Arbitrary Objects Research Articles

Exploring Arbitrariness Objections to Time Biases

AbstractThere are two kinds of time bias: near bias and future bias. While philosophers typically hold that near bias is rationally impermissible, many hold that future bias is rationally permissible. Call this normative hybridism. According to arbitrariness objections, certain patterns of preference are rationally impermissible because they are arbitrary. While arbitrariness objections have been leveled against both near bias and future bias, the kind of arbitrariness in question has been different. In this article we investigate whether there are forms of arbitrariness that are common to both kinds of preferences and, hence, whether there are versions of the arbitrariness objection that are objections to both near bias and future bias. If there are, then this might go some way toward undermining normative hybridism and to defending thoroughgoing time-neutralism.

A novel framework for predicting active flow control by combining deep reinforcement learning and masked deep neural network

Active flow control (AFC) through deep reinforcement learning (DRL) is computationally demanding. To address this, a masked deep neural network (MDNN), aiming to replace the computational fluid dynamics (CFD) environment, is developed to predict unsteady flow fields under the influence of arbitrary object motion. Then, a novel DRL-MDNN framework that combines the MDNN-based environment with the DRL algorithm is proposed. To validate the reliability of the framework, a blind test in a pulsating baffle system is designed. Vibration damping is considered to be the objective, and a traditional DRL-CFD framework is constructed for comparison. After training, a spatiotemporal evolution of 200 time steps under the influence of arbitrary object motion is predicted by the MDNN. The details of the flow field are compared with the CFD results, and a relative error within 5% is achieved, which satisfies the accuracy of serving as an interactive environment for DRL algorithms. The DRL-MDNN and traditional DRL-CFD frameworks are then applied to the pulsating baffle system to find the optimal control strategy. The results indicate that both frameworks achieve similar control performance, reducing vibration by 90%. Considering the resources expended in establishing the database, the computational resource consumption of the DRL-MDNN framework is reduced by 95%, and the interactive response time during each episode is decreased by 98.84% compared to the traditional DRL-CFD framework.

Detection-Free Object Tracking for Multiple Occluded Targets in Plenoptic Video

Multiple object tracking (MOT) is a fundamental task in vision, but MOT techniques for plenoptic video are scarce. Almost all 2D MOT algorithms that show high performance mostly use the detection-based method which has the disadvantage of operating only for a specific object. To enable tracking of arbitrary desired objects, this paper introduces a groundbreaking detection-free tracking method for MOT in plenoptic videos. The proposed method deviates from traditional detection-based tracking methods, emphasizing the challenges of tracking targets with occlusions. The paper presents specialized algorithms that exploit the multifocal information of plenoptic video, including the focal range restriction and dynamic focal range adjustment schemes to secure robustness for occluded object tracking. To the improvement of the spatial searching capability, the anchor ensemble and the dynamic change of spatial search region algorithms are also proposed. Additionally, in terms of MOT, to reduce the computation time involved, the motion-adaptive time scheduling technique is proposed, which improves computation speed while guaranteeing a certain level of accuracy. Experimental results show a significant improvement in tracking performance, with a 77% success rate based on intersection over union for occluded targets in plenoptic videos, marking a substantial advancement in the field of plenoptic object tracking.

Filtering with relational similarity

For decades, the success of the similarity search has been based on detailed quantifications of pairwise similarities of objects. Currently, the search features have become much more precise but also bulkier, and the similarity computations are more time-consuming. We show that nearly no precise similarity quantifications are needed to evaluate the k nearest neighbours (kNN) queries that dominate real-life applications. Based on the well-known fact that a selection of the most similar alternative out of several options is a much easier task than deciding the absolute similarity scores, we propose the search based on an epistemologically simpler concept of relational similarity. Having arbitrary objects q,o1,o2 from the search domain, the kNN search is solvable just by the ability to choose the more similar object to q out of o1,o2. To support the filtering efficiency, we also consider a neutral option, i.e., equal similarities of q,o1 and q,o2. We formalise such concept and discuss its advantages with respect to similarity quantifications, namely the efficiency, robustness and scalability with respect to the dataset size. Our pioneering implementation of the relational similarity search for the Euclidean and Cosine spaces demonstrates robust filtering power and efficiency compared to several contemporary techniques.

Controllable Video Generation With Text-Based Instructions

Most of the existing studies on controllable video generation either transfer disentangled motion to an appearance without detailed control over motion or generate videos of simple actions such as the movement of arbitrary objects conditioned on a control signal from users. In this study, we introduce Controllable Video Generation with text-based Instructions (CVGI) framework that allows text-based control over action performed on a video. CVGI generates videos where hands interact with objects to perform the desired action by generating hand motions with detailed control through text-based instruction from users. By incorporating the motion estimation layer, we divide the task into two sub-tasks: (1) control signal estimation and (2) action generation. In control signal estimation, an encoder models actions as a set of simple motions by estimating low-level control signals for text-based instructions with given initial frames. In action generation, generative adversarial networks (GANs) generate realistic hand-based action videos as a combination of hand motions conditioned on the estimated low control level signal. Evaluations on several datasets (EPIC-Kitchens-55, BAIR robot pushing, and Atari Breakout) show the effectiveness of CVGI in generating realistic videos and in the control over actions.

TossNet: Learning to Accurately Measure and Predict Robot Throwing of Arbitrary Objects In Real Time With Proprioceptive Sensing

TossNet: Learning to Accurately Measure and Predict Robot Throwing of Arbitrary Objects In Real Time With Proprioceptive Sensing

Isomorphic Mesh Generation from Point Clouds with Multilayer Perceptrons.

A novel neural network called the isomorphic mesh generator (iMG) is proposed to generate isomorphic meshes from point clouds containing noise and missing parts. Isomorphic meshes of arbitrary objects exhibit a unified mesh structure, despite objects belonging to different classes. This unified representation enables various modern deep neural networks (DNNs) to easily handle surface models without requiring additional pre-processing. Additionally, the unified mesh structure of isomorphic meshes enables the application of the same process to all isomorphic meshes, unlike general mesh models, where processes need to be tailored depending on their mesh structures. Therefore, the use of isomorphic meshes can ensure efficient memory usage and reduce calculation time. Apart from the point cloud of the target object used as input for the iMG, point clouds and mesh models need not be prepared in advance as training data because the iMG is a data-free method. Furthermore, the iMG outputs an isomorphic mesh obtained by mapping a reference mesh to a given input point cloud. To stably estimate the mapping function, a step-by-step mapping strategy is introduced. This strategy enables flexible deformation while simultaneously maintaining the structure of the reference mesh. Simulations and experiments conducted using a mobile phone have confirmed that the iMG reliably generates isomorphic meshes of given objects, even when the input point cloud includes noise and missing parts.

Correction to: Boolean-Valued Sets as Arbitrary Objects

Correction to: Boolean-Valued Sets as Arbitrary Objects

Cooperative object transportation with differential-drive mobile robots: Control and experimentation

Non-prehensile cooperative object transportation is a challenging model problem for distributed control and organization methods but also has practical applications. Therefore, it is widely studied in distributed robotics research. This paper describes and evaluates a novel transportation scheme for differential-drive mobile robots that is, to the authors’ best knowledge, the most versatile scheme of its kind successfully evaluated with real-world hardware. The proposed scheme can conceptually deal with any number of robots and arbitrary polygonal objects, including non-convex ones, without having to retune, retrain, or reconfigure any of the control parameters between different scenarios. This is achieved by splitting the task into a formation control and a formation finding task, both of which are tackled with model-based approaches using distributed optimization. Formation control and formation finding are complicated by the robots’ non-holonomic kinematic constraints. Therefore, a tailored distributed model predictive controller is used for formation control. Finding formations relies on a multibody-dynamics representation of the robots-object system to properly account for contact and non-holonomic constraints. Due to these measures, the transportation scheme achieves a very satisfactory performance and dexterity in real-world hardware experiments utilizing network communication and distributed computation.

Human image animation via semantic guidance

Image animation creates visually compelling effects by animating still source images according to driving videos. Recent work performs animation on arbitrary objects using unsupervised methods and can relatively robustly perform motion transfer on human bodies. However, the complex representation of motion and unknown correspondence between human bodies often lead to issues such as distorted limbs and missing semantics, which make human animation challenging. In this paper, we propose a semantically guided, unsupervised method of motion transfer, which uses semantic information to model motion and appearance. Specifically, we use a pre-trained human parsing network to encode the rich and diverse foreground semantic information, thus generating fine details. Secondly, we use a cross-modal attention layer to learn the semantic region’s correspondence between human bodies to guide the network in selecting appropriate input features, prompting the network to generate accurate results. Experiments demonstrate that our method outperforms state-of-the-art methods in motion-related metrics, while effectively addressing the problems of semantic missing and unclear limb structures prevalent in human motion transfer. These improvements can facilitate its applications in various fields, such as education and entertainment.

METHODS OF TRACKING AN ARBITRARY NUMBER OF OBJECTS IN REAL-TIME ON A MOBILE PLATFORM

The problem of choosing methods for tracking recognized objects in real-time for systems with limited hardware capabilities is considered. It was determined that for such scenarios, it is appropriate to integrate tracking methods into the device, bypassing data transmission via the Internet. Existing methods of tracking an arbitrary number of objects in real-time are considered. Among the performance evaluation metrics, the following were used: MOTA, MOTP, F1, MT, ML, ID, and FM. Based on the primary analysis of the effectiveness of such methods according to the metrics mentioned above, it was proposed to use the V-IOU tracking method to track recognized objects on a mobile platform in a mobile cyber-physical system. Key words: V-IOU, Arbitrary Object Class Tracking, Mobile Platform, Real-Time, MOTA, MOTP, Cyber-Physical System.

Advances in nonlinear metasurfaces for imaging, quantum, and sensing applications

Abstract Metasurfaces, composed of artificial meta-atoms of subwavelength size, can support strong light–matter interaction based on multipolar resonances and plasmonics, hence offering the great capability of empowering nonlinear generation. Recently, owing to their ability to manipulate the amplitude and phase of the nonlinear emission in the subwavelength scale, metasurfaces have been recognized as ultra-compact, flat optical components for a vast range of applications, including nonlinear imaging, quantum light sources, and ultrasensitive sensing. This review focuses on the recent progress on nonlinear metasurfaces for those applications. The principles and advances of metasurfaces-based techniques for image generation, including image encoding, holography, and metalens, are investigated and presented. Additionally, the overview and development of spontaneous photon pair generation from metasurfaces are demonstrated and discussed, focusing on the aspects of photon pair generation rate and entanglement of photon pairs. The recent blossoming of the nonlinear metasurfaces field has triggered growing interest to explore its ability to efficiently up-convert infrared images of arbitrary objects to visible images and achieve spontaneous parametric down-conversion. This recently emerged direction holds promising potential for the next-generation technology in night-vision, quantum computing, and biosensing fields.

Pose Estimation of Point Sets Using Residual MLP in Intelligent Transportation Infrastructure

6D pose estimation of arbitrary objects is a crucial topic for intelligent transportation infrastructure measurement. However, some external environmental factors and the characteristics of the object itself impact the accuracy of the object’s pose estimation in practical applications. In this paper, we propose a new multi-class dataset ICD-4 (Industrial car Components Dataset) for 6D object pose estimation, which mainly includes four component categories, and every category takes 20,000 different scenarios. ICD-4 dataset delivers quite a few research challenges involving the range of object pose transformations and has significant research value for small-scale pose estimation tasks. We also propose an innovative method PoseMLP, a pose estimation network that uses residual MLP (multilayer perceptron) modules to predict the 6D pose estimation directly. Simultaneously, the experimental results demonstrate the effectiveness and reliability of the proposed method.

DSMC Evaluation Stages: Fostering Robust and Safe Behavior in Deep Reinforcement Learning – Extended Version

Neural networks (NN) are gaining importance in sequential decision-making. Deep reinforcement learning (DRL), in particular, is extremely successful in learning action policies in complex and dynamic environments. Despite this success, however, DRL technology is not without its failures, especially in safety-critical applications: (i) the training objective maximizes average rewards, which may disregard rare but critical situations and hence lack local robustness; (ii) optimization objectives targeting safety typically yield degenerated reward structures, which, for DRL to work, must be replaced with proxy objectives. Here, we introduce a methodology that can help to address both deficiencies. We incorporate evaluation stages (ES) into DRL, leveraging recent work on deep statistical model checking (DSMC), which verifies NN policies in Markov decision processes. Our ES apply DSMC at regular intervals to determine state space regions with weak performance. We adapt the subsequent DRL training priorities based on the outcome, (i) focusing DRL on critical situations and (ii) allowing to foster arbitrary objectives. We run case studies on two benchmarks. One of them is the Racetrack, an abstraction of autonomous driving that requires navigating a map without crashing into a wall. The other is MiniGrid, a widely used benchmark in the AI community. Our results show that DSMC-based ES can significantly improve both (i) and (ii).

Filter-based solutions for finite and infinite edge diffraction

Sound diffraction occurs at (building) corners, objects and openings, prominently affecting occluded and reflected sounds. Here, a physically-based, parametric filter model for diffraction at arbitrary wedges is presented. The model connects existing high-frequency asymptotic and exact solutions in geometrical acoustics using up to four half-order low-pass filters. Compact expressions for the transfer function and impulse response of the singly diffracted field are derived, with errors below 0.1 dB. A filter modification is suggested to account for the exact solution at low frequencies. The filter solution is further simplified to approximate the spectral effects of diffraction from finite wedges and objects composed thereof, referred to as universal diffraction filter approximation (UDFA). A computationally highly-efficient recursive filter implementation is presented and it is demonstrated that diffraction from flat finite objects like plates or apertures can be closely approximated. To account for effects of higher-order diffraction at the object, a heuristic filter extension is suggested. The presented filter-based diffraction solution is suited for the prediction and simulation of sound propagation including non-specular reflections in architectural acoustics. For virtual acoustics, UDFA provides an efficient and accurate approximation of edge diffraction to account for perceptually relevant frequency-dependent attenuation, extendable to arbitrary objects.

Optimized Packing of 3D Objects Bounded by Spherical and Conical Surfaces

Introduction. Optimizing the packing of arbitrary geometric objects in additive manufacturing opens up new possibilities for increasing the efficiency of additive manufacturing of parts of a complex configuration due to the saving of energy, material and time resources. Additive manufacturing, a cornerstone in fields such as space engineering, medicine, mechanical engineering, and energy, has its efficiency hinging on the optimization of the 3D printing process. Given its widespread application, refining this process is of utmost importance. The purpose of the paper. The paper aims to develop an approach for packing assembled parts of complex geometry in the working area of a 3D printer, while adhering to the standards of 3D printing. Results. For the analytical description of the complex shaped industrial products, a, so called, “composed spherical cone” is used. This generates a family of such objects as spheres, cylinders, spherical cylinders, cones, truncated cones and spherical discs. Using the normalized quasi-phi-function of composed spherical cones, a mathematical model of the problem is presented in the form of a nonlinear programming problem. A solution strategy is developed, encompassing three primary stages: generation of feasible starting points, search of local minima and search of a better local minimum. Numerical examples of packing various industrial products in a 3D printer chamber is provided. 3D-parts are approximated by composed spherical cones with different metric parameters. Conclusions. The conducted numerical simulation confirms the effectiveness of the proposed optimization approach. This study emphasizes the importance of further research and innovation in the field of 3D printing and its optimization, and also demonstrates the potential of using mathematical models to solve practical problems in a production environment. Keywords: packing, assembled spherical cone, mathematical modeling, optimization, additive manufacturing.

A review of robotic grasp detection technology

AbstractIn order to complete many complex operations and attain more general-purpose utility, robotic grasp is a necessary skill to master. As the most common essential action of robots in factory and daily life environments, robotic autonomous grasping has a wide range of application prospects and has received much attention from researchers in the past decade. However, the accurate grasp of arbitrary objects in unstructured environments is still a research challenge that has not yet been completely overcome. A complete robotic grasp system usually involves three aspects: grasp detection, grasp planning, and control subsystem. As the first step, identifying the location of the object and generating the grasp pose is the premise of successful grasp, which is conducive to planning the subsequent grasp path and the realization of the entire grasp action. Therefore, this paper conducts a literature review focusing on grasp detection technology and concludes two significant aspects: the analytic and data-driven methods. According to the previous grasp experience of the target object, this paper divides the data-driven methods into the grasp of known and unknown objects. Then it describes in detail the typical grasp detection methods and related characteristics of each classification in the grasp of unknown objects. Finally, current research status and potential research directions in this field are discussed to provide some reference for related research.

Fluctuations of the energy density and intensity for arbitrary objects in an arbitrary environment

Fluctuations of the energy density and intensity for arbitrary objects in an arbitrary environment

Boolean-Valued Sets as Arbitrary Objects

Abstract This article explores the connection between Boolean-valued class models of set theory and the theory of arbitrary objects in roughly Kit Fine’s sense of the word. In particular, it explores the hypothesis that the set-theoretic universe as a whole can be seen as an arbitrary entity. According to this view, the set-theoretic universe can be in many different states. These states are structurally like Boolean-valued models, and they contain sets conceived of as variable or arbitrary objects.

Design optimization of soft robotic fingers biologically inspired by the fin ray effect with intrinsic force sensing

Soft grippers display adaptability, dexterity, and safety, garnering increased interest in their applications. However, accurately modeling their nonlinear deformation and sensing the grasping force remain challenging. Here, a generalized closed-form kinetostatic model of a biomimetic FRE soft finger is established based on the chained-beam-constraint model. A methodology combining a geometry-based contact constraint technique is presented, utilizing the minimum strain energy principle for sensorless, precise, and rapid estimation of the deformed contours and contact force when the FRE finger grasps an arbitrary object with a continuous surface. Method verification using FEA demonstrates a maximum error of no more than 1.28% and 2.44% for the contour and contact force estimation, respectively. Subsequently, a multiobjective genetic algorithm is used to optimize the FRE finger design for better adaptability and greater grasping force in a special scenario. Finally, the finger's capability to accurately perceive grasping force and deformed contours was demonstrated by four groups of grasping tests using cylinder and cube objects, with maximum average absolute error and relative error of 0.083 N, 9.84%, and 1.335 mm, 10.06%, respectively.