Partial Constraints Research Articles

Integrating Heuristic Methods with Deep Reinforcement Learning for Online 3D Bin-Packing Optimization.

This study proposes a method named Hybrid Heuristic Proximal Policy Optimization (HHPPO) to implement online 3D bin-packing tasks. Some heuristic algorithms for bin-packing and the Proximal Policy Optimization (PPO) algorithm of deep reinforcement learning are integrated to implement this method. In the heuristic algorithms for bin-packing, an extreme point priority sorting method is proposed to sort the generated extreme points according to their waste spaces to improve space utilization. In addition, a 3D grid representation of the space status of the container is used, and some partial support constraints are proposed to increase the possibilities for stacking objects and enhance overall space utilization. In the PPO algorithm, some heuristic algorithms are integrated, and the reward function and the action space of the policy network are designed so that the proposed method can effectively complete the online 3D bin-packing task. Some experimental results illustrate that the proposed method has good results in achieving online 3D bin-packing tasks in some simulation environments. In addition, an environment with image vision is constructed to show that the proposed method indeed enables an actual robot manipulator to successfully and effectively complete the bin-packing task in a real environment.

Optimal electric bus scheduling considering battery degradation effect and charging facility capacity

ABSTRACT Electric buses are environmentally friendly with the features of low noise levels and zero-emissions. However, higher upfront costs due to the battery degradation effect, charging facility capacity and operational issues are the main obstacles to large-scale application of electric buses. This study proposes a mixed-integer nonlinear model for optimizing electric bus scheduling with a partial charging strategy, battery degradation and constraints of charging facility capacity. A genetic algorithm is then proposed to solve the model. Last, a case study based on a real transit network in Nanjing, China is conducted. The experimental results show that compared with the existing scheduling scheme, the optimal scheduling model can reduce the total system costs by 8.20%, which validates the effectiveness of the proposed model. The findings in this paper can provide a reference for operators to formulate electric bus scheduling schemes and promote the sustainable development of public transport.

Adaptive fuzzy event-triggered control for a class of nonlinear time-delay multi-agent systems with dead zone and partial state constraints

This paper presents an adaptive fuzzy event-triggered control (ETC) method for a class of time-delay nonlinear multi-agent systems (MASs) with dead zone (DZ) and partial state constraints (PSCs). It should be pointed out that the states considered in this paper are unmeasurable and part of the system states are constrained by time-varying boundary. By utilizing fuzzy logic systems (FLSs) and backstepping design framework, a fuzzy state observer is constructed to estimate the unmeasured states, while the introduction of a time-varying barrier Lyapunov function (BLF) addresses the partial state constrained problem. Furthermore, during the design process of the state observer, compensation for the influence of the unknown DZ input on the system is achieved through utilization of known designed event-triggered input signal and adaptive parameter. Building upon this foundation, employing the Lyapunov stability theory and adaptive backstepping technique with ETC strategy, the developed distributed control mechanism demonstrates that all variables of the closed-loop system are bounded, the consensus error of the system can converge to a small region of origin and Zeno behavior can be ruled out. Finally, two simulation examples further illustrate the proposed control strategy and theorem.

A knowledge graphs representation method based on IsA relation modeling

Knowledge graph representation learning, which is able to support further knowledge computation and reasoning, has drawn much research attention in the field of artificial intelligence in recent years. Due to data sparsity, traditional knowledge graph methods focusing on the observed facts have poor performance. Therefore, researchers introduce auxiliary information to tackle this issue. As a kind of prior knowledge containing rich semantics, IsA relation could be used to boost model performance. We propose a knowledge representation learning method combined with isA relation modeling. Specifically, we model two features of isA relation—transitivity and antisymmetry. The transitivity is modeled by the projection invariance of vectors, and antisymmetry is modeled by partial order constraints. We use RotatE as our base model which could also be replaced by other knowledge embedding model with higher dimension. Finally, experimental results of link prediction and triple classification task on two datasets verify the proposed model’s effectiveness outperforming baseline models.

Особенности пересечения профессионально значимых концептов в языковом сознании кардиологов

The research is focused on the issues of conceptualization and identification of extra-linguistic aspects influencing the reflection of the received information in the language consciousness, revealing the connection of professionally significant concepts in the language consciousness of people. The aim of the study is to reveal whether the concept WORK is a hyperconcept in the language consciousness of representatives of the group distinguished by professional employment (cardiologists) in relation to the concepts representing the main objects of their labor functions (the concepts HEALTH and SICKNESS). The general research sample (1200 associations) was formed based on the results of two directional associative experiments with the words work, health, and disease stimuli with partial response constraints. The study was carried out on the integrated theoretical and methodological basis of psycholinguistics and cognitive linguistics. Scientific novelty is determined by the fact that the concepts WORK, HEALTH, SICKNESS are studied for the first time in the context of their representation in the language consciousness of representatives of a certain profession. The results of the scientific research allowed to establish that the concept WORK has a universal character and is an important element not only of the national, but also of the individual concept sphere. It was confirmed that in the spheres of employment requiring selfless labor, the WORK concept and the concepts denoting the main labor functions will not have a hierarchical relationship and will not act as hyper- and hypo-concepts.

Adaptive penalty-based neurodynamic approach for nonsmooth interval-valued optimization problem

The complex and diverse practical background drives this paper to explore a new neurodynamic approach (NA) to solve nonsmooth interval-valued optimization problems (IVOPs) constrained by interval partial order and more general sets. On the one hand, to deal with the uncertainty of interval-valued information, the LU-optimality condition of IVOPs is established through a deterministic form. On the other hand, according to the penalty method and adaptive controller, the interval partial order constraint and set constraint are punished by one adaptive parameter, which is a key enabler for the feasibility of states while having a lower solution space dimension and avoiding estimating exact penalty parameters. Through nonsmooth analysis and Lyapunov theory, the proposed adaptive penalty-based neurodynamic approach (APNA) is proven to converge to an LU-solution of the considered IVOPs. Finally, the feasibility of the proposed APNA is illustrated by numerical simulations and an investment decision-making problem.

Distributed Control for Nonlinear Time-Delay Multiagent Systems: Hybrid Saturation-Constraint Impulsive Approach.

This article mainly studies the problem of impulse consensus of multiagent systems under communication constraints and time delay. Considering the limited communication bandwidth of the agent, global and partial saturation constraints are considered. In addition, so as to further improve communication efficiency by reducing communication frequency, the novel control protocol combining event-triggered strategy and general impulse control protocol is proposed. Under this kind of novel control protocol, the communication frequency of multiagent systems can be reduced while avoiding "Zeno behavior." Through theoretical analysis, sufficient conditions for the systems to achieve consensus are obtained for the above two saturation constraint cases. In the end, the effectiveness of the novel protocols is proved by providing two different simulation instances.

Constraint subsets-based evolutionary multitasking for constrained multiobjective optimization

Constrained multiobjective optimization problems (CMOPs) are challenging because they need to optimize multiple conflicting objectives and satisfy various constraints simultaneously. To solve CMOPs, various constrained multiobjective evolutionary algorithms have been proposed in recent years. However, most of them tackle constraints by considering all constraints or zero constraint scenarios, these extreme treatment methods may be unable to utilize the information of multiple constraint subsets composed of partial constraints to maintain more promising infeasible solutions. To remedy this issue, a constraint subsets-based evolutionary multitasking method is developed, where a CMOP is transformed into a multitasking optimization problem by creating multiple simple auxiliary CMOPs. Particularly, the original CMOP is the main task, while the newly created CMOPs with different constraint subsets are the auxiliary tasks. Each task will be evolved by one specific population, and the knowledge transfer is conducted among tasks to realize the collaborative search. Meanwhile, the updating of the auxiliary task involves two stages. In the first stage, each auxiliary population will evolve to approach the pareto front of the constraint subset (s-CPF), promoting crossing the infeasible regions. While in the second stage, a feasible region-based search mechanism is proposed to approach the pareto front of the main task from each s-CPF, by utilizing unique and promising infeasible solutions. In addition, systematic experiments are carried out on three benchmark test suites and four real-world CMOPs. The experimental results fully demonstrate that the proposed algorithm is highly competitive with other state-of-the-art constrained multiobjective evolutionary algorithms.

On generalized Nash equilibrium problems in infinite-dimensional spaces using Nikaido–Isoda type functionals

We present an analysis of generalized Nash equilibrium problems in infinite-dimensional spaces with possibly non-convex objective functions of the players. Such settings arise, for instance, in games that involve nonlinear partial differential equation constraints. Due to non-convexity, we work with equilibrium concepts that build on first order optimality conditions, especially Quasi-Nash Equilibria (QNE), i.e. first-order optimality conditions for (Generalized) Nash Equilibria, and Variational Equilibria (VE), i.e. first-order optimality conditions for Normalized Nash Equilibria. We prove existence of these types of equilibria and study characterizations of them via regularized (and localized) Nikaido-Isoda merit functions. We also develop continuity and (continuous) differentiability results for these merit functions under quite weak assumptions, using a generalization of Danskin's theorem. They provide a theoretical foundation for, e.g. using globalized descent methods for computing QNE or VE.

Modeling of heat and mass transfer in the discontinuum approximation

The article presents a theoretical analysis of the governing equations expressing the fundamental conservation laws in the continuum and discontinuum approximations, and methods for solving problems of hydrodynamics as one of the most important subfields of continuum mechanics. This article is an attempt to more accurately describe physicochemical macro-processes. It is shown that the most suitable equations for computer modeling are the conservation laws under natural constraints on the minimum spatial and time scales, i.e., equations without partial derivatives and constraints on the solution smoothness. Using the continuity and thermal conductivity equations, a phenomenological method for constructing and numerically solving the governing equations is presented, and comparison with the traditional approach is given.

Experimental study on the effect of partial shear studs layout on flexural behavior of steel-concrete composite beams

In steel-concrete composite beams, partial shear connection offers advantages including greater ductility and lower cost. However, partial shear connection constraints on composite beam structural performance, such as reduced beam stiffness, increased steel-concrete interface slip, etc., should not be neglected. Several researches have revealed that shear connector layout is one of the main approaches to limit partially composite beam vulnerability. Shear connector layout optimization has not been completely investigated experimentally, and its effect on composite beam structural performance is still unknown. This paper focusses on the experimental study of the effect of shear connectors layout on the flexural performance of composite beams. It reports the optimization of the layout of shear connectors based on blocked distribution of shear connectors laid in a single row, while concentrating the highest number of shear studs towards the supports of a simply supported composite beam. A fully composite beam with normal layout of shear studs was tested as control specimen, while the rest of the beams used partial shear connection (η = 0.5). Beams with partial shear connection had 3 different layouts of shear studs. The first had uniformly distributed shear studs, and the rest had shear studs laid out in 2 and 3 blocks each of uniform spacing respectively. The results showed that the beam with 3 blocks layout each of equal spacing of shear studs had the closest best structural performance to the fully composite beam and had better ductility than the latter.

Adaptive optimal backstepping control for strict-feedback nonlinear systems with time-varying partial output constraints

This paper investigates the optimal backstepping control strategy for strict-feedback nonlinear systems subject to input saturation and time-varying partial output constraints. Compared with the existing results on output constraints, the time-varying partial output constraint is a more general constraint that can start and end at any time during the system operation, or remain unconstrained, which can be called as output constraints occurring in a limited time interval (OCOLT). A special barrier function is embedded into the optimal performance index function to satisfy the OCOLT condition under the optimal control framework, and a shift function is introduced to address the function discontinuity caused by the OCOLT problem. Then, an auxiliary system and a disturbance observer are respectively constructed to handle the influence of the input saturation and compounded disturbances. Meanwhile, the simplified reinforcement learning algorithm, employing the identifier-critic-actor architecture, is developed to achieve the optimal control objective within the framework of the backstepping technology. Moreover, the proposed optimal control method ensures the semi-globally uniformly ultimately bounded of all signals within the closed-loop system. Finally, two simulation examples are given to further prove the effectiveness of the presented optimal control approach.

Decentralized policy learning with partial observation and mechanical constraints for multiperson modeling

Extracting the rules of real-world multi-agent behaviors is a current challenge in various scientific and engineering fields. Biological agents independently have limited observation and mechanical constraints; however, most of the conventional data-driven models ignore such assumptions, resulting in lack of biological plausibility and model interpretability for behavioral analyses. Here we propose sequential generative models with partial observation and mechanical constraints in a decentralized manner, which can model agents’ cognition and body dynamics, and predict biologically plausible behaviors. We formulate this as a decentralized multi-agent imitation-learning problem, leveraging binary partial observation and decentralized policy models based on hierarchical variational recurrent neural networks with physical and biomechanical penalties. Using real-world basketball and soccer datasets, we show the effectiveness of our method in terms of the constraint violations, long-term trajectory prediction, and partial observation. Our approach can be used as a multi-agent simulator to generate realistic trajectories using real-world data.

Disturbance Observer-Based Safe Tracking Control for Unmanned Helicopters with Partial State Constraints and Disturbances

In this paper, a disturbance observer-based safe tracking control scheme is proposed for a medium-scale unmanned helicopter with rotor flapping dynamics in the presence of partial state constraints and unknown external disturbances. A safety protection algorithm is proposed to keep the constrained states within the given safe-set. A second-order disturbance observer technique is utilized to estimate the external disturbances. It is shown that the desired tracking performance of the controlled unmanned helicopter can be achieved with the application of the backstepping approach, dynamic surface control technique, and Lyapunov method. Finally, the availability of the proposed control scheme has been shown by simulation results.

Deep learning methods for blood flow reconstruction in a vessel with contrast enhanced x-ray computed tomography.

The reconstruction of blood velocity in a vessel from contrast enhanced x-ray computed tomography projections is a complex inverse problem. It can be formulated as reconstruction problem with a partial differential equation constraint. A solution can be estimated with the a variational adjoint method and proper orthogonal decomposition (POD) basis. In this work, we investigate new inversion approaches based on PODs coupled with deep learning methods. The effectiveness of the reconstruction methods is shown with simulated realistic stationary blood flows in a vessel. The methods outperform the reduced adjoint method and show large speed-up at the online stage.

Generating Fingerings for Piano Music with Model-Based Reinforcement Learning

The piano fingering annotation task refers to assigning finger labels to notes in piano sheet music. Good fingering helps improve the smoothness and musicality of piano performance. In this paper, we propose a method for automatically generating piano fingering using a model-based reinforcement learning algorithm. We treat fingering annotation as a partial constraint combinatorial optimization problem and establish an environment model for the piano performance process based on prior knowledge. We design a reward function based on the principle of minimal motion and use reinforcement learning algorithms to decide the optimal fingering combinations. Our innovation lies in establishing a more realistic environment model and adopting a model-based reinforcement learning approach, compared to model-free methods, to enhance the utilization of samples. We also propose a music score segmentation method to parallelize the fingering annotation task. The experimental section shows that our method achieves good results in eliminating physically impossible fingerings and reducing the amount of finger motion required in piano performance.

Observer-based fuzzy adaptive event-triggered control for strictly uncertain nonlinear systems with partial state constraints and output dead-zones

This paper delves into the fuzzy adaptive event-triggered tracking control for a certain class of strictly uncertain nonlinear systems subject to partial state constraints as well as output dead-zones. First of all, fuzzy logic systems (FLSs) are utilised to approximate the unpredictable items, a fuzzy adaptive observer is intended to enable state estimation. Subsequently, a type of smooth approximate model is introduced to settle the nondifferentiable phenomenon of output dead-zones. To reduce the computational overhead of the communication operation effectively, an improved event-triggered control strategy including a decreasing hyperbolic tangent function related to dead-zone, is applied to determine the actual control input. In addition, the barrier Lyapunov function (BLF) is fabricated to address the issue of partial state constraint. By theoretical analysis, the reference signal can be precisely tracked by the system output and all closed-loop signals remain uniformly ultimately bounded (UUB). Finally, the constructed controller's effectiveness is validated with two illustrative examples.

Multi-agent graph reinforcement learning for decentralized Volt-VAR control in power distribution systems

Volt/Var control (VVC) is a crucial function in power distribution systems to minimize power loss and maintain voltages within allowable limits. However, incomplete and inaccurate information about the distribution network makes model-based VVC methods difficult to implement in practice. In this paper, we propose a novel multi-agent graph-based deep reinforcement learning (DRL) algorithm named MASAC-HGRN to address the VVC problem under partial observation constraints. Our proposed algorithm divides the power distribution system into several regions, each region treated as an agent. Unlike traditional model-based or global-observation-based DRL methods, our proposed method leverages a practical decentralized training and decentralized execution (DTDE) paradigm to address the partial observation constraints. The well-trained agents gather information only from their interconnected neighbors and realize decentralized local control. Numerical studies with IEEE 33-bus and 123-bus distribution test feeders demonstrate that our proposed MASAC-HGRN algorithm outperforms the state-of-art RL algorithms and traditional model-based approaches in terms of VVC performance. Moreover, the DTDE framework exhibits flexibility and robustness in extensive robustness experiments.

OPTIMAL INVESTMENT UNDER PARTIAL INFORMATION AND ROBUST VAR-TYPE CONSTRAINT

This paper extends the utility maximization literature by combining partial information and (robust) regulatory constraints. Partial information is characterized by the fact that the stock price itself is observable by the optimizing financial institution, but the outcome of the market price of the risk [Formula: see text] is unknown to the institution. The regulator develops either a congruent or distinct perception of the market price of risk in comparison to the financial institution when imposing the Value-at-Risk (VaR) constraint. We also discuss a robust VaR constraint in which the regulator uses a worst-case measure. The solution to our optimization problem takes the same form as in the full information case: optimal wealth can be expressed as a decreasing function of state price density. The optimal wealth is equal to the minimum regulatory financing requirement in the intermediate economic states. The key distinction lies in the fact that the price density in the final state depends on the overall evolution of the estimated market price of risk, denoted as [Formula: see text] or that the upper boundary of the intermediate region exhibits stochastic behavior.

Fuzzy adaptive tracking control of fractional-order multi-agent systems with partial state constraints and input saturation via event-triggered strategy

This paper addresses the problem of adaptive tracking control for fractional-order multi-agent systems subject to input saturation and partial state constraints, utilizing an event-triggered strategy with output feedback. The interconnected graph of multiple agents is assumed to be directed and contain a spanning tree. Since only the system output is available, a fractional-order state observer is designed to obtain the unmeasurable states. The nonlinear dynamics of the system are assumed to be unknown and are approximated by a fuzzy logic system. By utilizing the barrier Lyapunov function, backstepping procedure and dynamic surface control technique, an event-triggered adaptive control scheme is proposed to ensure that the constrained states remain within their bounds, all system signals are bounded, tracking error converges to a bounded set containing the origin, and no Zeno behavior occurs. Finally, the validity of the presented method is verified by simulation.