Configurable platforms bring a research field to expand the attributes of parallel manipulators. This work is devoted to investigate the kinematics of a nine-degrees-of-freedom parallel manipulator whose active kinematic pairs are located near to the fixed platform, and it is equipped with a 6-R configurable platform. The mobility of the proposed 9-UPUR{6R} configurable parallel manipulator is such that it is possible to manipulate the kinematics of a grasping triangle associated to the configurable platform. The theory of screws is systematically applied to solve the direct and inverse infinitesimal kinematics of the manipulator. As an intermediate step, the displacement analysis is approached by means of algebraic geometry. The contribution is complemented with numerical examples to illustrate the versatility of the method of kinematic analysis.

In this paper, mathematical models of kinematics, statics and inverse dynamics are derived firstly according to the mechanical structure of leg hydraulic drive system (LHDS). Then, all the above models are integrated with MATLAB/Simulink to build the LHDS simulation model, the model not only considers influence of leg dynamic characteristics on hydraulic system but also takes into account nonlinearity, variable load characteristics and other common problems brought by hydraulic system, and solves compatibility and operation time which brought by using multiple software simultaneously. The experimental results show the simulation model built in this paper can accurately express characteristics of the system.

This paper proposes a navigation system for a non-holonomic mobile robot. The navigation is based on a “look and move” approach. The aim is to define intermediate points called sub-goals through which the robot must pass. This algorithm is particularly suitable for navigation in an unknown environment and obstacle avoidance. Between two successive sub-goals, a shortest path planning solution is adopted. We have adopted the “Dubins' car” because of the environment perception sensor, a 180° laser scanner. In order to minimize the calculation time, the theoretical results of shortest path are approximated by simple equations. The navigation algorithm proposed can be used either in a structured or unstructured environment. In this context the local map construction is based on the segmentation of a structured environment; so for an unstructured environment, a suitable algorithm must be used instead.

We present an approach that allows a robot to generate trajectories to perform a set of instances of a task using few physical trials. Specifically, we address manipulation tasks which are highly challenging to simulate due to complex dynamics. Our approach allows a robot to create a model from initial exploratory experiments and subsequently improve it to find trajectory parameters to successfully perform a given task instance. First, in a model generation phase, local models are constructed in the vicinity of previously conducted experiments that explain both task function behavior and estimated divergence of the generated model from the true model when moving within the neighborhood of each experiment. Second, in an exploitation-driven updating phase, these generated models are used to guide parameter selection given a desired task outcome and the models are updated based on the actual outcome of the task execution. The local models are built within adaptively chosen neighborhoods, thereby allowing the algorithm to capture arbitrarily complex function landscapes. We first validate our approach by testing it on a synthetic non-linear function approximation problem, where we also analyze the benefit of the core approach features. We then show results with a physical robot performing a dynamic fluid pouring task. Real robot results reveal that the correct pouring parameters for a new pour volume can be learned quite rapidly, with a limited number of exploratory experiments.

We propose a novel formal approach to robust motion planning (MP) in dynamic environments based on reachability analysis. While traditional MP methods usually fail to provide formal robust safety and performance guarantees, our approach provably ensures safe task achievement in time-varying and adversarial environments under parametric uncertainty. We leverage recent results on Hamilton–Jacobi (HJ) reachability and differential games in order to compute offline guaranteed motion plans that are compatible with the sampled-data (SD) paradigm. Also, we synthesize online provably robust safety-preserving and target-reaching feedback controls. Unlike earlier applications of reachability analysis to MP, our methodology handles arbitrary time-varying constraints, adversarial agents such as pursuing obstacles or evading targets, and takes into account the robot’s configuration. Furthermore, we use HJ projections in order to reduce significantly the computational burden without trading off safety guarantees. The validity of this approach is demonstrated through the case study of a robot arm subject to measurement errors, which is tasked with safely reaching a goal in a known time-varying workspace while avoiding capture by an unpredictable pursuer. Finally, the performance of the approach and research perspectives are discussed.

In this paper, we present a novel sampling-based motion planning method in various complex environments, especially with narrow passages. We use online the results of the planner in the ADD-RRT framework to identify the types of the local configuration space based on the principal component analysis (PCA). The identification result is then used to accelerate the expansion similar to RRV around obstacles and through narrow passages. We also propose a modified bridge test to identify the entrance of a narrow passage and boost samples inside it. We have compared our method with known motion planners in several scenarios through simulations. Our method shows the best performance across all the tested planners in the tested scenarios.

A crucial part of probabilistic roadmap planners is the nearest neighbor search, which is typically done by exact methods. Unfortunately, searching the neighbors can become a major bottleneck for the performance. This can occur when the roadmap size grows especially in high-dimensional spaces. In this paper, we investigate how well the approximate nearest neighbor searching works with probabilistic roadmap planners. We propose a method that is based on the locality-sensitive hashing and show that it can speed up the construction of the roadmap considerably without reducing the quality of the produced roadmap.

This paper presents the design and experimentation of a variable stiffness index finger exoskeleton consisting of four-bar mechanisms actuated by a linear actuator. The lengths of the four-bar mechanism were optimized so that it can follow a recorded index fingertip trajectory. The mechanism has a fixed compliance at the coupler of the four-bar link and a variable compliance at the linear actuator that moves the four-bar. The skeletal shape of the coupler of the finger link has been optimized using FEM. The exoskeleton can apply a constant fingertip force irrespective of the position of the fingers.

This article proposes a method for incremental data dimensionality reduction in loop closure detection for robotic autonomous navigation. The approach uses dominant eigenvector concept for: (a) spectral description of visual datasets and (b) representation in low dimension. Unlike most other papers on data dimensionality reduction (which is done in batch mode), our method combines a sliding window technique and coordinate transformation to achieve dimensionality reduction in incremental data. Experiments in both simulated and real scenarios were performed and the results are suitable.

In this study, the kinematics and dynamics of a single actuator wave (SAW)-like robot are explored. Comprising a helical spine and links, SAW has the potential for miniaturization. A kinematic model for SAW is firstly established, and the dynamic equation of motion is derived based on Kane’s method. For validation, the motion of SAW is simulated using both MATLAB and ADAMS, and the comparison of results demonstrates the effectiveness of the theoretical models. Then the inverse dynamic analysis is performed to reveal the power consumption. Finally, robot prototypes are developed and tested to confirm the robot velocity predicted by simulations.

Haptic devices have proven effective in stimulating proprioceptive sensing in post-stroke patients. In this work, pre-existing devices were used together in a remote environment for the teleassessment of impaired hands. A four-channel bilateral control system in the presence of large and variable time delay is proposed as a proof of concept. Time delay is managed with a novel communication disturbance observer (CDOB). The system also employed a scaling down compensation value (SDCV) for the CDOB. The proposed control system was tested successfully in bilateral haptic interaction, simulating a remote motor and functional evaluation of patients' hands, guaranteeing safe and stable interaction, even in the presence of large network delays.

This paper proposes a novel shuffle turning method for a humanoid robot that controls the load distribution of the soles of the robot's feet. Turning motions of a humanoid robot are conventionally performed through a repeated foot stepping motion. However, this motion is inefficient and time-consuming. In our method, the feet are slid along the floor without a stepping movement. In order to reduce the friction with the floor and to achieve the correct shuffle turning motion, a non-uniform load distribution of the soles is controlled. Experiments using a humanoid robot were conducted on two floors with differing friction amounts, and the validity of the proposed method was verified.

In this paper, a Neural-Network- (NN) based guidance methodology is proposed for the high-precision docking of autonomous vehicles/platforms. The novelty of the overall online motion-planning methodology is its applicability to cases that do not allow for the direct proximity measurement of the vehicle's pose (position and orientation). In such instances, a guidance technique that utilizes Line-of-Sight- (LOS) based task-space sensory feedback is needed to minimize the detrimental impact of accumulated systematic motion errors. Herein, the proposed NN-based guidance methodology is implemented during the final stage of the vehicle's motion (i.e., docking). Systematic motion errors, which are accumulated after a long-range motion are reduced iteratively by executing corrective motion commands generated by the NN until the vehicle achieves its desired pose within random noise limits. The proposed guidance methodology was successfully tested via simulations for a 6-dof (degree-of-freedom) vehicle and via experiments for a 3-dof high-precision planar platform.

This paper presents a distributed multiple mobile robots framework which allows programming and control of virtual and real mobile robots. The system provides the map building, path planning, robot task planning, simulation, and actual robot control functions in an indoor environment. Users can program the virtual robots in a customized simulation environment and check the performance of execution, i.e., if the simulation result is satisfying, users can download the code to a real robot. The paper focuses on the distributed architecture and key technologies of virtual robots simulation and control of real robots. A method for construction and transfer of a key index value (which stores the robot configuration) is proposed. Using this method, only the robot key configuration index is needed to build the robot in the virtual environment. This results in reduced network load and improved real time performance of the distributed system. Experiments were conducted to compare the performance of the proposed system with the performance of a centralized system. The results show that the distributed system uses less system resources and has better real time performance. What is more, this framework has been applied to Yaskawa's robot “SmartPal.” The simulation and experiment results show that our robotic framework can simulate and control the robot to perform complex tasks.

This paper discusses the modeling and control of a robotic manipulator with a new deburring tool, which integrates two pneumatic actuators to take advantage of a double cutting action. A coordination control method is developed by decomposing the robotic deburring system into two subsystems; the arm and the deburring tool. A decentralized control approach is pursued, in which suitable controllers were designed for the two subsystems in the coordination scheme. In simulation, three different tool configurations are considered: rigid, single pneumatic and integrated pneumatic tools. A comparative study is performed to investigate the deburring performance of the deburring arm with the different tools. Simulation results show that the developed robotic deburring system significantly improves the accuracy of the deburring operation.

This paper describes the design of an Internal Model Control (IMC) system for a planar two-degree-of-freedom robot. IMC was investigated as an alternative to the basic inverse control scheme which is difficult to implement. The proposed IMC system consisted of a forward internal neural model of the robot, a neural controller and a conventional feedback controller, all of which were realised easily. Both the neural model and the neural controller were based on recurrent networks which were trained using the backpropagation (BP) algorithm. The paper presents the results obtained with two types of recurrent networks as well as a conventional PID system.

Body posture determination methods have many applications, including product design, ergonomic workplace design, human body simulation, virtual reality, and animation industry. Initiated in robotics, inverse kinematic (IK) method has been widely applied to proactive human body posture estimation. The analytic inverse kinematic (AIK) method is a convenient and time-saving type of IK methods. It is also indicated that, based on AIK methods, a specific body posture can be determined by the optimization of an arbitrary objective function. The objective of this paper is to predict the postures of human arms during reaching tasks. In this research, a human body model is established in MATLAB, where the middle rotation axis analytic kinematic method is accomplished, based on this model. The joint displacement function and joint discomfort function are selected to be initially applied in this AIK method. Results show that neither the joint displacement function nor the joint discomfort function predicts postures that are close enough to natural upper limb postures of human being, during reaching tasks. Therefore, a bi-criterion objective function is proposed by integrating the joint displacement function and joint discomfort function. The accuracy of the arm postures, predicted by the proposed objective function, is the most satisfactory, while the optimal value of the coefficient, in the proposed objective function, is determined by golden section search.

Reinforcement learning (RL) has been successfully applied to a wealth of robot manipulation tasks and continuous control problems. However, it is still limited to industrial applications and suffers from three major challenges: sample inefficiency, real data collection, and the gap between simulator and reality. In this paper, we focus on the practical application of RL for robot assembly in the real world. We apply enlightenment learning to improve the proximal policy optimization, an on-policy model-free actor-critic reinforcement learning algorithm, to train an agent in Cartesian space using the proprioceptive information. We introduce enlightenment learning incorporated via pretraining, which is beneficial to reduce the cost of policy training and improve the effectiveness of the policy. A human-like assembly trajectory is generated through a two-step method with segmenting objects by locations and iterative closest point for pretraining. We also design a sim-to-real controller to correct the error while transferring to reality. We set up the environment in the MuJoCo simulator and demonstrated the proposed method on the recently established The National Institute of Standards and Technology (NIST) gear assembly benchmark. The paper introduces a unique framework that enables a robot to learn assembly tasks efficiently using limited real-world samples by leveraging simulations and visual demonstrations. The comparative experiment results indicate that our approach surpasses other baseline methods in terms of training speed, success rate, and efficiency.

Recently, deep learning methods have achieved considerable performance in gesture recognition using surface electromyography signals. However, improving the recognition accuracy in multi-subject gesture recognition remains a challenging problem. In this study, we aimed to improve recognition performance by adding subject-specific prior knowledge to provide guidance for multi-subject gesture recognition. We proposed a time–frequency feature transform suite (TFFT) that takes the maps generated by continuous wavelet transform (CWT) as input. The TFFT can be connected to a neural network to obtain an end-to-end architecture. Thus, we integrated the suite into traditional neural networks, such as convolutional neural networks and long short-term memory, to adjust the intermediate features. The results of comparative experiments showed that the deep learning models with the TFFT suite based on CWT improved the recognition performance of the original architectures without the TFFT suite in gesture recognition tasks. Our proposed TFFT suite has promising applications in multi-subject gesture recognition and prosthetic control.

We propose a computational design tool to enable casual end-users to easily design, fabricate, and assemble flat-pack furniture with guaranteed manufacturability. Using our system, users select parameterized components from a library and constrain their dimensions. Then they abstractly specify connections among components to define the furniture. Once fabrication specifications (e.g., materials) designated, the mechanical implementation of the furniture is automatically handled by leveraging encoded domain expertise. Afterwards, the system outputs three-dimensional models for visualization and mechanical drawings for fabrication. We demonstrate the validity of our approach by designing, fabricating, and assembling a variety of flat-pack (scaled) furniture on demand.