error is $3.51 \pm 2.60$ mm. For the curvature feedback obtained from image, the overall force magnitude estimation error is $0.049 \pm 0.048$ N and the overall location estimation error is $2.75 \pm 1.71$ mm. The results demonstrate that the curvature-based force estimation method is able to accurately estimate the contact force.

Fin Ray soft grippers, as a notable passive compliant structures, can be easily actuated by external devices to adapt their shape to conform to a grasped object. Their unique ability is aided by their V-shaped structure and morphable material utilized by the Fin Ray finger. Thus, when the internal structure changes, the adaptability and grasping abilities also change. However, related works focus on the effects of changing key parameters on the grasping performance based on the Festo structure, and few works have explored the effects of changing the internal structure. To close the research gap, four different Fin Ray structures are presented in this article, and a parameter determination process was carried out by maximizing their adaptability by investigating the key parameters of each structure through finite element analysis. Then, the force responses of four selected Fin Ray structures are analyzed and experimentally validated. The results show that the No Internal Filling structure obtained by omitting the crossbeams is ideal for grasping delicate targets with the best adaptability and the minimum resultant force. The cross structure attained by adding vertical beams connected to crossbeams decreases the adaptability of the Fin Ray finger but significantly increases the contact force. The unsymmetric design of the branched structure significantly enhances the final contact force while improving the passive adaptation to objects. Thus, the application of the Fin Ray finger ranges from adaptive delicate grasping tasks to high-force manipulation tasks.

In this paper, a novel cable-constrained parallel mechanism is presented as a lightweight, low-cost leg mechanism design for walking machines to be used on flat surfaces. The proposed leg mechanism has three translational degrees of freedom. It is based on two specific hybrid kinematic topologies being herewith proposed. The paper reports the kinematic analysis formulation and a position performance evaluation to confirm the main characteristics of the proposed solutions. A 3D CAD model and simulations are carried out to demonstrate the feasibility of the proposed design for performing a human-like gait trajectory. A prototype has been built, and preliminarily tests have been conducted to confirm the motion capabilities of the proposed mechanism design. Then a second, enhanced prototype has been designed and built. An experimental validation is carried out for tracking a planar walking trajectory with the built prototypes by using a real-time PCI controller. Results are presented to validate the operation characteristics of the proposed mechanism and to prove its feasibility for legged walking machines.

Currently, most of the robot path planning methods for spray painting are based on slicing the Computer-Aided Design model of the target surface to generate a series of path points. They usually neglect the geometric boundary of the model and the smoothness of the generated path, leading to a non-uniform coating thickness. To ameliorate it, an improved “boundary fitting approach” is proposed. In this method, the upper and lower boundaries of the target surface are firstly detected based on the topology of the stereolithography model. For each pass, several sample points are extracted with a uniform length interval from the intersection points generated by the basic slicing method. The path pass is then described by a fourth-order polynomial curve. It fits the boundary points and sample points for the $z$ - $t$ and $y$ - $t$ relationships, respectively. Based on the spray gun’s motion direction and spray direction, the orientation of each path point is also defined. The parameters of the path pass are optimized by particle swarm optimization to get the optimal uniformity of the resulting coating thickness. Both of the global uniformity and the local uniformity between two adjacent passes are considered. The strength of the proposed approach is validated by comparing the simulation with the basic and other typical algorithms. The results denote that boundary fitting approach could improve the uniformity of coating thickness. It brings about a better performance for the painted workpiece.

This paper presents a study on the design and modeling of a novel pneumatic self-repairing soft actuator. The self-repairing soft actuator is composed of driving element, heating element, and repairing element. The driving element completes the deformation of the self-repairing soft actuator. The heating element and the repairing element complete the self-repairing function of the self-repairing soft actuator. A model used to optimize the structure is established, and the structure of the self-repairing soft actuator is determined through finite element analysis and experiment. The self-repairing time model of the soft actuator is established. The influences of different factors on the self-repairing effect and the self-repairing time are analyzed. The self-repairing scheme of the soft actuator is determined. Experiments show that the shortest time for the self-repairing soft actuator to complete the self-repairing process is 83 min. When the self-repairing soft actuator works normally, the bending angle can reach 129.8° and the bending force can reach 24.96 N. After repairing, the bending angle can reach 108.2°, and the bending force can reach 21.85 N. The repaired soft actuator can complete normal locomotion.

The goal of few-shot semantic segmentation is to learn a segmentation model that can segment novel classes in queries when only a few annotated support examples are available. Due to large intra-class variations, the building of accurate semantic correlation remains a challenging job. Current methods typically use 4D kernels to learn the semantic correlation of feature maps. However, they still face the challenge of reducing the consumption of computation and memory while keeping the availability of correlations mined by their methods. In this paper, we propose the adaptively mining correlation network (AMCNet) to alleviate the aforementioned issues. The key points of AMCNet are the proposed adaptive separable 4D kernel and the learnable pyramid correlation module, which form the basic block for correlation encoder and provide a learnable concatenation operation over pyramid correlation tensors, respectively. Experiments on the PASCAL VOC 2012 dataset show that our AMCNet surpasses the state-of-the-art method by $0.7\%$ and $2.2\%$ on 1-shot and 5-shot segmentation scenarios, respectively.

In laparoscopic surgery, surgeons should develop several manual laparoscopic skills before carrying out real operative procedures using a low-cost box trainer. The Fundamentals of Laparoscopic Surgery (FLS) program was developed as a program to assess fundamental knowledge and surgical skills, required for basic laparoscopic surgery. The peg transfer task is a hands-on exam in the FLS program that assists a trainee to understand the relative minimum amount of grasping force necessary to move the pegs from one place to another place without dropping them. In this paper, an autonomous, sequential assessment algorithm based on deep learning, a multi-object detection method, and, several sequential If-Then conditional statements have been developed to monitor each step of a surgeon’s performance. Images from three different cameras are used to assess whether the surgeon executes the peg transfer task correctly and to display a notification on any errors on the monitor immediately. This algorithm improves the performance of a laparoscopic box-trainer system using top, side, and front cameras and removes the need for any human monitoring during a peg transfer task. The developed algorithm can detect each object and its status during a peg transfer task and notifies the resident about the correct or failed outcome. In addition, this system can correctly determine the peg transfer execution time, and the move, carry, and dropped states for each object by the top, side, and front-mounted cameras. Based on the experimental results, the proposed surgical skill assessment system can identify each object at a high score of fidelity, and the train-validation total loss for the single-shot detector (SSD) ResNet50 v1 was about 0.05. Also, the mean average precision (mAP) and Intersection over Union (IoU) of this detection system were 0.741, and 0.75, respectively. This project is a collaborative research effort between the Department of Electrical and Computer Engineering and the Department of Surgery, at Western Michigan University.

The time-optimal path following (OPF) problem is to find a time evolution along a prescribed path in task space with shortest time duration. Numerical solution algorithms rely on an algorithm-specific (usually equidistant) sampling of the path parameter. This does not account for the dynamics in joint space, that is, the actual motion of the robot, however. Moreover, a well-known problem is that large joint velocities are obtained when approaching singularities, even for slow task space motions. This can be avoided by a sampling in joint space, where the path parameter is replaced by the arc length. Such discretization in task space leads to an adaptive refinement according to the nonlinear forward kinematics and guarantees bounded joint velocities. The adaptive refinement is also beneficial for the numerical solution of the problem. It is shown that this yields trajectories with improved continuity compared to an equidistant sampling. The OPF is reformulated as a second-order cone programming and solved numerically. The approach is demonstrated for a 6-DOF industrial robot following various paths in task space.

Thanks to recent developments in service robotics technologies, precision agriculture (PA) is becoming an increasingly prominent research field, and several studies were made to present and outline how the use of mobile robotic systems can help and improve farm production. In this paper, the integration of a custom-designed mobile base with a commercial robotic arm is presented, showing the functionality and features of the overall system for crop monitoring and sampling. To this aim, the motion planning problem is addressed, developing a tailored algorithm based on the so-called manipulability index, that treats the base and robotic arm mobility as two independent degrees of motion; also developing an open source closed-form inverse kinematics algorithm for the kinematically redundant manipulator. The presented methods and sub-system, even though strictly related to a specific mobile manipulator system, can be adapted not only to PA applications where a mobile manipulator is involved but also to the wider field of assistive robotics.

Day by day, biped robots’ usage is increasing enormously in all industrial and non-industrial applications due to their ability to move in any unstructured environment compared to wheeled robots. Keeping this in mind, worldwide, many researchers are working on various aspects of biped robots, such as gait generation, dynamic balance margin, and the design of controllers. The main aim of this review article is to discuss the main challenges encountered in the biped gait generation and design of various controllers while moving on different terrain conditions such as flat, ascending and descending slopes or stairs, avoiding obstacles/ditches, uneven terrain, and an unknown environment. As per the authors’ knowledge, no single study has been carried out in one place related to the gait generation and design of controllers for each joint of the biped robot on various terrains. This review will help researchers working in this field better understand the concepts of gait generation, dynamic balance margin, and the design of controllers while moving on various terrains. Moreover, the current article will also cover the different soft computing techniques used to tune the gains of the controllers. In this article, the authors have reviewed a vast compilation of research work on the gait generation of the biped robot on various terrains. Further, the authors have proposed taxonomies on various design issues identified while generating the gait in different aspects. The authors reviewed approximately 296 articles and discovered that all researchers attempted to generate the dynamically balanced biped gait on various terrains.