Explicit Constraints Research Articles

Experienced Deep Reinforcement Learning With Generative Adversarial Networks (GANs) for Model-Free Ultra Reliable Low Latency Communication

In this paper, a novel experienced deep reinforcement learning (deep-RL) framework is proposed to provide model-free resource allocation for ultra reliable low latency communication (URLLC-6G) in the downlink of a wireless network. The goal is to guarantee high end-to-end reliability and low end-to-end latency, under explicit data rate constraints, for each wireless user without any models of or assumptions on the users' traffic. In particular, in order to enable the deep-RL framework to account for extreme network conditions and operate in highly reliable systems, a new approach based on generative adversarial networks (GANs) is proposed. This GAN approach is used to pre-train the deep-RL framework using a mix of real and synthetic data, thus creating an experienced deep-RL framework that has been exposed to a broad range of network conditions. The proposed deep-RL framework is particularly applied to a multi-user orthogonal frequency division multiple access (OFDMA) resource allocation system. Formally, this URLLC-6G resource allocation problem in OFDMA systems is posed as a power minimization problem under reliability, latency, and rate constraints. To solve this problem using experienced deep-RL, first, the rate of each user is determined. Then, these rates are mapped to the resource block and power allocation vectors of the studied wireless system. Finally, the end-to-end reliability and latency of each user are used as feedback to the deep-RL framework. It is then shown that at the fixed-point of the deep-RL algorithm, the reliability and latency of the users are near-optimal. Moreover, for the proposed GAN approach, a theoretical limit for the generator output is analytically derived. Simulation results show how the proposed approach can achieve near-optimal performance within the rate-reliability-latency region, depending on the network and service requirements. The results also show that the proposed experienced deep-RL framework is able to remove the transient training time that makes conventional deep-RL methods unsuitable for URLLC-6G. Moreover, during extreme conditions, it is shown that the proposed, experienced deep-RL agent can recover instantly while a conventional deep-RL agent takes several epochs to adapt to new extreme conditions.

Autonomous Navigation Framework for Intelligent Robots Based on a Semantic Environment Modeling

Humans have an innate ability of environment modeling, perception, and planning while simultaneously performing tasks. However, it is still a challenging problem in the study of robotic cognition. We address this issue by proposing a neuro-inspired cognitive navigation framework, which is composed of three major components: semantic modeling framework (SMF), semantic information processing (SIP) module, and semantic autonomous navigation (SAN) module to enable the robot to perform cognitive tasks. The SMF creates an environment database using Triplet Ontological Semantic Model (TOSM) and builds semantic models of the environment. The environment maps from these semantic models are generated in an on-demand database and downloaded in SIP and SAN modules when required to by the robot. The SIP module contains active environment perception components for recognition and localization. It also feeds relevant perception information to behavior planner for safely performing the task. The SAN module uses a behavior planner that is connected with a knowledge base and behavior database for querying during action planning and execution. The main contributions of our work are the development of the TOSM, integration of SMF, SIP, and SAN modules in one single framework, and interaction between these components based on the findings of cognitive science. We deploy our cognitive navigation framework on a mobile robot platform, considering implicit and explicit constraints for autonomous robot navigation in a real-world environment. The robotic experiments demonstrate the validity of our proposed framework.

On topology optimization with elliptical masks and honeycomb tessellation with explicit length scale constraints

Topology optimization using gradient search with negative and positive elliptical masks and honeycomb tessellation is presented. Through a novel skeletonization algorithm for topologies defined using filled and void hexagonal cells/elements, explicit minimum and maximum length scales are imposed on solid states in the solutions. An analytical example is presented suggesting that for a skeletonized topology, optimal solutions may not always exist for any specified volume fraction, minimum and maximum length scales, and that there may exist implicit interdependence between them. A sequence for length scale (SLS) methodology is proposed wherein solutions are sought by specifying only the minimum and maximum length scales with volume fraction getting determined within a specified range systematically. Through four benchmark problems in small deformation topology optimization, it is demonstrated that solutions by-and-large satisfy the length scale constraints though the latter may get violated at certain local sites. The proposed approach seems promising, noting especially that solutions, if rendered perfectly black and white with minimum length scale explicitly imposed and boundaries smoothened, are quite close in performance compared with the parent topologies. Attaining volume-distributed topologies, wherein members are more or less of the same thickness, may also be possible with the proposed approach.

CUSTOMER SPECIFIC COMPATIBILITY MATRICES FOR FUNCTIONAL INTEGRAL PRODUCT ARCHITECTURES

AbstractSupplier of system components face the challenge of customer requirements influencing the property level functional integral product architectures. For this, solution approaches focusing on the re-use of pre-engineered part variants are not applicable. However, to generate a valid product structure, customer-specific properties have to fit modelled product knowledge. Therefore, the approach models a reference class structure and analysis compatibilities on the property level for customer specific inputs concerning explicit product knowledge and constraints.

Udwadia–Kalaba constraint-based tracking control for artificial swarm mechanical systems: dynamic approach

A novel swarm tracking control for artificial swarm mechanical systems consisting of multiple mechanical agents is proposed. In this paper, the agents could not only perform some biological swarm behaviors, such as the repulsion and attraction between agents, but also track the moving target or desired trajectory together. Based on the artificial potential functions, the kinematic modeling of each agent is constructed. The kinematic performance of the swarm system is analyzed, which includes convergence, tracking, aggregation and formation. Inspired by Udwadia–Kalaba constraints, the kinematic modeling of the swarm system is treated as servo constraints and formulated in the second-order form. With the second-order constraints, the explicit servo constraint forces are derived. In virtue of the constraint forces in the closed form, we creatively design a dynamic control for each agent which guarantees the controlled swarm system to obey the required motion. The proposed control scheme is proved by a series of theorems and illustrated by the simulation of multiple nonholonomic mobile robots.

SG-Net: Syntax-Guided Machine Reading Comprehension

For machine reading comprehension, the capacity of effectively modeling the linguistic knowledge from the detail-riddled and lengthy passages and getting ride of the noises is essential to improve its performance. Traditional attentive models attend to all words without explicit constraint, which results in inaccurate concentration on some dispensable words. In this work, we propose using syntax to guide the text modeling by incorporating explicit syntactic constraints into attention mechanism for better linguistically motivated word representations. In detail, for self-attention network (SAN) sponsored Transformer-based encoder, we introduce syntactic dependency of interest (SDOI) design into the SAN to form an SDOI-SAN with syntax-guided self-attention. Syntax-guided network (SG-Net) is then composed of this extra SDOI-SAN and the SAN from the original Transformer encoder through a dual contextual architecture for better linguistics inspired representation. To verify its effectiveness, the proposed SG-Net is applied to typical pre-trained language model BERT which is right based on a Transformer encoder. Extensive experiments on popular benchmarks including SQuAD 2.0 and RACE show that the proposed SG-Net design helps achieve substantial performance improvement over strong baselines.

Optimization of the internal damping rubber elements of the small diameter roller wheel of tracked system

The article presents the formulation and solution of the problem of optimization of the internal damping rubber elements of the small diameter roller wheel of tracked system. The search for the optimal design is based on the results of calculating the stress-strain state of the rubber element caused by the assembly of the roller and loads during subsequent operation. As an objective function, the specific energy of deformation of the rubber was chosen. The geometric parameters of the rubber element of the roller wheel in the initial state and after installation in the structure are taken as variable parameters. Explicit and functional constraints in the form of inequations are imposed on the variable parameters. The results of solving the optimal design problem are presented.

Semantically Smooth Bilingual Phrase Embeddings Based on Recursive Autoencoders

In this paper, we propose Semantically Smooth Bilingual Recursive Autoencoders to learn bilingual phrase embeddings. The intuition behind our work is to exploit the intrinsic geometric structure of the embedding space and enforce the learned phrase embeddings to be semantically smooth. Specifically, we extend the conventional bilingual recursive autoencoders by preserving the translation and paraphrase probability distributions via regularization terms to simultaneously exploit richer explicit and implicit similarity constraints for bilingual phrase embeddings. To examine the effectiveness of our model, we incorporate two phrase-level similarity features based on the proposed model into a state-of-the-art phrase-based statistical machine translation system. Experiments on NIST Chinese–English test sets show that our model achieves substantial improvements over the baseline.

Human-Inspired Representation of Object-Specific Grasps for Anthropomorphic Hands

The human hand is a complex, highly-articulated system, which has been the source of inspiration in designing humanoid robotic and prosthetic hands. Understanding the functionality of the human hand is crucial for the design, efficient control and transfer of human versatility and dexterity to such anthropomorphic robotic hands. Although research in this area has made significant advances, the synthesis of grasp configurations, based on observed human grasping data, is still an unsolved and challenging task. In this work we derive a novel, constrained autoencoder model, that encodes human grasping data in a compact representation. This representation encodes both the grasp type in a three-dimensional latent space and the object size as an explicit parameter constraint allowing the direct synthesis of object-specific grasps. We train the model on 2250 grasps generated by 15 subjects using 35 diverse objects from the KIT and YCB object sets. In the evaluation we show that the synthesized grasp configurations are human-like and have a high probability of success under pose uncertainty.

A Subspace Approach to Sparse Sampling Based Data Gathering in Wireless Sensor Networks

Data gathering is an essential concern in Wireless Sensor Networks (WSNs). This paper proposes an efficient data gathering method in clustered WSNs based on sparse sampling to reduce energy consumption and prolong the network lifetime. For data gathering scheme, we propose a method that can collect sparse sampled data in each time slot with a fixed percent of nodes remaining in sleep mode. For data reconstruction, a subspace approach is proposed to enforce an explicit low-rank constraint for data reconstruction from sparse sampled data. Subspace representing spatial distributions of the WSNs data can be estimated from previous reconstructed data. Incorporating total variation constraint, the proposed reconstruction method reconstructs current time slot data efficiently. The results of experiments indicate that the proposed method can reduce the energy consumption and prolong the network lifetime with satisfying recovery accuracy.

Evaluating profitability of soil-renovation investments under crop rotation constraints in Finland

Increasing the resource use efficiency of agricultural production is considered as a central element in Sustainable Intensification (SI) of agriculture, which is a promising strategy to satisfy increasing demand for food while reducing negative impacts on farm economy and environment. One challenge for SI is that degradation of agricultural soils and resulting crop yield losses are affecting negatively farmers' incomes and environment. This study analyses economic profitability of soil renovation investments aimed for tackling soil compaction in a regional context of south-west Finland, where some individual land parcels are compacted on many farms, implying crop yield losses, which we assume as −30%. We use a dynamic optimisation farm model with multiple input-use responses on crop yields. Explicit field parcel-specific crop-rotation constraints are accounted for in solving the farmers' decision problem of soil-renovation investments. Our results calculated over a 30 year time period suggest that soil-renovation investments are profitable since they produce a positive net present value (NPV) assuming 2000–2014 average crop prices, at all discount rates up to 10% when 30% yield decrease due to soil compaction is assumed. Higher than average crop prices would increase the value of soil renovation investment significantly while lower than average future crop prices would have a relatively small effect on the profitability of soil-renovation investment. The payback times of soil-renovation investments are approximately 8–11 years, depending on the discount rate, but largely independent on crop prices. Soil renovation increases production of higher valued crops, but the utilisation of the whole production potential of a farm is dependent on crop prices. We found that the full increased production potential may not be utilized after the renovation investment if not utilized already without the investment. It is concluded that one may recommend soil-renovation investments as a profitable long-term investment in a typical case, but one cannot recommend the soil renovation if no significant yield gains are possible, or if only low valued crop are to be produced. Nevertheless the field parcel-specific restrictions to avoid soil compaction after the renovation are important to be accounted for in evaluating the profitability of soil renovation at the farm level, since avoiding soil compaction is one part of more sustainable production strategy.

Timetabling for Strategic Passenger Railway Planning

In research and practice, public transportation planning is executed in a series of steps, which are often divided into the strategic, the tactical, and the operational planning phase. Timetables are normally designed in the tactical phase, taking into account a given line plan, safety restrictions arising from infrastructural constraints, as well as regularity requirements and bounds on transfer times. In this paper, however, we propose a timetabling approach that is aimed at decision making in the strategic phase of public transportation planning and to determine an outline of a timetable that is good from the passengers’ perspective. Instead of including explicit synchronization constraints between train runs (as most timetabling models do), we include the adaption time (waiting time at the origin station) in the objective function to ensure regular connections between passengers’ origins and destinations. We model the problem as a mixed integer quadratic program and linearise it. Furthermore we propose a heuristic to generate starting solutions. We illustrate the type of solutions found by our approach on two case studies based on the Dutch railway network and analyse trade-offs that are made to balance dwell times and regularity of trains.

Laplacian Regularized Nonnegative Representation for Clustering and Dimensionality Reduction

Self-representation methods, such as low-rank representation (LRR), sparse subspace clustering (SSC) and their variants may generate negative coding coefficients since there is no explicit nonnegative constraint. These negative coefficients lack physical meaning. To be specific, it is unreasonable to allow a query sample encoded by heterogeneous samples to cancel each other out with subtractions. In this paper, we propose a novel model named Laplacian regularized nonnegative representation (LapNR). The new model improves its physical interpretability by ensuring that the query sample should be approximated from homogeneous samples and irrelevant to heterogeneous ones. More importantly, it captures the geometric information of input data by imposing the graph Laplacian to the nonnegative representations. As a result, the representation matrix generated by our LapNR model becomes sparse and discriminative. Based on the alternating direction method of multipliers (ADMM), an efficient optimization procedure is developed for LapNR. The extensive experiments on clustering and dimensionality reduction tasks show the effectiveness and efficiency of our LapNR.

Unit cell consistency of maximally localized Wannier functions

Unit cell consistency (UCC) means that the physical properties or quantities of solids resulted from electronic structure calculations should not depend on the specific choice of the unit cell. The UCC of maximally localized wannier functions (MLWFs), a family of localized orbitals that are very useful in the theoretical characterization of solids, has scarcely been studied. In this work, we explore both analytically and numerically the UCC of MLWFs, and propose an explicit symmetry constraint on the unitary transformation matrices to ensure the UCC is rigorously preserved. Numerical calculations also demonstrate that without the symmetry constraint the MLWFs constructed in a supercell model may violate the UCC. This work thus provides useful guidance for the use of MLWFs in sophisticated solid-state systems and applications.

Travel times in quasi-dynamic traffic assignment

ABSTRACT By extending static traffic assignment with explicit capacity constraints, quasi-dynamic traffic assignment yields more realistic results while avoiding many disadvantages of a dynamic assignment. We analyse the computation of travel times in quasi-dynamic assignment models. We formulate and check requirements for the correctness of resulting travel times, addressing both the calculation of travel times for individual routes and links itself, as well as the differences between travel times of different travel choices. We demonstrate that existing approaches for travel time computation in the literature fail to satisfy all requirements and derive a new link travel time formula from the vertical queuing theory that does meet all requirements. We discuss expected changes to assignment results and methodological advantages for pathfinding and model extensions, including horizontal queuing. The new link travel time formulation is finally applied to three example scenarios from literature.

Cascaded Nonlinear MPC for Realtime Quadrotor Position Tracking

In this paper we present a cascaded control approach using nonlinear model-predictive controllers for both stages. Using a quadrotor platform as an exemplary target plant with fast nonlinear dynamics, a realtime capable design is proposed that does not require the plant dynamics to exhibit clearly separable time constants as in classical cascaded control. In contrast to similar work we employ NMPC for the inner control loop instead of classical control approaches such as PID control, allowing to keep predictive properties as well as explicit constraint handling. We demonstrate via Monte-Carlo simulations that our design is able to achieve a significantly better position tracking performance of the quadrotor while being equally computationally expensive compared to monolithic position tracking NMPC.

Robust Object Tracking with Continuous Data Association based on Artificial Potential Moving Horizon Estimation

Abstract In this paper, a novel object tracking method based on moving horizon estimation (MHE) is introduced that integrates data association into numerical optimization on Bayesian state estimation. Object tracking is a classical problem that often appears in radar and vision systems for which either deterministic or probabilistic approach has been applied. While the former often encounter a failure of association, the latter avoids it by computing the expectation concerning the observations, but it requires the prior knowledge of the probabilistic distribution and may suffer from outliers. In this paper, a partially deterministic approach is built on MHE to resolve these concerns. Data association is realized by a potential function comprising the superposition of Gaussian distributions centered at each observed feature. The potential function is embedded into the stage cost of MHE; the optimal data association is conducted using the sequence of observations within the horizon. Thus robust object tracking is achieved utilizing multi-sampling data and integration of both dynamics and explicit constraints reflecting physical limitations. The advantage of the proposed method is verified through object tracking experiments on the crowded environment, where occlusion and misrecognition frequently occur.

Nonlinear Model Predictive Control for Heavy-Duty Hybrid Electric Vehicles Using Random Power Prediction Method

A primary challenge to the implementation of hybrid electric vehicles (HEVs) is the design of the energy management strategy for the vehicle. Most conventional strategies have been designed for passenger vehicles using rule-based or optimization-based control strategies that rely on navigation support; therefore, the optimal performance of heavy-duty HEVs that lack navigation support cannot be achieved using conventional strategies. In this study, we propose a nonlinear model predictive control (NMPC) for heavy-duty HEVs based on a random power prediction method. To obtain the models of multiple power sources, we analyzed the structure and powertrain of the vehicle using mathematical modeling methods. To account for the lack of navigation support, we used the data-driven prediction method by combining the grey model and Markov chain methods to obtain higher-accuracy ultra-short-term power prediction. Considering the predicted disturbance power, we established a multi-objective optimization function with explicit constraints to optimize fuel consumption, bus voltage, and battery state of charge. Under these constraints, a nonlinear programming problem based on the NMPC could be restricted to find an optimal numerical solution in real time. We validated the control strategy on a hardware-in-the-loop simulation platform and compared its results with those obtained using thermostat control, fuzzy, and dynamic programming approaches. The proposed control strategy achieved a considerably better all-round performance than rule-based control strategies; moreover, the results were considerably similar compared with those of offline global optimization strategies. Furthermore, the proposed method achieved excellent real-time operation capability, thereby providing a valuable reference for practical engineering applications.

State-constrained semilinear elliptic optimization problems with unrestricted sparse controls

In this paper, we consider optimal control problems associated with semilinear elliptic equation equations, where the states are subject to pointwise constraints but there are no explicit constraints on the controls. A term is included in the cost functional promoting the sparsity of the optimal control. We prove existence of optimal controls and derive first and second order optimality conditions. In addition, we establish some regularity results for the optimal controls and the associated adjoint states and Lagrange multipliers.

Improved Low-Rank Filtering of MR Spectroscopic Imaging Data With Pre-Learnt Subspace and Spatial Constraints.

To investigate the use of pre-learnt subspace and spatial constraints for denoising magnetic resonance spectroscopic imaging (MRSI) data. We exploit the partial separability or subspace structures of high-dimensional MRSI data for denoising. More specifically, we incorporate a subspace model with pre-learnt spectral basis into the low-rank approximation (LORA) method. Spectral basis is determined based on empirical prior distributions of the spectral parameters variations learnt from auxiliary training data; spatial priors are also incorporated as is done in LORA to further improve denoising performance. The effects of the explicit subspace and spatial constraints in reducing estimation bias and variance have been analyzed using Cramér-Rao Lower bound analysis, Monte-Carlo study, and experimental study. The denoising effectiveness of LORA can be significantly improved by incorporating pre-learnt spectral basis and spatial priors into LORA. This study provides an effective method for denoising MRSI data along with comprehensive analyses of its performance. The proposed method is expected to be useful for a wide range of studies using MRSI.