Soft grippers have shown promising performance in safe and adaptive grasping tasks. However, they often suffer from limitations in grasping force. To address this challenge, this paper presents a novel pneumatic three-finger soft gripper to achieve robust adaptive grasping. The gripper consists of three identical fingers, each containing a pneumatic bending soft actuator and a pneumatic lateral soft actuator. The bending actuator features a tilted pneumatic network structure, which provides superior bending performance compared to traditional vertical pneumatic network structure. The lateral actuator is equipped with three deflection chambers at the finger root to mimic the lateral motions of a human finger. Kinematic and static models are established to predict the bending angle and grasping force of the soft finger under pressurized air. The performance of the proposed soft finger is analyzed through finite element simulations, and the effect of the chamber tilt angle is also examined. The theoretical and simulation results are compared to verify the validity of the analytical models. Finally, the proposed soft gripper is fabricated by 3D printing and molding. Experimental results show that the gripper is capable of grasping various objects of different sizes, shapes, materials, and weights, and can perform dexterous manipulation tasks, such as cap unscrewing. The proposed soft gripper exhibits significant potential for applications in robotic robust grasping tasks.

Although there are many wearable sensors that make the acquisition of multi-modality data easier, effective feature extraction and fusion of the data is still challenging for lower limb locomotion mode recognition. In this article, a novel neural network is proposed for accurate prediction of five common lower limb locomotion modes including level walking, ramp ascent, ramp descent, stair ascent, and stair descent. First, the encoder-decoder structure is employed to enrich the channel diversity for the separation of the useful patterns from combined patterns. Second, a self-attention based cross-modality interaction module is proposed, which enables bilateral information flow between two encoding paths to fully exploit the interdependencies and to find complementary information between modalities. Third, a multi-modality fusion module is designed where the complementary features are fused by a channel-wise weighted summation whose coefficients are learned end-to-end. A benchmark dataset is collected from 10 health subjects containing EMG and IMU signals and five locomotion modes. Extensive experiments are conducted on one publicly available dataset ENABL3S and one self-collected dataset. The results show that the proposed method outperforms the compared methods with higher classification accuracy. The proposed method achieves a classification accuracy of 98.25% on ENABL3S dataset and 95.51% on the self-collected dataset. Note to Practitioners—This article aims to solve the real challenges encountered when intelligent recognition algorithms are applied in wearable robots: how to effectively and efficiently fuse the multi-modality data for better decision-making. First, most existing methods directly concatenate the multi-modality data, which increases the data dimensionality and brings computational burden. Second, existing recognition neural networks continuously compress the feature size such that the discriminative patterns are submerged in the noise and thus difficult to be identified. This research decomposes the mixed input signals on the channel dimension such that the useful patterns can be separated. Moreover, this research employs self-attention mechanism to associate correlations between two modalities and use this correlation as a new feature for subsequent representation learning, generating new, compact, and complementary features for classification. We demonstrate that the proposed network achieves 98.25% accuracy and 3.5 ms prediction time. We anticipate that the proposed network could be a general scientific and practical methodology of multi-modality signal fusion and feature learning for intelligent systems.

Over the past few years, self-supervised monocular depth estimation has received widespread attention. Most efforts focus on designing different types of network architectures and loss functions or handling edge cases, for example, occlusion and dynamic objects. In this work, we take another path and propose a novel conditional diffusion-based generative framework for self-supervised monocular depth estimation, dubbed MonoDiffusion. Because the depth ground-truth is unavailable in a self-supervised setting, we develop a new pseudo ground-truth diffusion process to assist the diffusion for training. Instead of diffusing at a fixed high resolution, we perform diffusion in a coarse-to-fine manner that allows for faster inference time without sacrificing accuracy or even better accuracy. Furthermore, we develop a simple yet effective contrastive depth reconstruction mechanism to enhance the denoising ability of model. It is worth noting that the proposed MonoDiffusion has the property of naturally acquiring the depth uncertainty that is essential to be implemented in safety-critical cases. Extensive experiments on the KITTI, Make3D and DIML datasets indicate that our MonoDiffusion outperforms prior state-of-the-art self-supervised competitors. The source code will be publicly available upon the acceptance.

Over the past few years, monocular depth estimation and completion have been paid more and more attention from the computer vision community because of their widespread applications. In this paper, we introduce novel physics (geometry)-driven deep learning frameworks for these two tasks by assuming that 3D scenes are constituted with piece-wise planes. Instead of directly estimating the depth map or completing the sparse depth map, we propose to estimate the surface normal and plane-to-origin distance maps or complete the sparse surface normal and distance maps as intermediate outputs. To this end, we develop a normal-distance head that outputs pixel-level surface normal and distance. Afterthat, the surface normal and distance maps are regularized by a developed plane-aware consistency constraint, which are then transformed into depth maps. Furthermore, we integrate an additional depth head to strengthen the robustness of the proposed frameworks. Extensive experiments on the NYU-Depth-v2, KITTI and SUN RGB-D datasets demonstrate that our method exceeds in performance prior state-of-the-art monocular depth estimation and completion competitors.

Online unsupervised video object segmentation (UVOS) uses the previous frames as its input to automatically separate the primary object(s) from a streaming video without using any further manual annotation. A major challenge is that the model has no access to the future and must rely solely on the history, i.e., the segmentation mask is predicted from the current frame as soon as it is captured. In this work, a novel contrastive motion clustering algorithm with an optical flow as its input is proposed for the online UVOS by exploiting the common fate principle that visual elements tend to be perceived as a group if they possess the same motion pattern. We build a simple and effective auto-encoder to iteratively summarize non-learnable prototypical bases for the motion pattern, while the bases in turn help learn the representation of the embedding network. Further, a contrastive learning strategy based on a boundary prior is developed to improve foreground and background feature discrimination in the representation learning stage. The proposed algorithm can be optimized on arbitrarily-scale data (i.e., frame, clip, dataset) and performed in an online fashion. Experiments on$\textit {DAVIS}_{\textit {16}}$, FBMS, and SegTrackV2 datasets show that the accuracy of our method surpasses the previous state-of-the-art (SoTA) online UVOS method by a margin of 0.8%, 2.9%, and 1.1%, respectively. Furthermore, by using an online deep subspace clustering to tackle the motion grouping, our method is able to achieve higher accuracy at$3\times $faster inference time compared to SoTA online UVOS method, and making a good trade-off between effectiveness and efficiency. Our code is available athttps://github.com/xilin1991/CluterNet.

This work aims to estimate a high-quality depth map from a single RGB image. Due to the lack of depth clues, making full use of the long-range correlation and local information is critical for accurate depth estimation. To this end, we introduce an uncertainty rectified cross-distillation between the Transformer and convolutional neural network (CNN) to achieve a comprehensive depth estimator. Specifically, we utilize the depth estimates from the Transformer branch and CNN branch as pseudo labels to teach each other. At the same time, the pixel-wise depth uncertainty is modeled to mitigate the negative impact of noisy pseudo labels. To avoid the large capacity gap induced by the strong Transformer branch deteriorating the cross-distillation, we transfer the feature maps from the Transformer to the CNN and develop coupling units to assist the weak CNN branch in leveraging the transferred features. Furthermore, we introduce CutFlip, a surprisingly simple yet highly effective data augmentation technique, which forces the model to focus on more valuable depth reasoning clues apart from the vertical image position. Extensive experiments demonstrate that our model, termedURCDC-Depth, exceeds in performance previous state-of-the-art approaches on the KITTI, NYU-Depth-v2 and SUN RGB-D datasets, with no additional computational burden in the evaluation phase. The source code will be publicly available upon acceptance. The source code is available athttps://github.com/ShuweiShao/URCDC-Depth.

Monocular depth estimation has drawn widespread attention from the vision community due to its broad applications. In this paper, we propose a novel physics (geometry)-driven deep learning framework for monocular depth estimation by assuming that 3D scenes are constituted by piece-wise planes. Particularly, we introduce a new normal-distance head that outputs pixel-level surface normal and plane-to-origin distance for deriving depth at each position. Meanwhile, the normal and distance are regularized by a developed plane-aware consistency constraint. We further integrate an additional depth head to improve the robustness of the proposed framework. To fully exploit the strengths of these two heads, we develop an effective contrastive iterative refinement module that refines depth in a complementary manner according to the depth uncertainty. Extensive experiments indicate that the proposed method exceeds previous state-of-the-art competitors on the NYU-Depth-v2, KITTI and SUN RGB-D datasets. Notably, it ranks 1st among all submissions on the KITTI depth prediction online benchmark at the submission time. The source code is available at https://github.com/ShuweiShao/NDDepth.

Accurate detection of gait event intention and sending it to lower limb exoskeleton (LLE) is the key to achieve active rehabilitation. Most existing surface electromyography (sEMG)-based gait event intention detection methods suffer from insufficient generalization and complex detection. In this paper, we propose a novel approach for detecting gait event intention using a single sEMG sensor. The gait event intention is obtained by detecting the peak activity of the rectus femoris during the stance period. First, the root mean square (RMS) features are extracted from the sEMG data of the rectus femoris. Then, the data groups composed of the RMS features are smoothed and all extreme points are calculated. Finally, the midstance (MSt) events are discovered when the latest maximum point satisfies the preset condition. The experimental results of three different gait speeds showed that the proposed approach could adapt to different walking speeds and maintain a high detection accuracy of gait event intention detection. This study provides a convenient and reliable detection approach for gait research of LLE.

Monocular depth estimation is an ill-posed task in computer vision, which holds great significance in the fields such as artificial intelligence, virtual reality, augmented reality, path planning, unmanned driving, and navigation guidance. The primary objective of monocular depth estimation is to predict the depth value of each pixel or infer depth information, given just a single red-green-blue (RGB) image as input. Traditional monocular depth estimation methods rely on limited depth cues, such as strict scene conditions. With the significant advancements in computer vision and artificial intelligence, monocular depth estimation using deep learning has been extensively researched and has yielded substantial results. This paper presents a comprehensive survey of monocular depth estimation. Firstly, we give an overall introduction to monocular depth estimation and explain it from traditional and deep learning-based methods, respectively. To specify, supervised, self-supervised and semi-supervised models are described in detail in deep learning-based methods. Additionally, we introduce publicly available benchmark datasets and evaluation metrics commonly used in this field. Finally, we discuss the current challenges and promising prospects for the development of monocular depth estimation.

Due to saturated regions of low dynamic range (LDR) images and large intensity changes among them, it is challenging to produce an information-enriched panoramic LDR image without visual artifacts from multiple geometrically synchronized LDR images with different exposures and piecewise overlapping fields of views for a high dynamic range (HDR) scene. Fortunately, the stitching of such images is innately a perfect scenario for the fusion of physics-driven and data-driven methods. Based on the insight, a novel neural augmented HDR panoramic stitching algorithm is proposed in this paper. Differently exposed panoramic LDR images are initialized by using a physics-driven method on top of the piecewise overlapping fields of views. They are then refined by a data-driven one, and finally merged together via a multi-scale exposure fusion algorithm to produce the desired panoramic LDR image. Experimental results validate the proposed algorithm11The source code and trained model will be publicly available upon the acceptance..

Monocular depth estimation (MDE) is a fundamental topic of geometric computer vision and a core technique for many downstream applications. Recently, several methods reframe the MDE as a classification-regression problem where a linear combination of probabilistic distribution and bin centers is used to predict depth. In this paper, we propose a novel concept of iterative elastic bins (IEBins) for the classification-regression-based MDE. The proposed IEBins aims to search for high-quality depth by progressively optimizing the search range, which involves multiple stages and each stage performs a finer-grained depth search in the target bin on top of its previous stage. To alleviate the possible error accumulation during the iterative process, we utilize a novel elastic target bin to replace the original target bin, the width of which is adjusted elastically based on the depth uncertainty. Furthermore, we develop a dedicated framework composed of a feature extractor and an iterative optimizer that has powerful temporal context modeling capabilities benefiting from the GRU-based architecture. Extensive experiments on the KITTI, NYU-Depth-v2 and SUN RGB-D datasets demonstrate that the proposed method surpasses prior state-of-the-art competitors. The source code is publicly available at https://github.com/ShuweiShao/IEBins.

Differently exposed low dynamic range (LDR) images are often captured sequentially using a smart phone or a digital camera with movements. Optical flow thus plays an important role in ghost removal for high dynamic range (HDR) imaging. The optical flow estimation is based on the theory of photometric consistency, which assumes that the corresponding pixels between two images have the same intensity. However, the assumption is no longer valid for the differently exposed LDR images since a pixel’s intensity changes significantly inter images. To address the problem, an unsupervised optical flow estimation framework, is presented in this study. Intensity mapping functions (IMFs) are first adopted to alleviate the intensity changes between the LDR images. Then a novel IMF-based unsupervised learning objective is proposed to circumvent the need for ground truth optical flows when training the deep network. Experimental results and ablation studies on publicly available datasets show that our framework outperforms the state-of-the-art unsupervised optical flow methods, demonstrating the effectiveness of the IMF and the learning objective. Our code is available athttps://github.com/liuziyang123/LDRFlow.

Monocular depth estimation plays a fundamental role in computer vision. Due to the costly acquisition of depth ground truth, self-supervised methods that leverage adjacent frames to establish a supervision signal have emerged as the most promising paradigms. In this work, we propose two novel ideas to improve self-supervised monocular depth estimation: 1) self-reference distillation and 2) disparity offset refinement. Specifically, we use a parameter-optimized model as the teacher updated as the training epochs to provide additional supervision during the training process. The teacher model has the same structure as the student model, with weights inherited from the historical student model. In addition, a multiview check is introduced to filter out the outliers produced by the teacher model. Furthermore, we leverage the contextual consistency between high-level and low-level features to obtain multiscale disparity offsets, which are used to refine the disparity output incrementally by aligning disparity information at different scales. The experimental results on the KITTI and Make3D datasets show that our method outperforms previous state-of-the-art competitors.

Depth estimation attracts widespread attention in the computer vision community. However, it is still quite difficult to recover an accurate depth map using only one RGB image. We observe a phenomenon that existing methods tend to fail in different cases, caused by differences in network architecture, loss function and so on. In this work, we investigate into the phenomenon and propose to integrate the strengths of multiple weak depth predictor to build a comprehensive and accurate depth predictor, which is critical for many real-world applications, e.g., 3D reconstruction. Specifically, we construct multiple base (weak) depth predictors by utilizing different Transformer-based and convolutional neural network (CNN)-based architectures. Transformer establishes long-range correlation while CNN preserves local information ignored by Transformer due to the spatial inductive bias. Therefore, the coupling of Transformer and CNN contributes to the generation of complementary depth estimates, which are essential to achieve a comprehensive depth predictor. Then, we design mixers to learn from multiple weak predictions and adaptively fuse them into a strong depth estimate. The resultant model, which we refer to as Transformer-assisted depth ensembles (TEDepth). On the standard NYU-Depth-v2 and KITTI datasets, we thoroughly explore how the neural ensembles affect the depth estimation and demonstrate that our TEDepth achieves better results than previous state-of-the-art approaches. To validate the generalizability across cameras, we directly apply the models trained on NYU-Depth-v2 to the SUN RGB-D dataset without any fine-tuning, and the superior results emphasize its strong generalizability.

Existing methods detect the keypoints in a non-differentiable way, therefore they can not directly optimize the position of keypoints through back-propagation. To address this issue, we present a partially differentiable keypoint detection module, which outputs accurate sub-pixel keypoints. The reprojection loss is then proposed to directly optimize these sub-pixel keypoints, and the dispersity peak loss is presented for accurate keypoints regularization. We also extract the descriptors in a sub-pixel way, and they are trained with the stable neural reprojection error loss. Moreover, a lightweight network is designed for keypoint detection and descriptor extraction, which can run at 95 frames per second for 640x480 images on a commercial GPU. On homography estimation, camera pose estimation, and visual (re-)localization tasks, the proposed method achieves equivalent performance with the state-of-the-art approaches, while greatly reduces the inference time.

Depth completion refers to inferring the dense depth map from a sparse depth map with or without corre-sponding color image. Numerous neural networks have been proposed to accomplish this task. However, insufficient uti-lization of heteromorphic data and the fact that predicted dense depth prefers a sparse depth enormously damage the performance of approaches. To reduce data preference and fully utilize two modalities, this paper proposes a novel network that predicts high- and low-frequency components of dense depth separately. Specifically, the framework consists of a Low-Frequency(LF) branch and a High-Frequency(HF) branch. In the LF branch, we recover the low-frequency depth component from sparse depth through an Adaptive Graph-Generate Graph Attention Network, which can be seen as a low-pass filter. In the HF branch, we model the high-frequency component, e.g. boundaries, as residuals to mitigate the impact of data preferences. Moreover, in this branch, we propose an Attention-based Self-Fusion mechanism to efficiently fuse multi-scale features extracted from the sparse depth and color image. Extensive experiments demonstrate that our approach achieves state-of-the-art performance on the KITTI benchmark and ranks 1st in root mean squared error among other published approaches.

In this paper, a novel adjustable-stiffness force sensor is developed for multitask measurements requiring different force resolutions and ranges. The applied force of the force sensor is indirectly measured through the linear deformation instead of the structure strain through an optical linear encoder. The main structure of the force sensor is actually a linear variable stiffness mechanism with a compact size and a large stiffness change. Its stiffness can be continuously adjusted by changing the effective second moment of area of the structure. Thus, the force sensor has an adjustable range and resolution since the displacement resolution of the optical linear encoder is constant. The stiffness modeling of the sensor is performed based on the matrix method, which is then evaluated by the finite element analysis. A principle prototype is finally fabricated for the adjustable-stiffness test and a concrete application example. The testing results show that the stiffness and resolution of the force sensor can be changed by the proposed stiffness adjustment. Moreover, it is effective to measure different-resolution forces. This adjustable-stiffness approach can be also extended to the design of a torque sensor or a force/torque sensor.

The generative adversarial network (GAN) is successfully applied to study the perceptual single image super-resolution (SISR). However, since the GAN is data-driven, it has a fundamental limitation on restoring real high frequency information for an unknown instance (or image) during test. On the other hand, the conventional model-based methods have a superiority to achieve instance adaptation as they operate by considering the statistics of each instance (or image) only. Motivated by this, we propose a novel model-based algorithm, which can extract the detail layer of an image efficiently. The detail layer represents the high frequency information of image and it is constituted of image edges and fine textures. It is seamlessly incorporated into the GAN and serves as a prior knowledge to assist the GAN in generating more realistic details. The proposed method, named DSRGAN, takes advantages from both the model-based conventional algorithm and the data-driven deep learning network. Experimental results demonstrate that the DSRGAN outperforms the state-of-the-art SISR methods on perceptual metrics, meanwhile achieving comparable results in terms of fidelity metrics. Following the DSRGAN, it is feasible to incorporate other conventional image processing algorithms into a deep learning network to form a model-based deep SISR.

Unsupervised video object segmentation (UVOS) aims at automatically separating the primary foreground object(s) from the background in a video sequence. Existing UVOS methods either lack robustness when there are visually similar surroundings (appearance-based) or suffer from deterioration in the quality of their predictions because of dynamic background and inaccurate flow (flow-based). To overcome the limitations, we propose an implicit motion-compensated network (IMCNet) combining complementary cues (i.e., appearance and motion) with aligned motion information from the adjacent frames to the current frame at the feature level without estimating optical flows. The proposed IMCNet consists of an affinity computing module (ACM), an attention propagation module (APM), and a motion compensation module (MCM). The light-weight ACM extracts commonality between neighboring input frames based on appearance features. The APM then transmits global correlation in a top-down manner. Through coarse-to-fine iterative inspiring, the APM will refine object regions from multiple resolutions so as to efficiently avoid losing details. Finally, the MCM aligns motion information from temporally adjacent frames to the current frame which achieves implicit motion compensation at the feature level. We perform extensive experiments on$\textit {DAVIS}_{\textit {16}}$and$\textit {YouTube-Objects}$. Our network achieves favorable performance while running at a faster speed compared to the state-of-the-art methods. Our code is available athttps://github.com/xilin1991/IMCNet.

Spatially varying exposure (SVE) is a promising choice for high-dynamic-range (HDR) imaging (HDRI). The SVE-based HDRI, which is called single-shot HDRI, is an efficient solution to avoid ghosting artifacts. However, it is very challenging to restore a full-resolution HDR image from a real-world image with SVE because: a) only one-third of pixels with varying exposures are captured by camera in a Bayer pattern, b) some of the captured pixels are over- and under-exposed. For the former challenge, a spatially varying convolution (SVC) is designed to process the Bayer images carried with varying exposures. For the latter one, an exposure-guidance method is proposed against the interference from over- and under-exposed pixels. Finally, a joint demosaicing and HDRI deep learning framework is formalized to include the two novel components and to realize an end-to-end single-shot HDRI. Experiments indicate that the proposed end-to-end framework avoids the problem of cumulative errors and surpasses the related state-of-the-art methods. Related codes and datasets will be provided athttps://github.com/yilun-xu/SVEHDRI/.

Keypoints matching is a pivotal component for many image-relevant applications such as image stitching, visual simultaneous localization and mapping (SLAM), and so on. Both handcrafted-based and recently emerged deep learning-based keypoints matching methods merely rely on keypoints and local features, while losing sight of other available sensors such as inertial measurement unit (IMU) in the above applications. In this paper, we demonstrate that the motion estimation from IMU integration can be used to exploit the spatial distribution prior of keypoints between images. To this end, a probabilistic perspective of attention formulation is proposed to integrate the spatial distribution prior into the attentional graph neural network naturally. With the assistance of spatial distribution prior, the effort of the network for modeling the hidden features can be reduced. Furthermore, we present a projection loss for the proposed keypoints matching network, which gives a smooth edge between matching and un-matching keypoints. Image matching experiments on visual SLAM datasets indicate the effectiveness and efficiency of the presented method.

Ghosting artifacts are believed to be the Achilles’ heel for high dynamic range (HDR) imaging (HDRI) via differently exposed images sequentially captured by a digital device. Spatially varying exposure (SVE)-based HDRI is an efficient solution to prevent the ghosting artifacts from appearing in a HDR image. However, it is challenging to restore a high-quality HDR image with the full resolution from a single raw Bayer image for the SVE-based HDRI. In this paper, a novel deep convolution neural network (DCNN) is proposed to address such a challenging problem. The proposed DCNN includes two distinctive components, a spatially varying convolution and an exposedness-aware compensation branch. The evaluations indicate that the quality of our results significantly surpasses several related algorithms. Related materials will be provided at https://github.com/yilun-xu/SVEHDRI/.

Self-supervised learning algorithms that compute depth map from monocular videos have achieved remarkable performance on urban scenes and have been applied extensively. These techniques still face significant challenges, however, when applied directly to endoscopic videos because of the brightness variations from frame to frame and inadequate representation learning during the training phase. Inspired by the optical flow for motion alignment between adjacent frames, we design a AFNet with structural stability loss and residual-based smoothness loss to learn the appearance flow across adjacent frames, which handles the brightness inconsistency issue efficaciously. In addition, we propose a novel self-attention mechanism named feature scaling module to alleviate the inadequate representation learning problem. In a comparison study to the current state-of-the-art self-supervised methods explored for urban videos on the SCARED dataset, the developed model surpasses existing methods by a large margin.

A major challenge in electroencephalogram (EEG) signal classification is that the EEG signals recorded from different subjects are drawn from different distributions. When the unlabeled EEG data of the new subject arrive, called target domain, classifying them with a classifier trained on prerecorded EEG data of other subjects, called source domain, will greatly decrease the classification accuracy. Being able to use the classifiers trained on data of source domain to accurately classify the data of target domain could reduce the time of the calibration phase in the actual application of the brain-computer interface. This study considers an offline cross-subject classification scenario. We propose a novel manifold trial selection method, which reduces the distribution distance between the source and target domains by manifold transformation and domain adaptation. The proposed method provides a trial selection strategy to suppress negative transfer by removing some abnormal samples. The proposed method is applied to the motor imagery-based brain–computer interface and compared with several existing algorithms. Experimental results show that the proposed method outperforms the state-of-the-art methods.

With the improvement of sensor technology and significant algorithmic advances, the accuracy of remote heart rate monitoring technology has been significantly improved. Despite of the significant algorithmic advances, the performance of rPPG algorithm can degrade in the long-term, high-intensity continuous work occurred in evenings or insufficient light environments. One of the main challenges is that the lost facial details and low contrast cause the failure of detection and tracking. Also, insufficient lighting in video capturing hurts the quality of physiological signal. In this paper, we collect a largescale dataset that was designed for remote heart rate estimation recorded with various illumination variations to evaluate the performance of the rPPG algorithm (Green, ICA, and POS). We also propose a low-light enhancement solution (technical solution) for remote heart rate estimation under the low-light condition. Using collected dataset, we found 1) face detection algorithm cannot detect faces in video captured in low light conditions; 2) A decrease in the amplitude of the pulsatile signal will lead to the noise signal to be in the dominant position; and 3) the chrominance-based method suffers from the limitation in the assumption about skin-tone will not hold, and Green and ICA method receive less influence than POS in dark illuminance environment. The proposed solution for rPPG process is effective to detect and improve the signal-to-noise ratio and precision of the pulsatile signal.

This paper presents a novel portable passive lower limb exoskeleton for walking assistance. The exoskeleton is designed with built-in spring mechanisms at the hip and knee joints to realize gravity balancing of the human leg. A pair of mating gears is used to convert the tension force from the built-in springs into balancing torques at hip and knee joints for overcoming the influence of gravity. Such a design makes the exoskeleton has a compact layout with small protrusion, which improves its safety and user acceptance. In this paper, the design principle of gravity balancing is described. Simulation results show a significant reduction of driving torques at the limb joints. A prototype of single leg exoskeleton has been constructed and preliminary test results show the effectiveness of the exoskeleton.

It is recognized that existing multi-scale exposure fusion algorithms can be improved using edge-preserving smoothing techniques. However, the complexity of edge-preserving smoothing-based multi-scale exposure fusion is an issue for mobile devices. In this paper, a simpler multi-scale exposure fusion algorithm is designed in YUV color space. The proposed algorithm can preserve details in the brightest and darkest regions of a high dynamic range (HDR) scene and the edge-preserving smoothing-based multi-scale exposure fusion algorithm while avoiding color distortion from appearing in the fused image. The complexity of the proposed algorithm is about half of the edge-preserving smoothing-based multi-scale exposure fusion algorithm. The proposed algorithm is thus friendlier to the smartphones than the edge-preserving smoothing-based multi-scale exposure fusion algorithm. In addition, a simple detail-enhancement component is proposed to enhance fine details of fused images. The experimental results show that the proposed component can be adopted to produce an enhanced image with visibly enhanced fine details and a higher MEF-SSIM value. This is impossible for existing detail enhancement components. Clearly, the component is attractive for PC-based applications.

The concept of stimuli-induced equilibrium point (SIEP) has been recently introduced to characterize the psychological interaction of a ramp driver with its putative leader and follower on the expressway during a merging maneuver. It enables the computation of the reference target gap speed and position for the on-ramp merging vehicle based on current traffic conditions and ramp vehicle response. The SIEP has been shown to improve the performance of existing automatic ramp merging control strategies while increasing the level of safety during the merging maneuver. The performance and advantages of the SIEP-based approach have been assessed only through numerical simulations. In this paper, we conducted a comprehensive experimental evaluation of the performance and safety of this SIEP-based approach to ramp merging control using a lab-based test-bed. We employed a novel Pc metric, which is based on the concept of probability of collision, to perform a systematic validation of the SIEP safety. Such a metric serves as a standardized methodology to quantitatively compare the SIEP-based approach with those in this paper.

In this paper, a novel revolute joint of adjustable stiffness with reconfigurability (JASR) is presented. The JASR is designed with zero-length base link four-bar linkage, and allows adjusting its stiffness to achieve soft- and hard-spring behaviour. The new joint has a compact and light-weight structure and can be integrated in robot and transmissions for different applications. In the paper, mathematical models are developed for the JASR, with which influences of design parameters on stiffness performance are analyzed. A prototype of JASR is constructed and preliminary test results demonstrate the compliance properties of the new joint.

Loop closure detection (LCD) is a crucial technique for robots, which can correct accumulated localization errors after long time explorations. In this paper, we propose a robust LCD algorithm based on Bag of SuperPoints and graph verification. The system first extracts interest points and feature descriptors using the SuperPoint neural network. Then a visual vocabulary is trained in an incremental and self-supervised manner considering the relations between consecutive training images. Finally, a topological graph is constructed using matched feature points to verify candidate loop closures obtained by a Bag-of-Words (BoW) framework. Comparative experiments with state-of-the-art LCD algorithms on several typical datasets have been carried out. The results demonstrate that our proposed graph verification method can significantly improve the accuracy of image matching and the overall LCD approach outperforms existing methods.

MRCPs (movement related cortical potentials) are slow negative potentials observed in EEG preceding movement, which represents the processing of the cerebral cortex during planning and preparation. Clinical studies have shown that, rehabilitation therapy with the active participation of the central nervous system can rebuild related nerve function, restore the patient's neural plasticity and characterize the intention to move by means of electroencephalographic activity which can be used in rehabilitation protocols with patients' cortical activity taking an active role during the intervention. We describe our method framework including protocol, data processing and pattern recognition. Then the experimental results are analyzed. The tests were carried out with healthy people and achieved satisfactory performance both in trial and asynchronous detection. Our purpose is to apply to restoration of neural pathway of patients.

The brain-computer interface (BCI) technology is a new human-machine interaction technology that realizes people to control external devices directly by thinking (i.e. electroencephalogram, EEG). However, because of the weakness and randomness of EEG signal, it is very complicated and difficult to process and identify the EEG signal recorded by the non-invasive BCI, and the decoding error often occurs. In view of the brain electrical signal decoding error, an experimental paradigm for simultaneous acquisition of spontaneous EEG and evoked EEG was designed, where the subjects generated the error-related potentials (ErrP) based on the decoded feedback of motor imagery EEG. We analyzed the EEG signal two times. The motor imagery EEG, which was the component of the EEG signal, was analyzed at the first time analysis. We classified the motor imagery EEG signal of left and right hand, then analyzed the classification method quantitatively using the Receiver Operating Characteristic (ROC) curves and the area under the curve (AVC). Although the EEG signal were influenced greatly by the individual difference, the AVC values can still reach more than 0.7. Meanwhile, the frequency domain characteristics were analyzed. The activation brain regions of the left-right hand motor imagery are mainly concentrated in the area of the perceptual motor cortex where is responsible for hand motion, but they will also be influenced by the artifacts of the surrounding channels. In the second time analysis, the ErrP was extracted and discussed. Its latency, waveform and amplitude characteristics were studied in the time domain and then a suitable classifier is selected by comparing a variety of classifiers, which classification accuracy is up to 90%. Therefore, the research based on the ErrP signal played a theoretical foundation for applying to the lower limb exoskeleton rehabilitation robot in the future, and ensured the feasibility of applying the command confirmation unit based on ErrP signal to the exoskeleton rehabilitation robot.

Edge-preserving smoothing based multi-scale exposure fusion is a state-of-the-art method to fuse differently exposed images of a high dynamic range (HDR) scene. However, its complexity could be an issue. In this paper, a novel multiscale exposure fusion algorithm is proposed by adopting an approximation method at the highest layer of the pyramid. Experimental results show that the proposed algorithm can be applied to fuse images with comparable or even better quality with the edge-preserving smoothing based multi-scale fusion algorithms. It simplifies the complexity of the edge-preserving smoothing based multi-scale exposure fusion algorithms significantly.

Classical convolutional neural networks used in computer vision tasks perform excellently in accuracy, but they are unsatisfactory in computational cost especially with the networks going deeper and the image size going larger. Special models based on visual attention have showed their advantages in dealing with spatial information for saving computational cost at inference time. These models are designed to imitate human visual attention mechanism, but they are not able to achieve realize adaptive receptive scope for different object size. In this paper, a recurrent location and scope selection approach is proposed to improve the attention efficiency, which is more similar to human visual mechanism. We evaluate our model on the basic visual recognition task, where it outperforms the baselines and could provide approximated bounding boxes in a weakly supervised way.

In this paper, we propose the novel concept of stimuli-induced equilibrium point to synthesize the speed and position references for automatic on-ramp merging systems. Based on the psychological field theory, the intensity of the stimuli that act upon a driver between two vehicles in a three-vehicle platooning configuration is mathematically modeled to calculate a point at which the stimuli resultant becomes zero. This approach intends to mimic drivers' decision process when certain distance separation with respect to the leader and follower vehicles is attained for safety. The location of this point is continuously updated according to the speed of the middle vehicle and the current traffic scenario. Such stimuli-induced equilibrium point has shown to improve the performance of existing automatic merging control schemes while increasing safety conditions by providing enough reaction time for drivers to avoid an eventual collision.

Multiscale exposure fusion is a fast approach to fuse several differently exposed images captured at the same high dynamic range (HDR) scene into a high-quality low-dynamic range (LDR) image. The fused image is expected to include all details of the input images. However the details in the brightest and darkest regions are usually not well preserved. Adding details that are extracted from the input images to the fused image is an efficient approach to overcome the problem. In this paper a new gradient domain weighted least square based image smoothing algorithm is proposed to extract the details in the brightest and darkest regions of the HDR scene. The extracted details are then added to an image that is produced using an edge-preserving smoothing pyramid based multiscale exposure fusion algorithm. Experimental results show that the proposed detail enhanced exposure fusion algorithm can preserve details in saturated regions especially the brightest regions better than the state-of-the-art multiscale exposure fusion algorithms.

Multi-scale exposure fusion is a fast approach to fuse several differently exposed images captured at the same high dynamic range (HDR) scene into a high quality low dynamic range (LDR) image. The fused image is expected to include all details of the input images, however, the details in the brightest and darkest regions are usually not preserved well. Adding details that are extracted from the input images to the fused image is an efficient approach to overcome the problem. In this paper, a fast selectively detail enhancement algorithm is proposed to extract the details in the brightest and darkest regions of the HDR scene and add the extracted details to the fused image. Experimental results show that the proposed algorithm can enhance the details of the fused image much faster than the existing algorithms with comparable or even better visual quality.

Multi-scale exposure fusion is an efficient way to fuse differently exposed low dynamic range (LDR) images of a high dynamic range (HDR) scene into a high quality LDR image directly. It can produce images with higher quality than single-scale exposure fusion, but has a risk of producing halo artifacts and cannot preserve details in brightest or darkest regions well in the fused image. In this paper, an edge-preserving smoothing pyramid is introduced for the multi-scale exposure fusion. Benefiting from the edge-preserving property of the filter used in the algorithm, the details in the brightest/darkest regions are preserved well and no halo artifacts are produced in the fused image. The experimental results prove that the proposed algorithm produces better fused images than the state-of-the-art algorithms both qualitatively and quantitatively.

High precision overlay alignment is of great importance to guarantee the quality of Roll-to-Roll printed electronics (R2RPE) products. Aiming at removing machining and assembling errors of the roller with both support and transport uses, an aerostatic bearing device with arrayed restrictors is proposed. In this paper the design of the whole device is presented. The mathematical model of the air film existed between the flexible substrate and the aerostatic bearing device is given by adopting simplified Navier-Stokes equations. In order to modeling the pressure distribution of the air film, numerical simulation is processed with Computational Fluid Dynamics (CFD) software FLUENT. Load capacity curve and stiffness cure are generated to optimize the size and distribution of restrictors on the device. The simulation results indicate that: 1) air film with homogeneous pressure distribution is obtained from the designed arrayed restrictors; 2) diameter of the restrictors has a major influence on load capacity and stiffness when the number of the restrictors reaches a certain quantity.

In this paper, the static stiffness of cable-driven wrist robotic rehabilitor (CDWRR) in its whole workspace is analyzed. A total stiffness matrix of this device consists of the exoskeleton stiffness model and the human arm stiffness model, which is obtained by using an equivalent stiffness model of exoskeleton and assuming a series of simplification of human arm. The analysis on stiffness was made with the MATLAB simulation results. Herein, the stiffness performance of the device during rehabilitation training was elucidated by the average stiffness index, stabilizability and relative stabilizability. Results show that the exoskeleton just has a great impact on the rotational stiffness. And the stiffness of cables plays a key role in the exoskeleton stiffness model and its relative stabilizability. Since the stiffness is associated with safety and comfort of rehabilitation training, it is essential to analyze the stiffness of rehabilitation device. Also, the analysis process of this paper can be referred by other similar cable-driven rehabilitors.

Detail enhancement is required by many problems in the fields of image processing and computational photography. Existing detail enhancement algorithms first decompose a source image into a base layer and a detail layer via an edge-preserving smoothing algorithm, and then amplify the detail layer to produce a detail-enhanced image. In this letter, we propose a newL0norm based detail enhancement algorithm which generates the detail-enhanced image directly. The proposed algorithm preserves sharp edges better than an existingL0norm based algorithm. Experimental results show that the proposed algorithm reduces color distortion in the detail-enhanced image, especially around sharp edges.

Guided image filter (GIF) is a well-known local filter for its edge-preserving property and low computational complexity. Unfortunately, the GIF may suffer from halo artifacts, because the local linear model used in the GIF cannot represent the image well near some edges. In this paper, a gradient domain GIF is proposed by incorporating an explicit first-order edge-aware constraint. The edge-aware constraint makes edges be preserved better. To illustrate the efficiency of the proposed filter, the proposed gradient domain GIF is applied for single-image detail enhancement, tone mapping of high dynamic range images and image saliency detection. Both theoretical analysis and experimental results prove that the proposed gradient domain GIF can produce better resultant images, especially near the edges, where halos appear in the original GIF.

The paper Automatic visual bag-of-words for online robot navigation and mapping by T. Nicosevici and R. Garcia (IEEE Trans. Robot., vol. 28, no. 4, pp. 886898, Aug. 2012) proposed an algorithm for robot navigation and mapping. In this paper, we correct some errors in their analysis.

A significant amount of attention has been focused on the methods of high heat flux removal due to the advancing requirements of the electronics industry. Water spray cooling is one of the best candidates for these thermal control problems. A new heater designed to simulate the high heat flux was briefly presented. The heating part of the heater was Insulated-Gate-Bipolar-Transistor (IGBT) component working at high speed switching state, which could generate a considerable amount of heat. In order to keep the junction temperature of the IGBT component within an acceptable limit, the component was cooling by the water spray cooling system. Subsequently, the conventional PID (proportional-integral-derivative) and self-tuning fuzzy PID algorithm were applied to indirectly control the junction temperature of the IGBT component to achieve the reference temperature. The results show the self-tuning fuzzy PID algorithm is much better than the conventional PID algorithm for this thermal management application. The tests are of great significance to the further study of water spray cooling and the high-power electrical devices working under extremely unfavorable conditions.

In the last few decades, selective visual attention has been extensively studied for its promising contributions to computer vision applications. Many different models have been proposed to compute visual saliency, which can be coarsely formulated as computational or psychophysical. Most existing methods are based on bottom-up mechanism, an automatic human behavior to guide gaze allocation. And low level features such as color, intensity and orientation are commonly adopted to compute saliency map. In this work, we propose a saliency computation method that integrates high-level information of object with low-level features. The result map is more suitable for most top-down tasks in the field of mobile robot requiring object information.

As a preprocessing step of many applications, such as object recognition, image retrieval and scene analysis, saliency detection plays an important role and remains a challenging and significant problem in computer vision. Most existing bottom-up methods utilize local or global contrast information to compute the saliency maps, whereas a few methods generate saliency maps with the use of background cues. This work presents a saliency detection method by applying independent component analysis with reference (ICA-R) algorithm to the background cues, which improves the performance of the final saliency maps. First, we segment the input image into superpixels. Second, we take superpixels on each side of image as reference signals to do ICA-R learning, respectively. Then, four saliency maps generated from the learning algorithm are integrated into one background saliency map. Finally, a graph-based manifold ranking algorithm is done to generate the final saliency maps. By doing experiments on a large publicly available database, we demonstrate that the proposed ICA-R saliency detection algorithm performs better than the state-of-the-art methods.

Parallel surface contact between the template and the substrate is very important in imprint lithography. In this paper, a novel force-decoupled compound parallel alignment stage is proposed for high-resolution imprint lithography. It mainly consists of a high-stiffness spherical air bearing (SAB) and a multi-degree-of-freedom (multi-DOF) flexure-based mechanism that functions for both the active and passive alignments. Apart from the function of the parallel alignment, the proposed stage can also endure a large imprinting force of more than 1000 N but does not cause any damage to the delicate components, which is mainly attributed to its force-decoupled characteristic. Through the stiffness modeling and finite element analysis (FEA), the performance is evaluated to satisfy the design requirement. Finally, experimental tests are conducted on the parallel alignment stage for the hot embossing process, and the grating patterns with linewidth of 2.5 μm are successfully transferred from the silicon template to the polymethy methacrylate (PMMA) substrate. This result demonstrates that the proposed stage can be used in the hot embossing process without degrading its alignment accuracy.

A low-cost and easy-to-customize Cable-driven Wrist Robotic Rehabilitor (CDWRR) has been developed for forearm and wrist motion training. This device can be potentially applied to rehabilitation of stroke patients for three degree-of-freedom (3-DOF) arm motion, including forearm supination/pronation, wrist flexion/extension and ulnar/radial deviation. The CDWRR can be customized for patients with different motor impairments of the wrist. With the cable-driven parallel structure, it has properties such as low-cost, low-weight, and easy-to-reconfigure. In this paper, the structural design, kinematic analysis, workspace calculations, and parameter identification algorithms are presented. Computer simulations of the identification algorithms are performed to validate the results. Finally, preliminary experiments on a healthy subject are carried out to demonstrate the feasibility of the proposed robot to provide assistance to the human wrist and forearm during movement training.

This paper presents a geometric calibration approach of a permanent magnet (PM) spherical actuator to improve its positioning accuracy. The proposed actuator consists of a ball-shaped rotor with multiple PM poles and a spherical-shell-shaped stator with circumferential air-core coils. Due to manufacturing and assembly restrictions, the actual geometric parameters of the spherical actuator differ from their nominal values. Hence, the identification of such errors is significant for high accuracy motion control. The calibration model is formulated based on the differential form of torque equation. To identify the position vector errors in the magnetization axes of PM poles and coils axes, an iterative least-squares algorithm is employed. The proposed calibration method can also be applied to other PM spherical actuators. To verify the robustness and effectiveness of the proposed calibration algorithm, simulations are conducted on the spherical actuator. The results have shown that the positioning accuracy of the spherical actuator is greatly improved after calibration.

This paper addresses the kinematic calibration issues for a 7-DOF cable-driven humanoid arm in order to improve its motion control accuracy. The proposed 7-DOF humanoid arm has a hybrid parallel-serial kinematic structure, which consists of three serially connected parallel cable-driven modules, i.e., a 3-DOF shoulder module, a 1-DOF elbow module, and a 3-DOF wrist module. Due to the unique arm design features such as hybrid parallel-serial structure, modular configuration, and redundant sensors, an integrated two-level self-calibration method is proposed in this work. The first level of self-calibration, termed as the central linkage mechanism calibration, is to identify the kinematics errors existed in the 7-DOF central linkage mechanism based on its self-motion capability. The second level of calibration, termed as the cable-driven module calibration, is to identify the kinematics errors existed in each of the parallel cable-driven modules based on its sensing redundancy. To simplify the formulation of the calibration algorithms, the error model of the serial central linkage mechanism is derived from its forward kinematics, in which the Products-Of-Exponential (POE) formula is employed, while the error models of the parallel cable-driven modules are derived from their inverse kinematics. The simulation and experimental results have shown that the proposed self-calibration algorithms can effectively improve the accuracy of the 7-DOF cable-driven humanoid arm.

The novel cable-driven anthropomorphic-arm manipulator (CDAM) mentioned in this paper is a 7-DOF hybrid redundant mechanism which fuse the advantages of redundant manipulator and cable-driven mechanism. This paper focuses on the stiffness of the CDAM and gives the Cartesian stiffness matrix calculation process. The process can be divided into three steps: firstly, the calculation of the stiffness of shoulder and wrist which are both four-cable-driven parallel mechanism; secondly, the stiffness in elbow which is a cable-driven single joint; lastly, by merging the wrist, elbow and shoulder stiffness to the joint stiffness matrix, the modified conservative congruence transformation (CCT) is used to get the solution of Cartesian stiffness matrix of CDAM. Base on the stiffness analysis of CDAM, a stiffness optimal algorithm is proposed to enhance the stiffness in motion and the simulation and experiment proves the effectiveness of this algorithm.

Control accuracy and consistent initial home posture is essential when we compare and analyze control algorithms. In general, in order to reduce the accumulative error of the controlling process or estimate the initial posture, the robot system need to return to its approximate home posture firstly. According to the structural characteristics of the cable-driven parallel robot, this paper describes a novel homing algorithm to a 3-DOF parallel spherical joint. Utilizing incremental encoders and limit switch to detect the home posture, the automatic homing function was realized in three steps by decoupling control to each axis of the spherical joint. Simulation was also performed to show the effectiveness of the homing algorithm.

It is difficult to classify object or scene images with high accuracy when the dataset is relatively large. Spatial Pyramid Matching (SPM) was proposed to deal with this problem, but there are some shortages. As an improvement for SPM, we proposed three pieces of meliorations: first, use approximate nearest neighbor method instead of k-means for clustering; second, regulate the size of codebook referring to quantity and pixels of the images, by calculating sub-codebook for every category and eliminating the codes which are nearer to the registered ones than the threshold; third, rescale the histogram features, and classify the scene with hierarchical strategy. Experiments prove that our approach make better performance than other state-of-the-art classification methods using just one matching kernel.

Every year many vehicle departure accidents happen due to the driver's carelessness. Lane Departure Warning System (LDWS) is a kind of system which can relieve the stress of the drivers and reduce traffic accidents. But most traffic scenes have greater dynamic range than the digital camera at present. It makes the accuracy of the system would be affected by the complicated lighting. Traditional lane detection methods always use a usual image taken by the camera to detect the lane boundary. In this paper, we will use three images with different exposure to merge a high dynamic range (HDR) image and detect the lane in the HDR image. The experimental results show that the high dynamic range image can improve the accuracy of the lane detection method. However, processing of merging HDR image is very time consuming. It makes HDR image can't be used in real-time LDWS. We proposed an improved method based on exposure fusion to reduce the computational time of the system.

In this paper, a simple method to extract regions of interest (ROI) from images is proposed. In the field of image processing, intensity, color and orientation are commonly used features for saliency map generation in most visual attention model. However, texture feature can contribute to the guidance of attention in a bottom-up model. We consider texture contrast as a component of final saliency map. Hue, saturation, and value (HSV) color space is also adopted in this paper for its good capability of representing the colors of human perception and simplicity of computation. Moreover, binocular stereo image pair is adopted as source image. The result shows that the proposed saliency computational method can effectively detect salient region, and it is more suitable for environmental perception and cognition, object detection, and mobile robot navigation.

This paper presents a three-DOF permanent spherical actuator, with precise measurement system. As magnetic model is very useful to torque model and control model, magnetic model is the basis of spherical actuator study. A new analytical magnetic field model is presented for the proposed 3-DOF spherical actuator in this paper. This analytical magnetic field method combines the Laplace equation with the equivalent magnetic charge law, which is simple and accurate. Finally, we apply the finite-element magnet analysis method to verify the accuracy of the proposed analytical method.

The research area of bio-inspired control methods for multi-legged robots and reptile robots has made significant development with the use of central pattern generators (CPGs) in recent years. However, there are still many problems to be solved to learn clearly the structure of CPG to adapt it to different applications. In this article, we use a method to configure CPG which makes the CPG have adaptive frequency according to the existing researches. Thus, the frequency of CPG can be changed automatically via the feedback of external limit cycle driving signals. Also, we try to explain the CPG of adaptive frequency from a dynamical way. Then we construct a new CPG method for locomotion control of quadruped robots. Finally we make simulations to verify the CPG locomotion control method on a quadruped model in the software of Adams.

In this paper we present an approach to indoor localization and 3D scene reconstruction using the Microsoft Kinect sensor. The proposed system can simultaneously estimates the position and orientation of a hand-held Kinect and generates a dense 3D model of the indoor environment. Furthermore, the robustness and processing time for four different feature descriptors (SURF, ORB, Shi-Tomasi and FAST) are evaluated. The experiment results demonstrate that our system can robustly deal with complicated data in common indoor scenarios while running in semi-real-time.

In chaos control, an originally chaotic system is modified so that periodic dynamics arise. One application of this is to use the periodic dynamics of a single chaotic system as walking patterns in legged robots. In our previous work we applied such a controlled chaotic system as a central pattern generator (CPG) to generate different gait patterns of our hexapod robot AMOSII. However, if one or more legs break, its control fails. Specifically, in the scenario presented here, its movement permanently deviates from a desired trajectory. This is in contrast to the movement of real insects as they can compensate for body damages, for instance, by adjusting the remaining legs' frequency. To achieve this for our hexapod robot, we extend the system from one chaotic system serving as a single CPG to multiple chaotic systems, performing as multiple CPGs. Without damage, the chaotic systems synchronize and their dynamics is identical (similar to a single CPG). With damage, they can lose synchronization leading to independent dynamics. In both simulations and real experiments, we can tune the oscillation frequency of every CPG manually so that the controller can indeed compensate for leg damage. In comparison to the trajectory of the robot controlled by only a single CPG, the trajectory produced by multiple chaotic CPG controllers resembles the original trajectory by far better. Thus, multiple chaotic systems that synchronize for normal behavior but can stay desynchronized in other circumstances are an effective way to control complex behaviors where, for instance, different body parts have to do independent movements like after leg damage.

Kinematic calibration is an effective method for improving the accuracy of the robot motion control. For the cable-driven robot, the flexibility of the cable makes the robot have good compliance and meet safety requirements; however, it brings a greater influence on the movement accuracy of the mechanism. Thus, kinematic calibration alone cannot accurately establish the error model. In view of the error analysis and flexibility compensation of the cable-driven robot, this paper analyzes the effect of flexible rope on kinematic movement accuracy by introducing a flexibility compensation weighting factor. A kind of comprehensive error analysis model of the cable-driven robot was established. By using kinematic calibration algorithm, it organically merges together the kinematic errors caused by the geometric parameters errors and that caused by flexibility of cable. With shoulder joint of the cable-driven humanoid-arm manipulator as the experimental object, the results showed that the algorithm has a better convergence, and it can effectively improve the accuracy of the robot motion control.

A virtual flexible curved bar coupled with force delay algorithm is proposed for automatic vehicle following, aiming at improving the accuracy of vehicle trajectory tracking, especially when leader vehicle is accelerating or making turns. A virtual flexible curved bar with force delay has been modeled that connects the leader to the follower. The length of this virtual bar is a function of the turning radiuses of the leader vehicle. Through this model, the follower vehicle is in effect being virtually dragged by the leader through the virtual flexible curved bar. It is the virtual dragging force that makes the follower accelerate/decelerate so as to adjust its speed to match that of the leader. Finally, simulations were carried out in MATLAB. The results showed that the proposed algorithm has improved the trajectory tracking error greatly, compared to the virtual rigid straight link approach.

The study in this paper covers torque modeling, trajectory planning and optimization control of current input of spherical actuators, in which the latter two are the major contributions. Trajectory planning is an effective way to improve the smoothness and stability of rotor motions. A novel three-dimensional (3D) orientation representation method based on manifold of S2is proposed to facilitate the trajectory planning of rotor. Current redundancy of spherical actuator is analyzed in detail, and optimization algorithm of current input is developed to improve the power efficiency and the fault tolerance capability of system. Simulation is then carried out to validate the proposed method and algorithm in this study. The simulation results indicate that by using the trajectory planning, the given torque values and the torque model, optimal current could be obtained to drive the rotor to achieve desired motions.

To solve the problem that the final velocity curve will be unsmoothed if the PVT(Position Velocity Time) nodes velocities are determined improperly when using PVT control algorithm, based on analyzing the general principle of spline interpolation and PVT motion control, this paper presents a triple spline interpolation based PVT algorithm, which ensures the smoothness of the velocity curve. The velocity of each node is firstly calculated via spline interpolation method, and then the final trace control curve is achieved by using PVT method to these points. The proposed algorithm is applied to the kinematics control of a cockroach robot. The structure and forward/inverse kinematics model of the cockroach robot is expounded. Finally, the reliability of the proposed algorithm is verified by the contrast simulation and experiment of a single leg of the cockroach robot with one of the existing algorithms. The results show that the proposed approach can be readily used for motion controls.

Based on the current research results of anthropomorphic-arm bionics and parallel manipulators, a motion control approach for a 7-DOF cable-driven manipulator is proposed. This paper introduces mechanical structure design of this anthropomorphic-arm first. For the inverse kinematics of the 7-DOF manipulator, a hybrid algorithm, based on gradient projection method and Paden-Kahan sub problems, is proposed to make the trajectory tracing of the manipulator in task space with high accuracy; a joint rate redistribution approach is also employed to optimize kinematic performance criterion and improve the fault-tolerance of the manipulator. The coupling cable lengths among the different joint modules, i.e., shoulder, elbow, and wrist joints, are analyzed in detail. Finally, to demonstrate the proposed algorithm, by utilizing ADAMS software, a straight-line trajectory motion simulation for the 7-DOF cable-driven manipulator is realized

Based on the local product-of-exponentials (POE) formula, this paper proposes an effective approach to solve the inverse displacement analysis for a class of modular 3-legged parallel robots by Paden-Kahan sub-problems. Since passive joint displacements can be solved together with solving active joint, so that the solved passive joint displacements can be regarded as guess solution to calculate forward kinematics by traditional numerical solution method. Through comparing with traditional iterative numerical solution method, proposed approach can evidently improve computation efficiency for forward kinematics. The effectiveness of the proposed approach has been demonstrated by machining demonstrations with online motion monitoring for a workpiece with spherical surface.

The design of a new six-degree-of-freedom (6-DOF) parallel-kinematics machine (PKM) has been proposed. Different from the conventional Stewart-Gough platform which has six extensible legs, the new PKM employs three identical RPRS legs to support the moving platform. Since all joint axes, excluding the three spherical joints at the leg ends, are parallel to each other and perpendicular to the base plane, this 6-DOF PKM presents a promising platform structure with decoupled-motion architecture (DMA) such that translation in a horizontal plane and rotation about a vertical axis are driven by the three active revolute joints, while translation in the vertical direction and rotation about horizontal axes are driven by the three active prismatic joints. As a result, this 6-DOF 3RPRS PKM with DMA has simple kinematics, large cylindrical reachable workspace, and high stiffness in the vertical direction. These features make it appropriate for light machining and heavy parts assembly tasks. Because of the DMA, a projection technique is employed for its kinematics analysis. By projecting the manipulator onto horizontal directions and vertical planes, the kinematics issues such as the displacement, singularity, and workspace analysis are significantly simplified.

A joystick-based interactive motion control approach is proposed for modular reconfigurable manipulators. Based on the product-of-exponentials (POE) formula, the velocity models as well as the incremental displacement models have been formulated for both serial manipulators (with arbitrary configurations and DOFs) and a class of three-legged parallel manipulators. As a result, two different control modes, i.e., the velocity control mode and the incremental displacement control mode, have been developed. A user-friendly GUI has also been developed, which can display the joystick input, the actual joint angles, and the end-effector pose simultaneously. A 6-DOF serial modular robot and a 6-DOF 3RPRS parallel robot have demonstrated the effectiveness of this approach.

Based on the numerical inverse kinematic algorithm developed for modular robots, this paper presents a new control method, termed joint angle increment redistribution, which makes that the maximum allowable joint rates of a redundant robot can be specifically defined according to the internal and external constrains such as joints, tasks, and environments. For example, if some joints have failures and need to be locked, the corresponding joint angle increments can be redistributed to be zero or very small values. The proposed approach can be readily used for online fault-tolerant control of redundant robots. It also makes the optimal control with multiple performance criteria easy. The effectiveness of the proposed algorithms has been demonstrated by a 7-DOF serial modular robot for the avoidance of joint angle limits.

This paper presents the inverse kinematic and dynamic analyses of the 3UPS-UP parallel mechanism with three degrees of freedom. For inverse kinematics, the kinematic constraint equations of the movable platform are established according to the structural character of the passive sub-chain, based on which the closed-form inverse kinematic formulas of the mechanism are obtained. In inverse dynamic analysis, the mechanism is decomposed into two parts through cutting the three spherical joints connecting the base and movable platforms, then the constraint forces acting on the parted joints are determined using the force or moment equilibrium's of both the active and passive sub-chains. Finally, the analytic expressions of actuator driving force are derived by means of the force equilibrium of the upper links of active sub-chains.

In this paper, we propose a novel design of a hybrid 6-DOF parallel-serial manipulator. It consists of a 3-DOF planar parallel platform (lower part) and a 3-DOF serial robot arm (upper part). Benefiting from the hybrid kinematic structure, the manipulator possesses compromised performance between the serial robot and the parallel one, e.g., larger reachable and dexterous workspace (comparing with a parallel robot), and higher rigidity and loading capacity (comparing with a serial robot). It order to rapidly deploy the system, the modularity design concept is employed in the system development. Based on the modular and symmetric design, the symbolic closed-form solutions for both forward and inverse displacement analysis are derived, which are great helps for the motion planning, computer simulation, and on-line control of the hybrid manipulator. Computation examples are provided to verify the proposed kinematic analysis algorithms.

A parallel robot, due to its closed-loop structure, normally has two Jacobian matrices: the inverse and forward Jacobian matrices. Conventional methods for singularity analysis of planar parallel robots are based on analysis of the ranks of the two Jacobian matrices. The inverse singularity has been well studied as the inverse Jacobian matrix always has a simple diagonal form. However, the forward singularity analysis is somehow complicated, partially because some essential geometric relations may be occulted in the formulation of the forward Jacobian matrix. This paper focuses on the forward singularity analysis of a class of 3-RRR planar parallel robots with various actuation schemes. A simple geometric approach based on the concept of instantaneous center is proposed. By analyzing the instantaneous mobility of the moving platform when all the active joints are locked, the necessary and sufficient geometrical conditions for the forward singularity configurations are readily identified. It has been shown that this simple geometrical approach can be employed for singularity analysis of various planar parallel robots and mechanisms.

The paper focuses on the kinematic control of redundant modular robots for trajectory tracing. Based on the geometric numerical inverse kinematic algorithm developed for modular robots, a new online control method is presented. In this method, the inverse kinematic solution can be optimized through constructing a weighted matrix. Following this approach, some fundamental interpolation algorithms are proposed for Cartesian space (task space) control of redundant modular robots. The effectiveness of the proposed algorithms has been experimentally demonstrated by a 7-DOF serial modular robot that performs a pick-and-place task with the avoidance of joint angle limits.

To realize control of robotic manipulators with redundant degrees of freedom, the concept of a motion optimizability measure is introduced. We derive an optimal solution technique for the inverse kinematics of a redundant robot that achieves real-time control with multiple performance criteria. Using this technique, we propose an efficient method for kinematic control. Experimental results are presented for a 7 DOF manipulator.

The stability and the end-task self-motion are important and difficult points. To solve these difficulties that exist in dynamic optimization of redundant manipulators, the paper researches the inner relation and contradictory conflict between the dynamic optimization and the joint velocities, and a new idea to raise the general quality of dynamic optimization by means of optimizing joint velocities is presented. A scheme resulting from adjusting an homogeneous joint velocity item in real-time is developed to effectively improve stability and joint velocities at end of motion to be near zero. Computer simulation verified the proposed approach to be very useful and efficient.

Redundant robots are characterized by dexterity, to overcome the difficulty of calculation when traditional manipulability is used for dexterity control, the paper researches the inner relation and contradictory conflict of the unity which consists of joint geometrical positions, orientations and joint velocities. A new idea to improve the weighted manipulability ellipsoid by optimizing joint velocities is presented thus geometrical position and orientation of the robot may be indirectly optimized by means of the feedback of joint velocities. Simulation verifies this scheme is very useful for real time control because of its simple arithmetic.