Search

To reduce the reliance on large-scale datasets, recent works in 3D segmentation resort to few-shot learning. Current 3D few-shot segmentation methods first pre-train models on 'seen' classes, and then evaluate their generalization performance on 'unseen' classes. However, the prior pre-training stage not only introduces excessive time overhead but also incurs a significant domain gap on 'unseen' classes. To tackle these issues, we propose a Non-parametric Network for few-shot 3D Segmentation, Seg-NN, and its Parametric variant, Seg-PN. Without training, Seg-NN extracts dense representations by hand-crafted filters and achieves comparable performance to existing parametric models. Due to the elimination of pre-training, Seg-NN can alleviate the domain gap issue and save a substantial amount of time. Based on Seg-NN, Seg-PN only requires training a lightweight QUEry-Support Transferring (QUEST) module, which enhances the interaction between the support set and query set. Experiments suggest that Seg-PN outperforms previous state-of-the-art method by +4.19% and +7.71% mIoU on S3DIS and ScanNet datasets respectively, while reducing training time by -90%, indicating its effectiveness and efficiency., Comment: CVPR Highlight. Code is available at https://github.com/yangyangyang127/Seg-NN. arXiv admin note: text overlap with arXiv:2308.12961

The popularity of Contrastive Language-Image Pre-training (CLIP) has propelled its application to diverse downstream vision tasks. To improve its capacity on downstream tasks, few-shot learning has become a widely-adopted technique. However, existing methods either exhibit limited performance or suffer from excessive learnable parameters. In this paper, we propose APE, an Adaptive Prior rEfinement method for CLIP's pre-trained knowledge, which achieves superior accuracy with high computational efficiency. Via a prior refinement module, we analyze the inter-class disparity in the downstream data and decouple the domain-specific knowledge from the CLIP-extracted cache model. On top of that, we introduce two model variants, a training-free APE and a training-required APE-T. We explore the trilateral affinities between the test image, prior cache model, and textual representations, and only enable a lightweight category-residual module to be trained. For the average accuracy over 11 benchmarks, both APE and APE-T attain state-of-the-art and respectively outperform the second-best by +1.59% and +1.99% under 16 shots with x30 less learnable parameters., Comment: Code is available at https://github.com/yangyangyang127/APE

Particle-based dynamic occupancy maps were proposed in recent years to model the obstacles in dynamic environments. Current particle-based maps describe the occupancy status in discrete grid form and suffer from the grid size problem, wherein a large grid size is unfavorable for motion planning while a small grid size lowers efficiency and causes gaps and inconsistencies. To tackle this problem, this paper generalizes the particle-based map into continuous space and builds an efficient 3D egocentric local map. A dual-structure subspace division paradigm, composed of a voxel subspace division and a novel pyramid-like subspace division, is proposed to propagate particles and update the map efficiently with the consideration of occlusions. The occupancy status at an arbitrary point in the map space can then be estimated with the weights of the particles. To reduce the noise in modeling static and dynamic obstacles simultaneously, an initial velocity estimation approach and a mixture model are utilized. Experimental results show that our map can effectively and efficiently model both dynamic obstacles and static obstacles. Compared to the state-of-the-art grid-form particle-based map, our map enables continuous occupancy estimation and substantially improves the mapping performance at different resolutions., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Learning & Autonomous Control

We introduce Point-Bind, a 3D multi-modality model aligning point clouds with 2D image, language, audio, and video. Guided by ImageBind, we construct a joint embedding space between 3D and multi-modalities, enabling many promising applications, e.g., any-to-3D generation, 3D embedding arithmetic, and 3D open-world understanding. On top of this, we further present Point-LLM, the first 3D large language model (LLM) following 3D multi-modal instructions. By parameter-efficient fine-tuning techniques, Point-LLM injects the semantics of Point-Bind into pre-trained LLMs, e.g., LLaMA, which requires no 3D instruction data, but exhibits superior 3D and multi-modal question-answering capacity. We hope our work may cast a light on the community for extending 3D point clouds to multi-modality applications. Code is available at https://github.com/ZiyuGuo99/Point-Bind_Point-LLM., Comment: Work in progress. Code is available at https://github.com/ZiyuGuo99/Point-Bind_Point-LLM

To reduce the reliance on large-scale datasets, recent works in 3D segmentation resort to few-shot learning. Current 3D few-shot semantic segmentation methods first pre-train the models on `seen' classes, and then evaluate their generalization performance on `unseen' classes. However, the prior pre-training stage not only introduces excessive time overhead, but also incurs a significant domain gap on `unseen' classes. To tackle these issues, we propose an efficient Training-free Few-shot 3D Segmentation netwrok, TFS3D, and a further training-based variant, TFS3D-T. Without any learnable parameters, TFS3D extracts dense representations by trigonometric positional encodings, and achieves comparable performance to previous training-based methods. Due to the elimination of pre-training, TFS3D can alleviate the domain gap issue and save a substantial amount of time. Building upon TFS3D, TFS3D-T only requires to train a lightweight query-support transferring attention (QUEST), which enhances the interaction between the few-shot query and support data. Experiments demonstrate TFS3D-T improves previous state-of-the-art methods by +6.93% and +17.96% mIoU respectively on S3DIS and ScanNet, while reducing the training time by -90%, indicating superior effectiveness and efficiency., Comment: Code is available at https://github.com/yangyangyang127/TFS3D

Recovering the shape and appearance of real-world objects from natural 2D images is a long-standing and challenging inverse rendering problem. In this paper, we introduce a novel hybrid differentiable rendering method to efficiently reconstruct the 3D geometry and reflectance of a scene from multi-view images captured by conventional hand-held cameras. Our method follows an analysis-by-synthesis approach and consists of two phases. In the initialization phase, we use traditional SfM and MVS methods to reconstruct a virtual scene roughly matching the real scene. Then in the optimization phase, we adopt a hybrid approach to refine the geometry and reflectance, where the geometry is first optimized using an approximate differentiable rendering method, and the reflectance is optimized afterward using a physically-based differentiable rendering method. Our hybrid approach combines the efficiency of approximate methods with the high-quality results of physically-based methods. Extensive experiments on synthetic and real data demonstrate that our method can produce reconstructions with similar or higher quality than state-of-the-art methods while being more efficient., Comment: IJCAI2023

The somatotopic interface (SI) and non-somatotopic interface (NI) are commonly used to provide non-invasive sensory feedback. Nevertheless, differences between somatotopic and non-somatotopic feedbacks are rarely reported, and objective evaluations of the corresponding brain response are missing as well. Few studies have reported how to design the stimulation encoding strategy based on the two interfaces in sensory feedback. The objective of this study was to investigate the difference in sensory characteristics between SI and NI, and propose an optimal encoding method for non-invasive feedback interfaces.. We recruited seven amputees and compared the tactile sensitivity to stimulated positions and intensities between SI (phantom finger area) and NI (upper arm) in a tactile discrimination task. Electroencephalography (EEG) evaluation task was subsequently conducted to objectively evaluate the stimulus-evoked brain response for SI and NI. Finally, the two kinds of tactile information (stimulated position and intensity) was applied to an object recognition task in a closed-loop prosthesis control system. Specifically, the object size was reflected by the prosthetic finger position through stimulated position encoding, and the object stiffness was reflected by the contact force of prosthetic fingers through stimulated intensity encoding. We compared the performance under four feedback conditions (combinations between two kinds of tactile information and two interfaces).. Behavioral results showed that NI was more sensitive to position information while SI was more sensitive to intensity information. EEG results were consistent with behavioral results, showing a higher sensitivity of sensory alpha ERD and a stronger correlation between alpha ERD and discrimination accuracies for NI in the position discrimination, while the trend was opposite in the intensity discrimination. The feedback encoding allowed amputees to discriminate the size and stiffness of nine objects w

Large-scale pre-trained models have shown promising open-world performance for both vision and language tasks. However, their transferred capacity on 3D point clouds is still limited and only constrained to the classification task. In this paper, we first collaborate CLIP and GPT to be a unified 3D open-world learner, named as PointCLIP V2, which fully unleashes their potential for zero-shot 3D classification, segmentation, and detection. To better align 3D data with the pre-trained language knowledge, PointCLIP V2 contains two key designs. For the visual end, we prompt CLIP via a shape projection module to generate more realistic depth maps, narrowing the domain gap between projected point clouds with natural images. For the textual end, we prompt the GPT model to generate 3D-specific text as the input of CLIP's textual encoder. Without any training in 3D domains, our approach significantly surpasses PointCLIP by +42.90%, +40.44%, and +28.75% accuracy on three datasets for zero-shot 3D classification. On top of that, V2 can be extended to few-shot 3D classification, zero-shot 3D part segmentation, and 3D object detection in a simple manner, demonstrating our generalization ability for unified 3D open-world learning., Comment: Code is available at https://github.com/yangyangyang127/PointCLIP_V2

Positioning with one inertial measurement unit and one ranging sensor is commonly thought to be feasible only when trajectories are in certain patterns ensuring observability. For this reason, to pursue observable patterns, it is required either exciting the trajectory or searching key nodes in a long interval, which is commonly highly nonlinear and may also lack resilience. Therefore, such a positioning approach is still not widely accepted in real-world applications. To address this issue, this work first investigates the dissipative nature of flying robots considering aerial drag effects and re-formulates the corresponding positioning problem, which guarantees observability almost surely. On this basis, a dimension-reduced wriggling estimator is proposed accordingly. This estimator slides the estimation horizon in a stepping manner, and output matrices can be approximately evaluated based on the historical estimation sequence. The computational complexity is then further reduced via a dimension-reduction approach using polynomial fittings. In this way, the states of robots can be estimated via linear programming in a sufficiently long interval, and the degree of observability is thereby further enhanced because an adequate redundancy of measurements is available for each estimation. Subsequently, the estimator's convergence and numerical stability are proven theoretically. Finally, both indoor and outdoor experiments verify that the proposed estimator can achieve decimeter-level precision at hundreds of hertz per second, and it is resilient to sensors' failures. Hopefully, this study can provide a new practical approach for self-localization as well as relative positioning of cooperative agents with low-cost and lightweight sensors.

Numerical models of electromyographic (EMG) signals have provided a huge contribution to our fundamental understanding of human neurophysiology and remain a central pillar of motor neuroscience and the development of human-machine interfaces. However, whilst modern biophysical simulations based on finite element methods are highly accurate, they are extremely computationally expensive and thus are generally limited to modelling static systems such as isometrically contracting limbs. As a solution to this problem, we propose a transfer learning approach, in which a conditional generative model is trained to mimic the output of an advanced numerical model. To this end, we present BioMime, a conditional generative neural network trained adversarially to generate motor unit activation potential waveforms under a wide variety of volume conductor parameters. We demonstrate the ability of such a model to predictively interpolate between a much smaller number of numerical model's outputs with a high accuracy. Consequently, the computational load is dramatically reduced, which allows the rapid simulation of EMG signals during truly dynamic and naturalistic movements.

Multiple mobile manipulators show superiority in the tasks requiring mobility and dexterity compared with a single robot, especially when manipulating/transporting bulky objects. When the object and the manipulators are rigidly connected, closed-chain will form and the motion of the whole system will be restricted onto a lower-dimensional manifold. However, current research on multi-robot motion planning did not fully consider the formation of the whole system, the redundancy of the mobile manipulator and obstacles in the environment, which make the tasks challenging. Therefore, this paper proposes a hierarchical framework to efficiently solve the above challenges, where the centralized layer plans the object's motion offline and the decentralized layer independently explores the redundancy of each robot in real-time. In addition, closed-chain, obstacle-avoidance and the lower bound of the formation constraints are guaranteed in the centralized layer, which cannot be achieved simultaneously by other planners. Moreover, capability map, which represents the distribution of the formation constraint, is applied to speed up the two layers. Both simulation and experimental results show that the proposed framework outperforms the benchmark planners significantly. The system could bypass or cross obstacles in cluttered environments, and the framework can be applied to different numbers of heterogeneous mobile manipulators.

This paper proposes a perception-shared and swarm trajectory global optimal (STGO) algorithm fused UAVs formation motion planning framework aided by an active sensing system. First, the point cloud received by each UAV is fit by the gaussian mixture model (GMM) and transmitted in the swarm. Resampling from the received GMM contributes to a global map, which is used as the foundation for consensus. Second, to improve flight safety, an active sensing system is designed to plan the observation angle of each UAV considering the unknown field, overlap of the field of view (FOV), velocity direction and smoothness of yaw rotation, and this planning problem is solved by the distributed particle swarm optimization (DPSO) algorithm. Last, for the formation motion planning, to ensure obstacle avoidance, the formation structure is allowed for affine transformation and is treated as the soft constraint on the control points of the B-spline. Besides, the STGO is introduced to avoid local minima. The combination of GMM communication and STGO guarantees a safe and strict consensus between UAVs. Tests on different formations in the simulation show that our algorithm can contribute to a strict consensus and has a success rate of at least 80% for obstacle avoidance in a dense environment. Besides, the active sensing system can increase the success rate of obstacle avoidance from 50% to 100% in some scenarios.

Particle-based dynamic occupancy maps were proposed in recent years to model the obstacles in dynamic environments. Current particle-based maps describe the occupancy status in discrete grid form and suffer from the grid size problem, wherein a large grid size is unfavorable for motion planning, while a small grid size lowers efficiency and causes gaps and inconsistencies. To tackle this problem, this paper generalizes the particle-based map into continuous space and builds an efficient 3D egocentric local map. A dual-structure subspace division paradigm, composed of a voxel subspace division and a novel pyramid-like subspace division, is proposed to propagate particles and update the map efficiently with the consideration of occlusions. The occupancy status of an arbitrary point in the map space can then be estimated with the particles' weights. To further enhance the performance of simultaneously modeling static and dynamic obstacles and minimize noise, an initial velocity estimation approach and a mixture model are utilized. Experimental results show that our map can effectively and efficiently model both dynamic obstacles and static obstacles. Compared to the state-of-the-art grid-form particle-based map, our map enables continuous occupancy estimation and substantially improves the performance in different resolutions., Comment: This paper has been accepted by IEEE Transactions on Robotics

Although multifarious variants of convolutional neural networks (CNNs) have proved successful in cardiac index quantification, they seem vulnerable to mild input perturbations, e.g., spatial transformations, image distortions, and adversarial attacks. Such brittleness erodes our trust in CNN-based automated diagnosis of various cardiovascular diseases. In this work, we describe a simple and effective method to learn robust CNNs for left ventricle (LV) quantification, including cavity and myocardium areas, directional dimensions, and regional wall thicknesses. The key to the success of our approach is the use of the biologically-inspired steerable pyramid transform (SPT) as fixed front-end processing, which brings three computational advantages to LV quantification. First, the basis functions of SPT match the anatomical structure of the LV as well as the geometric characteristics of the estimated indices. Second, SPT enables sharing a CNN across different orientations as a form of parameter regularization, and explicitly captures the scale variations of the LV in a natural way. Third, the residual highpass subband can be conveniently discarded to further encourage robust feature learning. A concise and effective metric, named Robustness Ratio, is proposed to evaluate the robustness under various input perturbations. Extensive experiments on 145 cardiac sequences show that our SPT-augmented method performs favorably against state-of-the-art algorithms in terms of prediction accuracy, but is significantly more robust under input perturbations., Comment: 10 pages, 13 figures, journal paper

Abstract Advances in development of artificial muscles have enabled creation of soft robots with biological dexterity and self-adaption in unstructured environments; however, production of scalable artificial muscles with multiple-mode actuations remains elusive. Inspired by muscle-fiber arrays in muscular hydrostats, we present a class of versatile artificial muscles called MAIPAMs (muscle-fiber array inspired pneumatic artificial muscles), capable of multiple-mode actuations (such as parallel elongation-bending-spiraling actuations, 10 parallel bending actuations and cascaded elongation-bending-spiraling actuations). Our MAIPAMs consist of active 3D elastomer-balloon arrays reinforced by a passive elastomer membrane, achieved through a planar design and one-step rolling fabrication approach. We introduce prototypical designs for the MAIPAMs and demonstrate their muscle-mimic structures and versatility, as well as their scalable ability to integrate flexible but non-stretchable layers for contraction and twisting actuation modes and compliant electrodes for self-sensing. We further demonstrate that this class of artificial muscles shows potential for versatile robotic applications, such as carrying a camera for recording videos, gripping or manipulating objects, and climbing a pipe-line.

Flying robots such as the quadrotor could provide an efficient approach for medical treatment or sensor placing of wild animals. In these applications, continuously targeting the moving animal is a crucial requirement. Due to the underactuated characteristics of the quadrotor and the coupled kinematics with the animal, nonlinear optimal tracking approaches, other than smooth feedback control, are required. However, with severe nonlinearities, it would be time-consuming to evaluate control inputs, and real-time tracking may not be achieved with generic optimizers onboard. To tackle this problem, a novel efficient egocentric regulation approach with high computational efficiency is proposed in this paper. Specifically, it directly formulates the optimal tracking problem in an egocentric manner regarding the quadrotor's body coordinates. Meanwhile, the nonlinearities of the system are peeled off through a mapping of the feedback states as well as control inputs, between the inertial and body coordinates. In this way, the proposed efficient egocentric regulator only requires solving a quadratic performance objective with linear constraints and then generate control inputs analytically. Comparative simulations and mimic biological experiment are carried out to verify the effectiveness and computational efficiency. Results demonstrate that the proposed control approach presents the highest and stablest computational efficiency than generic optimizers on different platforms. Particularly, on a commonly utilized onboard computer, our method can compute the control action in approximately 0.3 ms, which is on the order of 350 times faster than that of generic nonlinear optimizers, establishing a control frequency around 3000 Hz.

Xiaoyi Yi,1 Xiangyang Zhu,1 Yong Zhou,1 Dongmei Zhang,2 Mengmeng Li,2 Yuting Zhu,1 Xiaoming Guo1 1Deparment of Neurology, Affiliated Hospital 2 of Nantong University, Nantong, People’s Republic of China; 2Clinical Research Center, Affiliated Hospital 2 of Nantong University, Nantong, People’s Republic of ChinaCorrespondence: Xiangyang ZhuDepartment of Neurology, Affiliated Hospital 2 of Nantong University, 6 Haier-Xiang North Road, Nantong, 226000, Jiangsu, People’s Republic of ChinaFax +86 513-85061148Email zhuxxyy2092@163.comPurpose: Previous studies have shown that insulin resistance and inflammation may be associated with the pathophysiological mechanisms of mood disorders. Here, we investigated whether homeostatic model assessment of insulin resistance (HOMA-IR) and serum interleukin-1β (IL-1β) in acute ischemic stroke patients might be associated with post-stroke depression (PSD).Materials and Methods: The prospective study was conducted in China from February 2019 to September 2020. HOMA-IR and clinical data were collected at the time of admission. Serum levels of IL-1β were determined with enzyme-linked immunosorbent assays. Symptoms of depression and anxiety were screened by using the Hamilton Depression and Anxiety Scale at 6 months after stroke, and PSD was diagnosed on the basis of the Diagnostic and Statistical Manual of Mental Disorders (DSM-V) criteria. The association of potential risk factors with PSD was analyzed with multivariate logistic regression analysis. Finally, the ability of HOMA-IR and IL-1β to predict PSD was assessed with receiver operating characteristic curve.Results: A total of 305 people was included in the study; 65% were male, and the median age was 69.5± 11.8 years. At the 6-month follow-up, 113 patients (37.5%) showed depressive symptoms. In multivariate logistic regression analysis, HOMA-IR and IL-1β as graded variables were associated with an

This paper investigates a novel active-sensing-based obstacle avoidance paradigm for flying robots in dynamic environments. Instead of fusing multiple sensors to enlarge the field of view (FOV), we introduce an alternative approach that utilizes a stereo camera with an independent rotational DOF to sense the obstacles actively. In particular, the sensing direction is planned heuristically by multiple objectives, including tracking dynamic obstacles, observing the heading direction, and exploring the previously unseen area. With the sensing result, a flight path is then planned based on real-time sampling and uncertainty-aware collision checking in the state space, which constitutes an active sense and avoid (ASAA) system. Experiments in both simulation and the real world demonstrate that this system can well cope with dynamic obstacles and abrupt goal direction changes. Since only one stereo camera is utilized, this system provides a low-cost and effective approach to overcome the FOV limitation in visual navigation., Comment: Accepted by IEEE Transactions on Mechatronics on 27 Jan 2021

While training an end-to-end navigation network in the real world is usually of high cost, simulation provides a safe and cheap environment in this training stage. However, training neural network models in simulation brings up the problem of how to effectively transfer the model from simulation to the real world (sim-to-real). In this work, we regard the environment representation as a crucial element in this transfer process and propose a visual information pyramid (VIP) model to systematically investigate a practical environment representation. A novel representation composed of spatial and semantic information synthesis is then established accordingly, where noise model embedding is particularly considered. To explore the effectiveness of this representation, we compared the performance with representations popularly used in the literature in both simulated and real-world scenarios. Results suggest that our environment representation stands out. Furthermore, an analysis on the feature map is implemented to investigate the effectiveness through inner reaction, which could be irradiative for future researches on end-to-end navigation., Comment: 10 pages, 11 figures

Dielectric elastomer actuators (DEAs) are a promising actuation technology in soft robotics owing to their large voltage-induced deformation and rapid response. However, most existing DEA design paradigms are empirical or intuitive, lacking the mathematical modeling and optimization methodology to exploit their actuation capabilities for prescribed motion tasks. In this paper, we present an automatic design methodology to maximize the concerned displacement(s) of DEAs by topology optimization of the applied spatial electric fields (SEFs). Our method is enabled by integrating the freeform SEF profile captured by implicit level sets, and the constitutive model of DEAs incorporating geometric and material nonlinearities and the electromechanical coupling effect, into a gradient-based optimizer. We implement our method for motions of single and multiple degrees of freedom (DOFs) of planar DEAs, and the optimized SEFs have been found to improve the output displacements by more than 75% compared with their intuitive counterparts. We further demonstrate a proof-of-concept application in which our designed two-DOF DEAs can actively drive various host structures to shape-morph from flat sheets to desired three dimensional configurations. Overall, our paper represents the first step toward automatic design of soft DEAs for diverse potential applications in soft machines and robots.

All-solid-state lithium batteries (ASSLBs) are being considered as the ultimate solution to the safety issue of current lithium ion batteries which use flammable organic electrolyte. The properties of the solid electrolyte, the most important component in ASSLBs, largely affect the electrode/electrolyte interfacial behavior and eventually the performance of ASSLBs. Sulfide electrolytes are considered as one of the most promising solid electrolyte for ASSLBs because of its excellent mechanical properties. However, they suffer from poor electrochemical stability and lithium dendrite formation. In this thesis, I demonstrated that the nitrogen-doped sulfide solid electrolyte system (75-1.5x)Li2S-25P2S5-xLi3N showed comprehensive performance improvements. The ionic conductivity is enhanced and the interfacial resistance between Li anode and solid electrolyte gets reduced by over 80%. The dendrite formation in solid electrolyte could also be effectively suppressed with the critical current density enhanced by 70%. The simultaneous improvement make it a promising solid electrolyte for ASSLBs.

This paper deals with mechanical systems with passive contact elements, such as whole-hand grasps and fixture systems. The force closure problem in fixtures and manipulation systems with hybrid (active and passive) contacts is shown to be quite different from the pure active force closure in a multi-fingered robot hand. We discuss the conditions of active and passive force closure problems in such devices based on a rigid-body model with frictional contact. The contact force space is decomposed into three orthogonal subspaces: the space of external forces, the space of active internal forces, and the space of passive internal forces. The space of active internal force and the space of passive internal force play important roles in achieving the closure grasping. This paper presents an algorithm for computing the basis of each subspace. Based on this force decomposition, the force closure problem is formulated as linear matrix inequality feasibility problems, and minimization of the joint torque is also studied. © IMechE 2012.

This paper deals with mechanical systems with passive contact elements, such as whole-hand grasps and fixture systems. The force closure problem in fixtures and manipulation systems with hybrid (active and passive) contacts is shown to be quite different from the pure active force closure in a multi-fingered robot hand. We discuss the conditions of active and passive force closure problems in such devices based on a rigid-body model with frictional contact. The contact force space is decomposed into three orthogonal subspaces: the space of external forces, the space of active internal forces, and the space of passive internal forces. The space of active internal force and the space of passive internal force play important roles in achieving the closure grasping. This paper presents an algorithm for computing the basis of each subspace. Based on this force decomposition, the force closure problem is formulated as linear matrix inequality feasibility problems, and minimization of the joint torque is also studied. © IMechE 2012.

This paper deals with mechanical systems with passive contact elements, such as whole-hand grasps and fixture systems. The force closure problem in fixtures and manipulation systems with hybrid (active and passive) contacts is shown to be quite different from the pure active force closure in a multi-fingered robot hand. We discuss the conditions of active and passive force closure problems in such devices based on a rigid-body model with frictional contact. The contact force space is decomposed into three orthogonal subspaces: the space of external forces, the space of active internal forces, and the space of passive internal forces. The space of active internal force and the space of passive internal force play important roles in achieving the closure grasping. This paper presents an algorithm for computing the basis of each subspace. Based on this force decomposition, the force closure problem is formulated as linear matrix inequality feasibility problems, and minimization of the joint torque is also studied. © IMechE 2012.

The deformation of the workpiece-fixture system has essential influence on the locating accuracy of the workpiece. To minimize the overall deformation of the workpiece-fixture system is an important issue in fixture design. This paper focuses on the fixture layout design with compliant model. A topology optimization approach is presented in order to reduce the complexity introduced by the high computational cost of the finite element equation solving and the exhaustive search in the point set domain. With finite element analysis, algorithms are developed for the optimization problem of locator synthesis in the point set domain. Numerical examples are also presented to verify the effectiveness of the proposed approach. © 2011 IEEE.

The deformation of the workpiece-fixture system has essential influence on the locating accuracy of the workpiece. To minimize the overall deformation of the workpiece-fixture system is an important issue in fixture design. This paper focuses on the fixture layout design with compliant model. A topology optimization approach is presented in order to reduce the complexity introduced by the high computational cost of the finite element equation solving and the exhaustive search in the point set domain. With finite element analysis, algorithms are developed for the optimization problem of locator synthesis in the point set domain. Numerical examples are also presented to verify the effectiveness of the proposed approach. © 2011 IEEE.

The deformation of the workpiece-fixture system has essential influence on the locating accuracy of the workpiece. To minimize the overall deformation of the workpiece-fixture system is an important issue in fixture design. This paper focuses on the fixture layout design with compliant model. A topology optimization approach is presented in order to reduce the complexity introduced by the high computational cost of the finite element equation solving and the exhaustive search in the point set domain. With finite element analysis, algorithms are developed for the optimization problem of locator synthesis in the point set domain. Numerical examples are also presented to verify the effectiveness of the proposed approach. © 2011 IEEE.

This paper deals with the mechanical systems with passive contact elements, such as the whole hand grasp and fixture system. We discuss the conditions of active and passive force closure problems in such devices based on rigid body model with frictional contact. The contact force space is decomposed into three orthogonal subspaces: the space of external forces, the space of active internal forces, and the space of passive internal forces. The space of active internal force and the space of passive internal force play important roles in achieving the closure grasping. This paper presents an algorithm for computing the basis of each subspace. Based on this force decomposition, the force closure problem is formulated as LMI feasibility problems, and minimization of the joint torque is also studied.

This paper deals with the mechanical systems with passive contact elements, such as the whole hand grasp and fixture system. We discuss the conditions of active and passive force closure problems in such devices based on rigid body model with frictional contact. The contact force space is decomposed into three orthogonal subspaces: the space of external forces, the space of active internal forces, and the space of passive internal forces. The space of active internal force and the space of passive internal force play important roles in achieving the closure grasping. This paper presents an algorithm for computing the basis of each subspace. Based on this force decomposition, the force closure problem is formulated as LMI feasibility problems, and minimization of the joint torque is also studied.

This paper deals with the mechanical systems with passive contact elements, such as the whole hand grasp and fixture system. We discuss the conditions of active and passive force closure problems in such devices based on rigid body model with frictional contact. The contact force space is decomposed into three orthogonal subspaces: the space of external forces, the space of active internal forces, and the space of passive internal forces. The space of active internal force and the space of passive internal force play important roles in achieving the closure grasping. This paper presents an algorithm for computing the basis of each subspace. Based on this force decomposition, the force closure problem is formulated as LMI feasibility problems, and minimization of the joint torque is also studied.

This paper presents a numerical test for the closure properties (force closure and form closure) of multifingered grasps. For three-dimensional (3-D) grasps with frictional point contacts or soft contacts, the numerical test is formulated as a convex constrained optimization problem without linearization of the friction cone. For 3-D frictionless grasps, it can be calculated by solving a single linear program. The proposed numerical test (along with the rank of the grasp matrix) provides an efficient tool for the analysis of the force-closure property and the relative force-closure property.

This paper establishes the equivalence between the solution to a linear Chebyshev approximation problem and that of a weighted least squares (WLS) problem with the weighting parameters being appropriately defined. On this basis, we present an algorithm for form error evaluation of geometric features. The algorithm is implemented as an iterative procedure. At each iteration, a WLS problem is solved and the weighting parameters are updated. The proposed algorithm is of general-purpose, it can be used to evaluate the exact minimum zone error of various geometric features including flatness, circularity, sphericity, cylindericity and spatial straightness. Numerical examples are presented to show the effectiveness and efficiency of the algorithm.

This paper presents a numerical test for the closure properties (force closure and form closure) of multifingered grasps. For three-dimensional (3-D) grasps with frictional point contacts or soft contacts, the numerical test is formulated as a convex constrained optimization problem without linearization of the friction cone. For 3-D frictionless grasps, it can be calculated by solving a single linear program. The proposed numerical test (along with the rank of the grasp matrix) provides an efficient tool for the analysis of the force-closure property and the relative force-closure property.

This paper establishes the equivalence between the solution to a linear Chebyshev approximation problem and that of a weighted least squares (WLS) problem with the weighting parameters being appropriately defined. On this basis, we present an algorithm for form error evaluation of geometric features. The algorithm is implemented as an iterative procedure. At each iteration, a WLS problem is solved and the weighting parameters are updated. The proposed algorithm is of general-purpose, it can be used to evaluate the exact minimum zone error of various geometric features including flatness, circularity, sphericity, cylindericity and spatial straightness. Numerical examples are presented to show the effectiveness and efficiency of the algorithm.

This paper presents a numerical test for the closure properties (force closure and form closure) of multifingered grasps. For three-dimensional (3-D) grasps with frictional point contacts or soft contacts, the numerical test is formulated as a convex constrained optimization problem without linearization of the friction cone. For 3-D frictionless grasps, it can be calculated by solving a single linear program. The proposed numerical test (along with the rank of the grasp matrix) provides an efficient tool for the analysis of the force-closure property and the relative force-closure property.

This paper establishes the equivalence between the solution to a linear Chebyshev approximation problem and that of a weighted least squares (WLS) problem with the weighting parameters being appropriately defined. On this basis, we present an algorithm for form error evaluation of geometric features. The algorithm is implemented as an iterative procedure. At each iteration, a WLS problem is solved and the weighting parameters are updated. The proposed algorithm is of general-purpose, it can be used to evaluate the exact minimum zone error of various geometric features including flatness, circularity, sphericity, cylindericity and spatial straightness. Numerical examples are presented to show the effectiveness and efficiency of the algorithm.

Recovering the shape and appearance of real-world objects from natural 2D images is a long-standing and challenging inverse rendering problem. In this paper, we introduce a novel hybrid differentiable rendering method to efficiently reconstruct the 3D geometry and reflectance of a scene from multi-view images captured by conventional hand-held cameras. Our method follows an analysis-by-synthesis approach and consists of two phases. In the initialization phase, we use traditional SfM and MVS methods to reconstruct a virtual scene roughly matching the real scene. Then in the optimization phase, we adopt a hybrid approach to refine the geometry and reflectance, where the geometry is first optimized using an approximate differentiable rendering method, and the reflectance is optimized afterward using a physically-based differentiable rendering method. Our hybrid approach combines the efficiency of approximate methods with the high-quality results of physically-based methods. Extensive experiments on synthetic and real data demonstrate that our method can produce reconstructions with similar or higher quality than state-of-the-art methods while being more efficient.