A pin-structure is an array of independent pins and possesses of hyper-adaptability for arbitrary shape replication. Currently, the researches on pin-structure designing have kept the independence of each pin, which causes the complexity of the mechanism and controlling. Here, a novel pin-array clamper (PAC) is designed by applying specific topology of a wire to thread all the pins. The PAC presents a unique feature of adaptive contacting force upon its autonomous shape replication toward complex-shaped objects which used to be a challenge in robotic manipulation. Experimental results as well as theoretical analysis characterize the adaptiveness in both force and shape. In order to improve the homogeneity of the contacting force, the PAC is updated by a double-layer design with comparison with a single-layer one. As validation, the PAC is demonstrated by clamping objects varying in shape, rigidity and weight. Non-invasive force contacting has been achieved through rigid-compliant mechanical structure design. The installation of PAC on a robotic arm can achieve stable grasping of durians as well as transportation and rotation. This PAC offers a new insight for achieving adaptive grasping unconventional s. To get a sense of the PAC’s functionality and practicality, we refer the reader to the live YouTube demonstration for various objects with different shapes and materials https://youtu.be/njmJg7AZBTE.

Ensuring safe driving while maintaining travel efficiency for autonomous vehicles (AVs) in dynamic and occluded environments is a critical challenge. This article proposes an occlusion-aware contingency safety-critical planning approach for real-time autonomous driving. Leveraging reachability analysis for risk assessment, forward reachable sets (FRSs) of phantom vehicles (PVs) are used to derive risk-aware dynamic velocity boundaries. These velocity boundaries are incorporated into a biconvex nonlinear programming (NLP) formulation that formally enforces safety using spatiotemporal barrier constraints, while simultaneously optimizing exploration and fallback trajectories within a receding horizon planning framework. To enable real-time computation and coordination between trajectories, we employ the consensus alternating direction method of multipliers (ADMMs) to decompose the biconvex NLP problem into low-dimensional convex subproblems. The effectiveness of the proposed approach is validated through simulations and real-world experiments in occluded intersections. Experimental results demonstrate enhanced safety and improved travel efficiency, enabling real-time safe trajectory generation in dynamic occluded intersections under varying obstacle conditions. The project page is available at: https://zack4417.github.io/oacp-website/.

Ensuring safety and driving consistency is a significant challenge for autonomous vehicles operating in partially observed environments. This work introduces a consistent parallel trajectory optimization (CPTO) approach to enable safe and consistent driving in dense obstacle environments with perception uncertainties. Utilizing discrete-time barrier function theory, we develop a consensus safety barrier module that ensures reliable safety coverage within the spatiotemporal trajectory space across potential obstacle configurations. Following this, a bi-convex parallel trajectory optimization problem is derived that facilitates decomposition into a series of low-dimensional quadratic programming problems to accelerate computation. By leveraging the consensus alternating direction method of multipliers (ADMM) for parallel optimization, each generated candidate trajectory corresponds to a possible environment configuration while sharing a common consensus trajectory segment. This ensures driving safety and consistency when executing the consensus trajectory segment for the ego vehicle in real time. We validate our CPTO framework through extensive comparisons with state-of-the-art baselines across multiple driving tasks in partially observable environments. Our results demonstrate improved safety and consistency using both synthetic and real-world traffic datasets.

Achieving visual explanations in spiking neural networks (SNNs) is challenging due to the spatial sparsity and temporal discontinuity of spikes, which make it difficult to generate coherent saliency mappings and hinder interpretability. To address this, we propose hierarchical spike aggregation activation map (HSA2M), a method inspired by two neurobiological principles: 1) hierarchical feature integration in the ventral pathway (V$1\rightarrow $V$2\rightarrow $V$4\rightarrow $IT) and 2) short interspike intervals (ISI) reflecting decision-relevant saliency. HSA2M achieves fine-grained visual explanations in SNNs through multilayer spike aggregation and adaptive fusion. It consists of three core modules: a spike activation map generator (SAMG) that constructs layer-wise saliency maps via temporal spike aggregation, a Fisher-weighted fusion (FWF) module that adaptively integrates multilayer maps using Fisher information (FI), and a metric-aware hyperparameter optimizer (MA-HPO) that enhances explanatory fidelity through metric-driven parameter tuning. By integrating these components, HSA2M generates more precise and high-fidelity visual explanations while maintaining event-driven efficiency through spike-based processing. Extensive experiments on neuromorphic (DVS-Gesture and DSEC-Semantic) and static (Tiny-ImageNet and ImageNet) benchmarks demonstrate that HSA2M outperforms state-of-the-art methods in terms of interpretability [e.g., ADCC improved from 0.8792 to 0.9215 (+4.81%)], faithfulness [e.g., Spearman’s rank correlation coefficient$\rho $improved from 0.189 to 0.209(+10.085%)], and adversarial robustness [e.g., normalized L1 distance decreased from 0.0673 to 0.0092 (−86.32%)].

Despite the significant success of imitation learning in robotic manipulation, its application to bimanual tasks remains highly challenging. Existing approaches mainly learn a policy to predict a distant next-best end-effector pose (NBP) and then compute the corresponding joint rotation angles for motion using inverse kinematics. However, they suffer from two important issues: (1) rarely considering the physical robotic structure, which may cause self-collisions or interferences, and (2) overlooking the kinematics constraint, which may result in the predicted poses not conforming to the actual limitations of the robot joints. In this paper, we propose Kinematics enhanced Spatial-TemporAl gRaph Diffuser (KStar Diffuser). Specifically, (1) to incorporate the physical robot structure information into action prediction, KStar Diffuser maintains a dynamic spatial-temporal graph according to the physical bimanual joint motions at continuous timesteps. This dynamic graph serves as the robot-structure condition for denoising the actions; (2) to make the NBP learning objective consistent with kinematics, we introduce the differentiable kinematics to provide the reference for optimizing KStar Diffuser. This module regularizes the policy to predict more reliable and kinematics-aware next end-effector poses. Experimental results show that our method effectively leverages the physical structural information and generates kinematics-aware actions in both simulation and real-world.

Tangram assembly, the art of human intelligence and manipulation dexterity, is a new challenge for robotics and reveals the limitations of state-of-the-arts. Here, we describe our initial exploration and highlight key problems in reasoning, planning, and manipulation for robotic tangram assembly. We present MRChaos (Master Rules from Chaos), a robust and general solution for learning assembly policies that can generalize to novel objects. In contrast to conventional methods based on prior geometric and kinematic models, MRChaos learns to assemble randomly generated objects through self-exploration in simulation without prior experience in assembling target objects. The reward signal is obtained from the visual observation change without manually designed models or annotations. MRChaos retains its robustness in assembling various novel tangram objects that have never been encountered during training, with only silhouette prompts. We show the potential of MRChaos in wider applications such as cutlery combinations. The presented work indicates that radical generalization in robotic assembly can be achieved by learning in much simpler domains. The code will be available https://robotll.github.io/MasterRulesFromChaos/.

Object transfer through throwing is a classic dynamic manipulation task that necessitates precise control and perception capabilities. However, developing dynamic models for unstructured environments using analytical methods presents challenges. In this study, we present DartBot, a robot that integrates tactile exploration and reinforcement learning to achieve robust throwing skills for nonrigid relatively small objects under the influence of moment of inertia which cause the object to spin in the air. Unlike traditional sim-to-real transfer methods, our approach involves direct training of the agent on a real hardware robot equipped with a high-resolution tactile sensor, enabling reinforced learning in a realistic and dynamic environment. By leveraging tactile perception, we incorporate pseudo-embeddings of the physical properties of objects into the learning process through tilting actions at two distinct angles. This tactile information enables the agent to infer and adapt its throwing strategy, resulting in improved accuracy when handling various objects and targeting distant locations. Furthermore, we demonstrate that the quality of a grasp significantly impacts the success rate of the throwing task. We evaluate the effectiveness of our method through extensive experiments, demonstrating superior performance and generalization capabilities in real-world throwing scenarios. We achieved a success rate of 95% for unseen objects with a mean error of 3.15 cm from the goal. A high-resolution video demo of our work is available athttps://youtu.be/KNFgDeLt-0g. Note to Practitioners—The industrial demand for precise and accurate object transfer beyond the robot’s maximum kinematic range is rapidly growing, necessitating advancements in robotic throwing manipulation to efficiently utilize resources. In this context, this paper contributes to the field by presenting a method for the transfer of deformable objects through overhand throwing, addressing the challenges of achieving precise control and perception capabilities by learning the complex physics of the task using raw data. The approach offers valuable insights and techniques for enhancing throwing manipulation tasks. The integration of high-resolution tactile sensing and reinforcement learning, while considering the influence of moment of inertia, opens up new possibilities for handling deformable objects in throwing tasks and developing dynamic models for such unstructured environments. The learned throwing policy is applied to a variety of previously unseen objects, demonstrating its effectiveness and ability to generalize in real-world throwing scenarios. The presented work holds applicability in various domains such as medical rehabilitation, logistic warehouses for packaging, and handling of urban waste. It shows promise in improving the precision, accuracy and efficiency of the throwing task. In the future, we aim to expand the current overhand throwing framework by incorporating rapid grasping in cluttered environments and enabling throwing to far distances with diverse target locations.

Enforcing safety while preventing overly conservative behaviors is essential for autonomous vehicles to achieve high task performance. In this paper, we propose a barrier-enhanced parallel homotopic trajectory optimization (BPHTO) approach with the over-relaxed alternating direction method of multipliers (ADMM) for real-time integrated decision-making and planning. To facilitate safety interactions between the ego vehicle (EV) and surrounding vehicles, a spatiotemporal safety module exhibiting bi-convexity is developed on the basis of barrier function. Varying barrier coefficients are adopted for different time steps in a planning horizon to account for the motion uncertainties of surrounding HVs and mitigate conservative behaviors. Additionally, we exploit the discrete characteristics of driving maneuvers to initialize nominal behavior-oriented free-end homotopic trajectories based on reachability analysis, and each trajectory is locally constrained to a specific driving maneuver while sharing the same task objectives. By leveraging the bi-convexity of the safety module and the kinematics of the EV, we formulate the BPHTO as a bi-convex optimization problem. Then constraint transcription and the over-relaxed ADMM are employed to streamline the optimization process, such that multiple trajectories are generated in real time with feasibility guarantees. Through a series of experiments, the proposed development demonstrates improved task accuracy, stability, and consistency in various traffic scenarios using synthetic and real-world traffic datasets.

Multimodal Large Language Models (MLLMs) have shown impressive reasoning abilities and general intelligence in various domains. It inspires researchers to train end-to-end MLLMs or utilize large models to generate policies with human-selected prompts for embodied agents. However, these methods exhibit limited generalization capabilities on unseen tasks or scenarios, and overlook the multimodal environment information which is critical for robots to make decisions. In this paper, we introduce a novel **Robo**tic **M**ultimodal **P**erception-**P**lanning (**RoboMP$^2$**) framework for robotic manipulation which consists of a Goal-Conditioned Multimodal Preceptor (GCMP) and a Retrieval-Augmented Multimodal Planner (RAMP). Specially, GCMP captures environment states by employing a tailored MLLMs for embodied agents with the abilities of semantic reasoning and localization. RAMP utilizes coarse-to-fine retrieval method to find the $k$ most-relevant policies as in-context demonstrations to enhance the planner. Extensive experiments demonstrate the superiority of RoboMP$^2$ on both VIMA benchmark and real-world tasks, with around 10% improvement over the baselines.

Detecting moving events produced by moving objects is a crucial task in the realms of autonomous driving and mobile robots. Moving objects have the potential to create ghost artifacts in mapped environments and pose risks to autonomous navigation. LiDAR serves as a vital sensor for autonomous systems due to its ability to provide dense and precise range measurements. However, existing LiDAR datasets often lack sufficient discussion on the motion labeling of moving objects, containing only a limited representation of moving entities within a single scene. Furthermore, the methodologies for Moving Event Detection (MED) on LiDAR sensors have not been comprehensively explored or evaluated. To address these gaps, this study focuses on constructing a diverse LiDAR moving event dataset encompassing multiple scenes with a high density of moving objects. A thorough review of current MED techniques is conducted, followed by the establishment of a performance benchmark based on evaluating these methods using our dataset. Additionally, part sequences of the dataset are utilized to host an online MED competition, aimed at fostering collaboration within the research community and advancing related studies.

In-hand manipulation is challenging in robotics due to the intricate contact dynamics and high degrees of control freedom. Precise manipulation with high accuracy often requires tactile perception, which adds further complexity to the system. Despite the challenges in perception and control, the rolling stick problem is an essential and practical motion primitive with many demanding industrial applications. This work aims to learn the high-resolution tactile dynamics of the rolling stick. Specifically, we try manipulating a small stick using the Allegro hand equipped with the Digit vision-based tactile sensor. The learning framework includes an action filtering module, tactile perception module, and learning with uncertainty module, all designed to operate in low data regimes. With only 2.3% amount of data and 5.7% model complexity of previous similar work, our learned contact dynamics model achieves better grasp stability, sub-millimeter precision, and promising zero-shot generalizability across novel objects. The proposed framework demonstrates the potential for precise in-hand manipulation with tactile feedback on real hardware. The project source code is available at: https://github.com/duyipai/Allegro_Digit. A video presentation is available here.

As automation technologies advance, the need for compact and multi-modal sensors in robotic applications is growing. To address this demand, we introduce CompdVision, a novel sensor that employs a compound-eye imaging system to combine near-field 3D visual and tactile sensing within a compact form factor. CompdVision utilizes two types of vision units to address diverse sensing needs, eliminating the need for complex modality conversion. Stereo units with far-focus lenses can see through the transparent elastomer for depth estimation beyond the contact surface. Simultaneously, tactile units with near-focus lenses track the movement of markers embedded in the elastomer to obtain contact deformation. Experimental results validate the sensor’s superior performance in 3D visual and tactile sensing, proving its capability for reliable external object depth estimation and precise measurement of tangential and normal contact forces. The dual modalities and compact design make the sensor a versatile tool for robotic manipulation.

While the conditional sequence modeling with the transformer architecture has demonstrated its effectiveness in dealing with offline reinforcement learning (RL) tasks, it is struggle to handle out-of-distribution states and actions. Existing work attempts to address this issue by data augmentation with the learned policy or adding extra constraints with the value-based RL algorithm. However, these studies still fail to overcome the following challenges: (1) insufficiently utilizing the historical temporal information among inter-steps, (2) overlooking the local intra-step relationships among return-to-gos (RTGs), states, and actions, (3) overfitting suboptimal trajectories with noisy labels. To address these challenges, we propose $\textbf{D}$ecision $\textbf{M}$amba ($\textbf{DM}$), a novel multi-grained state space model (SSM) with a self-evolving policy learning strategy. DM explicitly models the historical hidden state to extract the temporal information by using the mamba architecture. To capture the relationship among RTG-state-action triplets, a fine-grained SSM module is designed and integrated into the original coarse-grained SSM in mamba, resulting in a novel mamba architecture tailored for offline RL. Finally, to mitigate the overfitting issue on noisy trajectories, a self-evolving policy is proposed by using progressive regularization. The policy evolves by using its own past knowledge to refine the suboptimal actions, thus enhancing its robustness on noisy demonstrations. Extensive experiments on various tasks show that DM outperforms other baselines substantially.

Multi-mobile robot systems (MMRSs) show great advantages over one single robot in many applications. However, the robots are required to form desired task-specified formations, making feasible motions decrease significantly. Thus, it is challenging to determine whether the robots can pass through an obstructed environment under formation constraints, especially in an obstacle-rich environment. Furthermore, is there an optimal path for the robots? To deal with the two problems, a novel graph-based motion planner is proposed in this article. Valid configurations of the system are defined to satisfy both formation and obstacle constraints. Then, the whole valid configuration space is identified and mapped to an undirected graph. The breadth-first search (BFS) method is employed on the graph to answer the question of whether there is a feasible path on the graph. Finally, an optimal path will be planned on the updated graph, considering the cost of path length and formation preference. Simulation results show that the planner can be applied to get optimal motions of robots under formation constraints in obstacle-rich environments. In addition, different types of constraints are considered to verify the generality.

We study six-dimensional (6D) perceptive peg-in-hole problem for practical connector insertion task in this paper. To enable the manipulator system to handle different types of pegs in complex environment, we develop a perceptive robotic assembly system that utilizes an in-hand RGB-D camera for peg-in-hole with multiple types of pegs. The proposed framework addresses the critical hole detection and pose estimation problem through combining the learning-based detection with model-based pose estimation strategies. By exploiting the structure of the peg-in-hole task, we consider a rectangle-shape based characterization for modeling the candidate socket. Such a characterization allows us to design simple learning-based methods to detect and estimate the 6D pose of the target socket that balances between processing speed and accuracy. To validate our method, we test the performance of the proposed perceptive peg-in-hole solution using a KUKA iiwa7 robotic arm to accomplish the socket insertion task with two types of practical sockets (RJ45/HDMI). Without the need of additional search, our method achieves an acceptable success rate in the connector insertion tasks. The results confirm the reliability of our method and show that our method is suitable for real world application.

This paper tackles the task of singulating and grasping paper-like deformable objects. We refer to such tasks as paper-flipping. In contrast to manipulating deformable objects that lack compression strength (such as shirts and ropes), minor variations in the physical properties of the paper-like deformable objects significantly impact the results, making manipulation highly challenging. Here, we present Flipbot, a novel solution for flipping paper-like deformable objects. Flipbot allows the robot to capture object physical properties by integrating exteroceptive and proprioceptive perceptions that are indispensable for manipulating deformable objects. Furthermore, by incorporating a proposed coarse-to-fine exploration process, the system is capable of learning the optimal control parameters for effective paper-flipping through proprioceptive and exteroceptive inputs. We deploy our method on a real-world robot with a soft gripper and learn in a self-supervised manner. The resulting policy demonstrates the effectiveness of Flipbot on paper-flipping tasks with various settings beyond the reach of prior studies, including but not limited to flipping pages throughout a book and emptying paper sheets in a box. The code is available here: https://robotll.github.io/Flipbot/.

Grasping previously unseen objects for the first time, in which only partially occluded views of the object are available, remains a difficult challenge. Despite their recent successes, deep learning-based end-to-end methods remain impractical when training data and resources are limited and multiple grippers are used. Two-step methods that first identify the object shape and structure using deformable shape templates, then plan and execute the grasp, are free from those limitations, but also have difficulty with partially occluded objects. In this paper, we propose a two-step method that merges a richer set of shape primitives, the deformable superquadrics, with a deep learning network,DSQNet, that is trained to identify complete object shapes from partial point cloud data. Grasps are then generated that take into account the kinematic and structural properties of the gripper while exploiting the closed-form equations available for deformable superquadrics. A seven-dof robotic arm equipped with a parallel jaw gripper is used to conduct experiments involving a collection of household objects, achieving average grasp success rates of 93% (compared to 86% for existing methods), with object recognition times that are ten times faster. Code is available athttps://github.com/seungyeon-k/DSQNet-publicNote to Practitioners—This paper provides a comprehensive two-step method for grasping previously unseen objects, in which only partially occluded views of the object may be available. End-to-end deep learning-based methods typically require large amounts of training data, in the form of images of the objects taken from different angles and with different levels of occlusion, and grasping experiments that record the success and failure of each attempt; if a new gripper is used, more often than not the training data must be recollected and a new set of experiments performed. Two-step methods that first identify the object structure and shape using deformable shape templates, then plan the grasp based on knowledge of the object shape, are currently a more practical solution, but also have difficulty when only occluded views of the object are available. Our newly proposed two-step method takes advantage of a more flexible set of shape primitives, and also uses a supervised deep learning network to identify the object from occluded views. Our experimental results indicate improved grasp success rates against the state-of-the-art, with recognition rates that are up to ten times faster. Our method shows high recognition and grasping performance so is well applicable on most of the general household objects, but it cannot be directly applied to more diverse public 3D datasets since it requires some human-annotated segmentation labels. In future research, we will develop our deep learning network to automatically learn segmentation without human-annotated labels, allowing it to recognize more complex and diverse object shapes.

Recounts the career and contributions of Peter Luh.

Perceiving the dynamical environment both visually and tactilely is crucial for the survival of animals, and therefore, is considered of importance in robotics research. Recently, there has been an increasing interest in vision-based tactile sensors due to their high sensing resolution and robustness to environmental changes. However, almost all vision-based tactile sensors make only partial use of the camera, specifically, only when contact occurs, and stay idle at other times, which results in a waste of the camera information bandwidth. In this paper, we propose a new visual-tactile dual-modality sensor called SpecTac, which can visually inspect the environment and make tactile observations. The main novelty of the sensor is the use of ultraviolet (UV) LEDs and randomly distributed UV fluorescent markers. When the LEDs are on, those markers will be bright and can easily be distinguished and tracked from the background. Besides, by controlling the on and off of the UV LEDs, due to the switchable visibility of those markers, the sensor will switch between visual and tactile sensing mode. The qualities of tactile and visual perception are evaluated quantitatively by force estimation, visual triangulation and visual feature matching. By combining both modalities into one compact sensor, the information from the camera is better utilized, and it is hoped that the sensor will achieve more flexibility in the motion of the robot arm, especially in tasks where the workspace is narrow.

3D object detection has been wildly studied in recent years, especially for robot perception systems. However, existing 3D object detection is under a closed-set condition, meaning that the network can only output boxes of trained classes. Unfortunately, this closed-set condition is not robust enough for practical use, as it will identify unknown objects as known by mistake. Therefore, in this paper, we propose an open-set 3D object detector, which aims to (1) identify known objects, like the closed-set detection, and (2) identify unknown objects and give their accurate bounding boxes. Specifically, we divide the open-set 3D object detection problem into two steps: (1) finding out the regions containing the unknown objects with high probability and (2) enclosing the points of these regions with proper bounding boxes. The first step is solved by the finding that unknown objects are often classified as known objects with low confidence, and we show that the Euclidean distance sum based on metric learning is a better confidence score than the naive softmax probability to differentiate unknown objects from known objects. On this basis, unsupervised clustering is used to refine the bounding boxes of unknown objects. The proposed method combining metric learning and unsupervised clustering is called the MLUC network. Our experiments show that our MLUC network achieves state-of-the-art performance and can identify both known and unknown objects as expected.

Classical close-set semantic segmentation networks have limited ability to detect out-of-distribution (OOD) objects, which is important for safety-critical applications such as autonomous driving. Incrementally learning these OOD objects with few annotations is an ideal way to enlarge the knowledge base of the deep learning models. In this paper, we propose an open world semantic segmentation system that includes two modules: (1) an open-set semantic segmentation module to detect both in-distribution and OOD objects. (2) an incremental few-shot learning module to gradually incorporate those OOD objects into its existing knowledge base. This open world semantic segmentation system behaves like a human being, which is able to identify OOD objects and gradually learn them with corresponding supervision. We adopt the Deep Metric Learning Network (DMLNet) with contrastive clustering to implement open-set semantic segmentation. Compared to other open-set semantic segmentation methods, our DMLNet achieves state-of-the-art performance on three challenging open-set semantic segmentation datasets without using additional data or generative models. On this basis, two incremental few-shot learning methods are further proposed to progressively improve the DMLNet with the annotations of OOD objects.

Monitoring the state of contact is essential for robotic devices, especially grippers that implement geckoinspired adhesives where intimate contact is crucial for a firm attachment. However, due to the lack of deformable sensors, few have demonstrated tactile sensing for gecko grippers. We present Viko, an adaptive gecko gripper that utilizes vision-based tactile sensors to monitor contact state. The sensor provides high-resolution real-time measurements of contact area and shear force. Moreover, the sensor is adaptive, low-cost, and compact. We integrated gecko-inspired adhesives into the sensor surface without impeding its adaptiveness and performance. Using a robotic arm, we evaluate the performance of the gripper by a series of grasping test. The gripper has a maximum payload of 8N even at a low fingertip pitch angle of 30°. We also showcase the gripper’s ability to adjust fingertip pose for better contact using sensor feedback. Further, everyday object picking is presented as a demonstration of the gripper’s adaptiveness.

Tactile sensing on human feet is crucial for motion control, however, has not been explored in robotic counterparts. This work is dedicated to endowing tactile sensing to legged robot’s feet and showing that a single-legged robot can be stabilized with only tactile sensing signals from its foot. We propose a robot leg with a novel vision-based tactile sensing foot system and implement a processing algorithm to extract contact information for feedback control in stabilizing tasks. A pipeline to convert images of the foot skin into high-level contact information using a deep learning framework is presented. The leg was quantitatively evaluated in a stabilization task on a tilting surface to show that the tactile foot was able to estimate both the surface tilting angle and the foot poses. Feasibility and effectiveness of the tactile system were investigated qualitatively in comparison with conventional single-legged robotic systems using inertia measurement units (IMU). Experiments demon-strate the capability of vision-based tactile sensors in assisting legged robots to maintain stability on unknown terrains and the potential for regulating more complex motions for humanoid robots.

Self-supervised learning for depth estimation possesses several advantages over supervised learning. The benefits of no need for ground-truth depth, online fine-tuning, and better generalization with unlimited data attract researchers to seek self-supervised solutions. In this work, we propose a new self-supervised framework for stereo matching utilizing multiple images captured at aligned camera positions. A cross photometric loss, an uncertainty-aware mutual-supervision loss, and a new smoothness loss are introduced to optimize the network in learning disparity maps end-to-end without ground-truth depth information. To train this framework, we build a new multiscopic dataset consisting of synthetic images rendered by 3D engines and real images captured by real cameras. After being trained with only the synthetic images, our network can perform well in unseen outdoor scenes. Our experiment shows that our model obtains better disparity maps than previous unsupervised methods on the KITTI dataset and is comparable to supervised methods when generalized to unseen data. Our source code and dataset are available at https://sites.google.com/view/multiscopic.

Structures with origami design enable objects to transform into various three-dimensional shapes. Traditionally origami structures are designed with zero-thickness flat paper sheets. However, the thickness and intersection of origami facets are non-negligible in most cases, uniquely when integrating origami design with robotic design because of the more efficient force transfer between thick plates compared with zero-thickness paper-sheets. Meanwhile, the single-layer-paper oriented initial design limited the shape transformation potential as multiple layer origami structures could conduct more variety of deformation. In this article, we are proposing a general design method of parallel-motion thick origami structures that could apply in robotic design like a parallel-motion gripper.

The supercoiled polymer (SCP) actuator is a novel artificial muscle, which is manufactured by twisting and coiling polymer fibers. This new artificial muscle is soft, low-cost and shows good linearity. Being utilized as an actuator, the artificial muscle could generate significant mechanical power in a muscle-like form upon electrical activation by Joule heating. In this study, we adopt this new artificial muscle to actuate a novel designed robotic manipulator, which is composed of two parts. The first part is a robotic arm based on the inspiration of the musculoskeletal system. The arm is fabricated with two ball-and-socket joints as skeleton and SCP actuators as driven muscles. The second part is a Fin Ray Effect inspired soft gripper that can perform grasping tasks on fragile objects. The manipulator prototype is fabricated and experimental tests are conducted including both simple but effective control of the bio-inspired arm as well as characterization of the gripper. Lastly, a pick and place demonstration of a fragile fruit is performed utilizing the proposed manipulator. We envision that the bio-inspired robotic manipulator design driven by SCP actuators could potentially be used in other robotic applications.

The properties and applications of auxetics have been widely explored in the past years. Through proper utilization of auxetic structures, designs with unprecedented mechanical and structural behaviors can be produced. Taking advantage of this, we present the development of novel and low-cost 3D structures inspired by a simple auxetic unit. The core part, which we call the body in this paper, is a 3D realization of 2D rotating squares. This body structure was formed by joining four similar structures through softer material at the vertices. A monolithic structure of this kind is accomplished through a custom-built multi-material 3D printer. The model works in a way that, when torque is applied along the face of the rotational squares, they tend to bend at the vertex of the softer material, and due to the connected-ness of the design, a proper opening and closing motion is achieved. To demonstrate the potential of this part as an important component for robots, two applications are presented: a soft gripper and a crawling robot. Vacuum-driven actuators move both the applications. The proposed gripper combines the benefits of two types of grippers whose fingers are placed parallel and equally spaced to each other, in a single design. This gripper is adaptable to the size of the object and can grasp objects with large and small cross- sections alike. A novel bending actuator, which is made of soft material and bends in curvature when vacuumed, provides the grasping nature of the gripper. Crawling robots, in addition to their versatile nature, provide a better interaction with humans. The designed crawling robot employs negative pressure-driven actuators to highlight linear and turning locomotion.

In this work, we address a planar non-prehensile sorting task. Here, a robot needs to push many densely packed objects belonging to different classes into a configuration where these classes are clearly separated from each other. To achieve this, we propose to employ Monte Carlo tree search equipped with a task-specific heuristic function. We evaluate the algorithm on various simulated and real-world sorting tasks. We observe that the algorithm is capable of reliably sorting large numbers of convex and non-convex objects, as well as convex objects in the presence of immovable obstacles.

The widespread use of fluidic actuation for soft robots creates a high demand for soft pumps and compressors. However, current off-the-shelf pumps are usually rigid, noisy, and cumbersome. As a result, it is hard to integrate most commercial pumps into soft robotic systems, which restricts the autonomy and portability of soft robots. This paper presents the novel design of a soft pump based on bellow structure and super-coiled polymer (SCP) artificial muscles. The pump is flexible, lightweight, modular, scalable, quiet, and low cost. The pumping mechanism and fabrication process of the proposed soft pump is demonstrated. A pump prototype is fabricated to verify the proposed design and characterize its performance. From the characterization results, the pump can reach an output flow rate of up to 54 ml/min and delivers pressure up to 2.63 kPa. The pump has potential applications in untethered soft robots and wearable devices.

Self-supervised learning for visual object tracking possesses valuable advantages compared to supervised learning, such as the non-necessity of laborious human annotations and online training. In this work, we exploit an end-to-end Siamese network in a cycle-consistent self-supervised framework for object tracking. Self-supervision can be performed by taking advantage of the cycle consistency in the forward and backward tracking. To better leverage the end-to-end learning of deep networks, we propose to integrate a Siamese region proposal and mask regression network in our tracking framework so that a fast and more accurate tracker can be learned without the annotation of each frame. The experiments on the VOT dataset for visual object tracking and on the DAVIS dataset for video object segmentation propagation show that our method outperforms prior approaches on both tasks.

This article describes an innovative design of variable stiffness soft actuator, which can potentially be utilized for manipulation and locomotion of soft robots. The new actuator is a combination of two types of actuations: soft pneumatic actuation and muscle-like supercoiled polymer (SCP) actuation. Soft pneumatic actuator has two roles: first is to generate bending motions and second is to increase the stiffness of the whole actuator together with SCP artificial muscles. SCP artificial muscles are exploited to generate pre-load to resist the whole actuator from (excessive) deformation when external load is applied. These two types of actuations are arranged antagonistically to realize stiffness tuning of the whole actuator. At a given bending position, stiffness of the actuator could be tuned by controlling the pressure inside the air chamber and the tension on the SCP artificial muscles. In experimental section, tests are conducted to characterize the applied SCP artificial muscles before they are applied to the proposed actuator. Afterwards, tests of proposed actuator are performed to examine its variable stiffness capability. From experimental results, the proposed actuator can achieve 3.47 times stiffness variation ratio from 0.0312 N/mm(40kPa air pressure and no SCP actuation) to 0.1083 N/mm(82kPa air pressure and SCP actuation at 0.143 W/cm) at the same position (bending angle of 56 degree). This study exhibits the potential of applying SCP artificial muscles to promote the performance of soft robots.

Moving a human body or a large and bulky object may require the strength of whole arm manipulation (WAM). This type of manipulation places the load on the robot's arms and relies on global properties of the interaction to succeed- rather than local contacts such as grasping or non-prehensile pushing. In this paper, we learn to generate motions that enable WAM for holding and transporting of humans in certain rescue or patient care scenarios. We model the task as a reinforcement learning problem in order to provide a robot behavior that can directly respond to external perturbation and human motion. For this, we represent global properties of the robot-human interaction with topology-based coordinates that are computed from arm and torso positions. These coordinates also allow transferring the learned policy to other body shapes and sizes. For training and evaluation, we simulate a dynamic sea rescue scenario and show in quantitative experiments that the policy can solve unseen scenarios with differently-shaped humans, floating humans, or with perception noise. Our qualitative experiments show the subsequent transporting after holding is achieved and we demonstrate that the policy can be directly transferred to a real world setting.

This work presents a novel variable stiffness structure consisting of a fiber-constrained dielectric elastomer tube filled with insulating oil. The tensile stiffness of the structure can be adjusted by voltages and its initial value can be customized according to the initial pre-stretch of the material. The structure has a dimension of ∼30 mm diameter × 50 mm length. A mathematical analysis is established to predict the initial tensile stiffness of the structure. The changes of the tensile stiffness of the structure under voltages are verified experimentally. The results show a decrease of the tensile stiffness of the device by 25% at 4 kV and the decrement is also related to the elongation of the structure. With different pre-stretches and dimensions of the dielectric elastomer, one can obtain devices with different variation ranges of tensile stiffness.

Rearranging objects on a tabletop surface by means of nonprehensile manipulation is a task which requires skillful interaction with the physical world. Usually, this is achieved by precisely modeling physical properties of the objects, robot, and the environment for explicit planning. In contrast, as explicitly modeling the physical environment is not always feasible and involves various uncertainties, we learn a nonprehensile rearrangement strategy with deep reinforcement learning based on only visual feedback. For this, we model the task with rewards and train a deep Q-network. Our potential field-based heuristic exploration strategy reduces the amount of collisions which lead to suboptimal outcomes and we actively balance the training set to avoid bias towards poor examples. Our training process leads to quicker learning and better performance on the task as compared to uniform exploration and standard experience replay. We demonstrate empirical evidence from simulation that our method leads to a success rate of 85%, show that our system can cope with sudden changes of the environment, and compare our performance with human level performance.

Soft actuators play an important role in producing motions in soft robots, and dielectric elastomers have shown great promise because of their considerable voltage-induced deformation. In particular, air-filled dielectric elastomer actuators have been well studied, where the air inside provides prestretches to improve the actuation range. This paper proposes a network of inflated dielectric elastomer actuators, interconnected via a chamber, with the advantages to be highly deformable and continuously controllable. Theoretical analyses show that the networked design is able to largely postpone the occurrence of material failures of the actuators, resulting in a large and continuous actuation range for their control. We further carried out experiments for validation, and the results were largely in line with the theoretical predictions. These findings essentially provide insight into developing networked soft actuators, for achieving large actuation capability.

Soft robots are inherently compliant and adaptive, therefore they are promising candidates for interacting with humans. However robotic manipulators utilizing soft actuators are often constrained by a series of actuator performance limitations. In this work we design a novel linear soft robotic actuator with significantly improved performances over the existing products, achieving 300% deformation ratio, quasi-constant output force over a wide motion range, while maintaining passive compliance and adaptability. Moreover, the novel actuator is less prone to friction, and could be fabricated using inject molding and 3D printing, hence having high repeatability at very low cost. An analytical model was developed to characterize the actuator behavior and provide a guideline for actuator design according to performance specifications. A 6 DOF soft manipulator was designed and fabricated utilizing the novel soft actuator. The manipulator arm had a serial kinematic structure with a biomimetic wrist and was driven by 12 soft actuators mounted onto the arm links. With 1.2m workspace radius and 1kg payload, the working air pressure could be as low as 1bar. Preliminary results have shown the validity of the novel soft actuator and manipulator designs, as well as the strong potential of soft robots in human-oriented applications.

Soft robots, primarily made out of intrinsically soft materials, have flourished greatly in the past decade due to their advantages such as flexibility and adaptability over rigid-bodied robots. A rich repertoire of soft robots designed from intuitive or biomimetic approaches have been developed to provide new solutions for robots. However, these design approaches are limited by the designers' experience and inspiration, and a systematic design methodology for soft robots is still missing. We tackle this issue by mathematically recasting the design problem under the framework of topology optimization problem. To demonstrate the effectiveness of the proposed methodology, in this paper, we develop a pneumatically actuated soft gripper consisting of three fingers, each finger is able to undergo a free travel bending and deliver a grasping force. Hence, each gripper finger is designed as a continuum compliant mechanism to achieve its maximal bending deformation. The proposed soft gripper with complex shape is directly fabricated through 3D printing technology. Experimental results show that the deflected soft finger is able to achieve a 41° free travel bending and generate 0.68N blocked force upon 0.11MPa actuation pressure. This work represents an important step towards the goal of designing soft robots automatically.

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.

This paper presents an algorithm for acquiring high-quality models from multiple calibrated photographs by computing and merging depth maps. The algorithm first computes depth maps from multi-view stereo using a proposed expansion-based approach that returns a 3D point cloud with noisy and redundant information. Then the estimated depth maps are merged into an accurate surface model by a cleaning, downsampling, surface normal estimation and Poisson surface reconstruction process. The proposed approach has been implemented and the experimental results with several real datasets demonstrate that the approach can produce accurate surface models efficiently.

Unlike active force closure, which is a property for the multi-finger robotic hand grasping, passive force closure are involved in the grasping systems with constraining devices that cannot freely control the contact forces, such as the whole-arm grasping and manufacturing fixture. In passive grasping, the contact forces rely on the physical compliance of the system which is usually described by complex contact mechanics models. The purpose of this paper is to study the properties of a type of contact model, the linear elastic contact model, so that it is possible to determine the passive force closure condition and to understand the essential characteristics of the passive grasping. The formula to solve the passive grasping forces is derived. Properties of the passive grasping is studied. The kinematic compatibility equation which describes the requirement of the coordination of contact forces is discovered, which is unique to the passive grasping. The algorithm to find the range of the preload to guarantee the passive force closure is deduced. The algorithm is demonstrated with two examples.

Deformations of contacts between the workpiece and locators/clamps resulting from large contact forces cause overall workpiece displacement, and affect the localization accuracy of the workpiece. An important characteristic of a workpiece-fixture system is that locators are passive elements and can only react to clamping forces and external loads, whereas clamps are active elements and apply a predetermined normal load to the surface of workpiece to prevent it from losing contact with the locators. Clamping forces play an important role in determining the final workpiece quality. This paper presents a general method for determining the optimal clamping forces including their magnitudes and positions. First, we derive a set of “compatibility” equations that describe the relationship between the displacement of the workpiece and the deformations at contacts. Further, we develop a locally elastic contact model to characterize the nonlinear coupling between the contact force and elastic deformation at the individual contact. We define the minimum norm of the elastic deformations at contacts as the objective function, then formulate the problem of determining the optimal clamping forces as a constrained nonlinear programming problem which guarantees that the fixturing of the workpiece is force closure. Using the exterior penalty function method, we transform the constrained nonlinear programming into an unconstrained nonlinear programming which is, in fact, the nonlinear least square. Consequently, the optimal magnitudes and positions of clamping forces are obtained by using the Levenberg–Marquardt method which is globally convergent. The proposed planning method of optimal clamping forces, which may also have an application to other passive, indeterminate problems such as power grasps in robotics, is illustrated with numerical example.

A two-channel bilateral controller is proposed for teleoperation systems, which takes into account both the free space motion and the constrained motion. Specifically, the force-position (F-P) architecture is applied during the constrained motion, while the position-position (P-P) architecture is applied during the free space motion. Perfect transparency can be achieved in theory. In addition, the controller is robust to model uncertainties and disturbances, and it does not need to switch the control modes of the master and the slave controllers during the transition between the free space motion and the constrained motion. Experiments are conducted to demonstrate the effectiveness of the proposed bilateral controller.

Under a whole hand grasp, it may not be possible to generate grasping forces in all directions. Thus, the traditional techniques developed based on fingertip contacts is inadequate. In this paper, we decompose the contact force space into four orthogonal subspaces, each with a clear physical interpretation. Based on linear matrix inequalities (LMI's) representations of grasping constraints, we address and formulate the active force closure and the active grasp feasibility problems as LMI feasibility problems. Combining the effects of both active and passive forces, we propose a new cost index for the whole hand grasping force optimization problem. We further simply the force optimization problem for a whole hand grasp, which is active force closure.

A level set based method is proposed for simultaneous optimization of material property and topology of functionally graded structures. The objective is to determine the optimal material property (via material volume fraction) and structural topology to maximize the performance of the structure in a given application. In the proposed method volume fraction and structural boundary are considered as design variables, with the former being discretized as a scaler field and the latter being implicitly represented by level set method. To perform simultaneous optimization, the two design variables are integrated into a common objective functional. Sensitivity analysis is conducted to obtain the descent directions. The optimization process is then expressed as the solution to a coupled Hamilton-Jacobi equation and diffusion partial differential equation. Numerical results are provided for the problem of mean compliance optimization in two dimensions.

In the basic impedance control structure, it is usually required to know the environment stiffness/impedance for precise force tracking. In addition, the performance may be degraded when the random external disturbances exist. By incorporating a PI-type compensator to the basic impedance control structure, this paper presents a combined impedance/direct control scheme for control of robot manipulators, which is characterized by high disturbance rejection, robustness to uncertainties, and simple structure for application. Moreover, it does not require to switch the control modes during the transition between the free space motion and the constrained motion. Therefore, the proposed controller combines the advantages of both the direct control and the impedance control. Computer simulations are performed to demonstrate the superiority of the proposed control scheme over the impedance control.

A new scheme for 3D reconstruction of implicit surfaces from large scattered point sets based on the radial basis functions (RBFs) is proposed in this paper. The partition of unity (POU) method and a binary tree is used to organize the point sets into some overlapping local subdomains and reconstructing a local surface for each of the subdomains from non-disjunct subsets of the points, we use only a single point at the offset of the surface to avoid the trivial solution of RBF linear system. When the offset point is chosen properly, the technique is not only efficient but also robust, offering a higher level of scalability. The global solution can be obtained by combining the local solutions with POU equations. We also adapt the methodology of level set propagation of a dynamic surface and employ it for smoothing the reconstructed surfaces. We develop versatile computational framework with many benefits in topological flexibility and numerical efficiency.

A mapping algorithm is essential to teleoperate a robot hand. Joint-to-joint mapping, pose mapping and point-to-point mapping are three commonly used methods for telemanipulation. However, these methods might not produce satisfactory performance if the robot hand is non-anthropomorphic. This paper introduces a method for mapping based on the relative positions between fingertips. An algorithm particularly for a three-fingered non-anthropomorphic robot hand is presented. The principle of the method is to find suitable parameters in the hand frame, to transform them to the robot frame, and then to compute the robot fingertip positions according to the transformed parameters. The mapping results and the comparisons with the traditional methods validate the advantages of the proposed method.

A system of rigid bodies with multiple simultaneous unilateral contacts is considered in this paper. The problem is to predict the velocities of the bodies and the frictional forces acting on the simultaneous multicontacts. This paper presents a numerical method based on an extension of an explicit time-stepping scheme and an application of the differential inclusion process introduced by J. J. Moreau. From a differential kinematic analysis of contacts, we derive a set of transfer equations in the velocity-based time-stepping formulation. In applying the Gauss-Seidel iterative scheme, the transfer equations are combined with the Signorini conditions and Coulomb's friction law. The contact forces are properly resolved in each iteration, without resorting to any linearization of the friction cone. The proposed numerical method is illustrated with examples, and its performance is compared with an acceleration-based scheme using linear complementary techniques. Multibody contact systems are broadly involved in many engineering applications. The motivation of this is to solve for the contact forces and body motion for planning the fixture-inserting operation. However, the results of the paper can be generally used in problems involving multibody contacts, such as robotic manipulation, mobile robots, computer graphics and simulation, etc. The paper presents a numerical method based on an extension of an explicit time-stepping scheme, and an application of the differential inclusion process introduced by J. J. Moreau, and compares the numerical results with an acceleration-based scheme with linear complementary techniques. We first describe the mathematical model of contact kinematics of smooth rigid bodies. Then, we present the Gauss-Seidel iterative method for resolving the multiple simultaneous contacts within the time-stepping framework. Finally, numerical examples are given and compared with the previous results of a different approach, which shows that the simulation results of these two methods agree well, and it is also generally more efficient, as it is an explicit method. This paper focuses on the description of the proposed time-stepping and Gauss-Seidel iterations and their numerical implementation, and several theoretical issues are yet to be resolved, like the convergence and uniqueness of the Gauss-Seidel iteration, and the existence and uniqueness of a positive k in solving frictional forces. However, our limited numerical experience has indicated positive answers to these questions. We have always found a single positive root of k and a convergent solution in the Gauss-Seidel iteration for all of our examples.

An investigation was initiated on the study of the kinematic mapping between human hand and the non-anthropomorphic robot hand. To account for the significant dissimilarities between them, a "virtual circle mapping" method has been developed based on the fingertips' relative positions. The principle of the method is to find suitable parameters in the hand frame, transform them to the robot frame, and then compute the robot fingertip positions according to the transformed parameters. The preliminary results and the comparison with the point-to-point mapping results are presented and analyzed. The generalization of the relative-position based mapping idea is also discussed.

A system of rigid bodies with multiple simultaneous contacts is considered in this paper. The problem is to predict the velocities of the bodies and the frictional forces acting on the simultaneous multi-contacts. This paper presents a numerical method based on an extension of an explicit time-stepping scheme and an application of the differential inclusion process introduced by J. J. Moreau. From the differential kinematic analysis of contacts, we derive a set of transfer equations in the velocity based time-stepping formulation. In applying the Gauss-Seidel iterative scheme, the transfer equations are combined with the Signorini conditions and Coulomb's friction law. The contact forces are properly resolved in each iteration, without resorting to any linearization of the friction cone. Numerical examples of the performance of the proposed method are compared with an acceleration-based scheme using linear complementarity techniques.

This paper addresses an optimal planning problem for workpiece localization with coordinate measurements. The fundamental issue is to find the best probing locations and a suitable sampling size, such that the uncertainty of the localization error is within a predefined limited bound. First, we introduce two sequential optimization algorithms to incrementally increase the localization accuracy, defined by the determinant of the information matrix of the measurements. Then, a reliability analysis method is incorporated for finding a sample size that is sufficient to reduce the uncertainty of the localization error to a limited bound. By combining these two analysis tools, we present a near-optimal probing strategy for finding the best probing locations and a suitable sampling size. With this strategy, given the desired translation and orientation error bounds and desired confidence limit, we can experimentally determine the least number of points needed to measure. Simulation and experimental results show the efficiency of the proposed probing strategy.

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.

While the classical notion of force closure is defined for actively controlled and coordinated robotic fingers, passive contacts play an equally important role in workpiece fixturing and often in robotic manipulation. This paper presents a description of passive forces arising at the normal and frictional contacts by passive physical means. The passive contacts generate reactive forces only as a response to an external force and/or any active force. Within the framework of rigid body contact, a contact system with passive forces is generally undeterminate. We present a general approach based on an application of the minimum norm principle. The model reveals some intricate properties of the passive contact forces, including internal forces at the passive and/or active contacts. Some practical implications of the passive nature in fixture design are discussed.

This paper presents an optimal planning problem for workpiece measurement. Two sequential optimization algorithms are introduced to find maximum determinant solutions. Then, based on a reliability analysis of workpiece localization and the sequential optimization algorithms, a computer-aided probing strategy is proposed. With this strategy, given the desired translation and orientation error bounds and desired confidence limit, we can experimentally find the least number of points needed to measure. Simulation results show the efficiency of the computer-aided probing strategy.

In this paper, we propose an approach to design a proper fixture layout for a 3D curved workpiece. The problem is tackled in a point set domain by discretizing the exterior surface of the workpiece into a dense collection of candidate fixturing points and then searching for a small proper set of fixturing points that satisfies the total restraint of the workpiece and reduces the workpiece positioning error. The algorithm first randomly selects an initial set of seven fixturing points and then iteratively improves it by exchanging with the other candidate points through a best-first strategy and a randomized motion. Finally, the algorithm has been implemented and its efficiency has been ascertained by two examples.

In this article an analysis is presented to the problem of characterizing the accuracy of deterministic localization of fixtures. In a statistical framework, the positioning accuracy of the workpiece localized by the locators of a fixture is described by a symmetric, positive-definite accurateness matrix (or variance matrix). The accurateness (variance) matrix is identified to have similar structural properties to the stiffness (compliance) matrix of an unloaded, stable robot grasp. This connection leads us to describe a set of frame-invariant characteristic parameters with geometric interpretation. The principal translational accuratenesses and rotational variances are defined for constructions of frame-invariant quality measures for a meaningful comparison of different locating schemes. An example is presented to illustrate the concept and usefulness of the characterizing properties in optimizing a fixture layout.

The conventional point-kinematic model of fixtures only treats point geometry of the contacts between locators and the workpiece. However, this model, which ignores the underlying surface properties of the locators-plus-workpiece system, is inherently incapable of capturing the effects of the geometric properties important to accurate positioning of the workpiece. In this paper, we present a fixture kinematic analysis based on the full kinematics of locator-workpiece contact. This model incorporates a "virtual" kinematic chain with meshing parameters of contact kinematics in a velocity formulation. Conditions of a deterministic fixture are derived. It is shown that the workpiece position and orientation are completely characterized by the kinematic properties of the locator contacts with the workpiece, including not only the arbitrary locator location errors but also the surface properties at non-prismatic locator-workpiece contacts. This is illustrated with numerical examples. The fixture kinematic analysis developed here has a strong implication for designing fixtures with high locating precision requirements.

In this paper, an analysis is presented of the problem of characterizing the accuracy of deterministic localization of fixtures. In a statistical framework, the positioning accuracy of the workpiece localized by the locators of a fixture is described by a symmetric, positive definite accurateness matrix (or variance matrix). The accurateness (variance) matrix is identified as having similar structural properties to the stiffness (compliance) matrix of an unloaded, stable robot grasp. This connection leads us to describe a set of frame-invariant characteristic parameters with geometric interpretation. The principal translational accuratenesses and rotational variances are defined for constructions of frame-invariant quality measures for a meaningful comparison of different locating schemes. Examples are presented to illustrate the concept and usefulness of the characterizing properties in optimizing a fixture layout.

This paper addresses two major issues in fixture layout design: 1) to determine the feasible fixture configurations that satisfy fundamental requirements suck as kinematic localization and total fixturing (form-closure); and 2) to evaluate the acceptable fixture designs on several quality criteria and select the optimal fixture appropriate with practical demands. The performance objectives considered include the workpiece localization accuracy, and the norm and distribution of the locator contact forces. An efficient automated tool based on an interchange algorithm is developed for designing optimal fixture layout for arbitrary 3D parts. A thorough analysis is performed on the fixture characteristics during the single and multicriteria optimization process for different frequent cases, and on the inter-relationship between locators and clamps, leading to conclusions and strategies for performing fixture synthesis.

Fixtures play an important role in many manufacturing operations such as inspection, machining and part fabrication. In the development of a fixture, it is desired that the feasible fixturing surfaces and optimal fixturing locations on the workpiece be selected automatically. An algorithm is presented to determine optimal fixturing locations which totally restrain the workpart in the fixture without being disturbed by any external force. First, based on observation that form-closure fixturing points exist on a set of surfaces if and only if the convex hull of the vertex contact wrenches resulting from the vertices of the surfaces contains the origin of R/sup 6/, an efficient approach is developed for finding an eligible set of fixturing surfaces. Second, we formulate the problem of determining optimal fixturing points on the eligible set of fixturing surfaces as a quadratic programming (QP) problem with the workpiece positioning accuracy as the performance index and the robust form-closure requirement as the linear constraints. Finally, the implementation for two numerical examples demonstrates the usefulness and efficiency of the proposed algorithm.

Fixtures play an important role in many manufacturing operations such as inspection, machining, and part fabrication. In the development of a fixture, it is desired that the feasible fixturing surfaces and optimal fixturing points on the workpiece be selected automatically. An algorithm is presented to automate the generation of optimal fixturing points, which totally restrains the workpiece in the fixture, i.e., satisfies the form-closure condition, as well as minimizes the workpiece positional errors. First, a heuristics is proposed for searching a set of fixturing surfaces capable of providing form-closure. Then, we formulate the problem of determining optimal fixturing points on the eligible set of fixturing surfaces as a quadratic programming problem with the workpiece positioning accuracy as the performance index and the robust form-closure requirement as the linear constraints. Finally, the implementation for three numerical examples demonstrates the usefulness and efficiency of the proposed algorithm.

This paper describes an approach to optimal design of a fixture layout with the minimum required number of elements, i.e., six locators and a clamp. The approach applies to parts with arbitrary 3D geometry and is restricted to be within a discrete domain of locations for placing the fixture elements of non-frictional contacts. The paper addresses two major issues: 1) to develop an efficient algorithm for fixture synthesis in the point set domain; and 2) to evaluate the acceptable fixture designs based on several performance criteria and to select the optimal fixture according to practical requirements. The performance objectives considered include the workpiece localization accuracy, and the norm and dispersion of the locator contact forces. An interchange algorithm with random initiation is developed. Also, the fixture performance characteristics are evaluated to understand their tradeoffs. The importance of the accurate localization and the contact force balance is discussed.

Addresses two issues in fixture layout design for 3D workpieces: (1) precision workpiece localization and (2) robust force-closure. An analysis is given to quantify these two fundamental requirements. Based on a concept of optimum experiment design, the optimal fixture design problems are treated to select optimal locators and clamps. An interchange algorithm is described, in which the fixture locators are generated sequentially first and are further improved. The algorithms use multiple criteria to balance the demands for precision localization and robust force closure. Examples are presented to illustrate the issues and to show the effectiveness of the proposed approach.

This paper presents a new approach to the problem of fixture layout design for 3D workpieces. The approach is based on a concept of optimum experiment design, and the problem is treated as an optimal aggregation to select optimal locators from an initial collection of a large number of fixel locations on the surfaces of the given workpiece and to achieve form-closure for the part. An interchange algorithm is described, in which the fixture locators are generated sequentially first and are further improved. The algorithm uses the D-optimality criterion to minimize the workpiece positioning error. An example of turbine airfoil is presented to illustrate the effectiveness of the proposed approach.

Factory and facility automation has been widely implemented since the revolution of computers. A variety of automatic material processing machines and material handling equipment have been designed and manufactured for various applications. The facility layout optimization is one of the major tasks in designing automated systems. This paper proposes a generic methodology that provides a systematic way to design an optimal layout for all types of automated facilities. The quantitative design criteria of automatic material processing machines and material handling equipment are addressed first. An optimal connectivity among machines is then solved through topology approach and heuristic algorithm. Thus, an optimized facility layout can be derived and completed by combining the optimal topology connectivity, physical constraints, and designer's preference.

The author treats the problem of collision between a robot end-effector and the manipulated object in robot catching. By applying rigid-body impact mechanics, intermittent dynamics involving a sequence of collisions is modeled by a difference-algebraic system. Through a stability analysis, the author presents open-loop strategies to perform a task using a paddlelike end-effector to catch a circular object in two-dimensional space. Computer simulation results have shown that the strategies are reliable and effective. The generalization of the method to more general robotic manipulation in dynamical environments is also discussed.>