Merging Problem Research Articles

Deep reinforcement learning algorithm based ramp merging decision model

On-ramp merge is a complex traffic scenario in autonomous driving. Because of the uncertainty of the driving environment, most rule-based models cannot solve such a problem. This paper designs a ramp merging decision model based on deep deterministic policy gradient algorithm (DDPG) to solve the vehicle merging problem. To address the problems of slow algorithm merging and poor robustness of previous deep reinforcement learning algorithms in the field of intelligent vehicle ramp merging leading to the low success rate of intelligent vehicle merging, first, we introduce a simple recurrent unit (SRU) for extracting intelligent vehicle states and environment features and use the DDPG algorithm for intelligent vehicle decision making. Second, the experience playback pool of DDPG algorithm is improved by using priority sampling instead of uniform sampling. Finally, a multi-objective reward function is set up during training, considering factors such as safety and efficiency. The simulation experiments show that the improved algorithm improves the merging speed of the model, reduces the collision rate, and enables the vehicle to make more reasonable decisions. In addition, the superiority of the method is demonstrated by comparing with the advanced method.

Consensus-Based Merging and Spacing Method for Aircraft Self-Separation at Intersections

Within the context of delegating separation related tasks from an air traffic controller to the flight deck, this paper analyzes the merging and spacing problem for autonomous aircraft operations at busy airway intersections. A consensus-based control protocol is developed to achieve an ordered and safe traffic flow at a given intersection waypoint. Two primary implementation steps are covered in the protocol. In the first step, consensus on the target merging flow is achieved, where the merging stream is modeled as a straight line with the minimum total converging distance. In the second step, multiple aircraft with double-integrator dynamics and time-varying communication topologies are guided to merge into the target flow while maintaining appropriate interaircraft spacing. A state control law is designed, and the Lyapunov analysis method is leveraged to derive sufficient conditions on the communication topology and the control parameter for merging agents to reach consensus in finite time. Performance of the proposed method is evaluated through experimental simulations under different hypothetical scenarios in the two-dimensional plane.

Large-scale fabrication of nanofibers by tiny-needle-spaced electrostatic-induction-assisted solution blowing spinning

In this paper, a technology and device for large-scale fabrication of nanofibers called tiny-needle-spaced electrostatic-induction-assisted solution blowing spinning (TESBS) was developed. The airflow stretching force is used as the initial driving force for jet formation in TESBS, which avoids the electric field interference existing in the jet formation stage of multi-needle electrospinning(MES). The addition of an induced electric field in TESBS solves the problem of mutual merging of jets in multi-needle solution blowing spinning (MSBS). The needle spacing of TESBS can be as small as 1 mm, which is much smaller than MES (100 mm) and MSBS (3 mm). The substantial reduction in needle spacing can increase the arrangement density of blunt needles, thereby increasing the output of nanofibers. Compared with MSBS, the average diameter and diameter standard deviation of TESBS nanofibers can be reduced by 52.6% and 78.7%, respectively. Compared with MES, the uniformity of the TESBS nanofiber web has been significantly improved. The formula for the critical needle spacing to ensure that the TESBS jets do not merge with each other was derived. The output of 15-needle TESBS can reach as high as 3 ml/min. The average diameter of TESBS nanofibers decreases with the decrease in injection speed or the increase in voltage. The distance between the needle and the receiver has little effect on the average fiber diameter. TESBS nanofibers with good quality and high yield have broad and bright application prospects in many fields.

Ameliorated Snake Optimizer-Based Approximate Merging of Disk Wang-Ball Curves.

A method for the approximate merging of disk Wang-Ball (DWB) curves based on the modified snake optimizer (BEESO) is proposed in this paper to address the problem of difficulties in the merging of DWB curves. By extending the approximate merging problem for traditional curves to disk curves and viewing it as an optimization problem, an approximate merging model is established to minimize the merging error through an error formulation. Considering the complexity of the model built, a BEESO with better convergence accuracy and convergence speed is introduced, which combines the snake optimizer (SO) and three strategies including bi-directional search, evolutionary population dynamics, and elite opposition-based learning. The merging results and merging errors of numerical examples demonstrate that BEESO is effective in solving approximate merging models, and it provides a new method for the compression and transfer of product shape data in Computer-Aided Geometric Design.

Cognitive mapping of indoor environments: constructing an indoor navigation network from crowdsourced indoor route descriptions

ABSTRACT Indoor navigation networks provide an effective solution for modeling indoor environments for navigational purposes. In comparison to pure geometric structures, network structures that are aligned with the user’s cognitive map are perceived as more intuitive. However, there has been limited research conducted on constructing indoor navigation networks that align with user’s cognitive maps. Human route descriptions contain valuable insights into how individuals recognize their surroundings and how humans structure spatial information cognitively. Using crowdsourced route descriptions to construct indoor navigation networks can provide an approximation of people’s cognitive maps. This study proposes a graph-based method to solve the problem of merging human indoor route descriptions. It models indoor route descriptions as directed attributed graphs and transforms the challenges into a graph merging problem. This method relies on order and direction information between references. In a case study with human indoor route descriptions, an indoor navigation network was generated by merging crowdsourced indoor route descriptions. The network has the potential to facilitate a comparison between existing indoor network models and identify the indoor navigation network that best matches the network derived from crowdsourced route descriptions. Additionally, the network could be used to generate more intuitive indoor route descriptions.

A Study of Disjoint Set Union in Programming Competitions

Disjoint Set Union (DSU) is a tree data structure, which is used to effectively deal with the problems of merging and querying disjoint sets. The DSU algorithm can be used to merge sets and query to which set the node belongs. The DSU algorithm is usually implemented using arrays and tree structures, but there are also methods that use hash tables. The DSU algorithm has a wide range of applications in the connectivity of graph theory, social network and image processing. It helps researchers better understand and analyze set operations, provides a basis for subsequent work, and promotes the solution and optimization of various problems in the field. At the same time, in the programming competition of college students, the use of DSU is more frequent, usually the use of set query is more, resulting in high time complexity and unable to solve the problem quickly. Therefore, path compression strategy is introduced to significantly improve the efficiency of set query. Finally, the application of path compression in union search is introduced in the form of programming competition.

Deep Multi-Agent Reinforcement Learning for Highway On-Ramp Merging in Mixed Traffic

On-ramp merging is a challenging task for autonomous vehicles (AVs), especially in mixed traffic where AVs coexist with human-driven vehicles (HDVs). In this paper, we formulate the mixed-traffic highway on-ramp merging problem as a multi-agent reinforcement learning (MARL) problem, where the AVs (on both merge lane and through lane) collaboratively learn a policy to adapt to HDVs to maximize the traffic throughput. We develop an efficient and scalable MARL framework that can be used in dynamic traffic where the communication topology could be time-varying. Parameter sharing and local rewards are exploited to foster inter-agent cooperation while achieving great scalability. An action masking scheme is employed to improve learning efficiency by filtering out invalid/unsafe actions at each step. In addition, a novel priority-based safety supervisor is developed to significantly reduce collision rate and greatly expedite the training process. A gym-like simulation environment is developed and open-sourced with three different levels of traffic densities. We exploit curriculum learning to efficiently learn harder tasks from trained models under simpler settings. Comprehensive experimental results show the proposed MARL framework consistently outperforms several state-of-the-art benchmarks.

On the methodology of three-way structured merge in version control systems: Top-down, bottom-up, or both

Three-way merging is an essential component of version control systems. Despite the efficiency of the conventional line-based textual methods, syntax-based structured approaches have demonstrated benefits in improving merge accuracy. Prior structured merging approaches visit abstract syntax trees in a top-down manner, which struggles to identify and merge shifted code generally. This work introduces a novel methodology combining a top-down and a bottom-up visit of abstract syntax trees, which manipulates shifted code effectively and elegantly. Especially, we reduce the merge problem of ordered lists to computing a topological sort of strongly connected components of the constraint graph. Compared with four representative merge tools in 40,533 real-world merge scenarios, our approach achieves the highest merge accuracy while being 2.5x as fast as a state-of-the-art structured merge tool.

Dual Histogram Equalization Algorithm Based on Adaptive Image Correction

For the visual measurement of moving arm holes in complex working conditions, a histogram equalization algorithm can be used to improve image contrast. To lessen the problems of image brightness shift, image over-enhancement, and gray-level merging that occur with the traditional histogram equalization algorithm, a dual histogram equalization algorithm based on adaptive image correction (AICHE) is proposed. To prevent luminance shifts from occurring during image equalization, the AICHE algorithm protects the average luminance of the input image by improving upon the Otsu algorithm, enabling it to split the histogram. Then, the AICHE algorithm uses the local grayscale correction algorithm to correct the grayscale to prevent the image over-enhancement and gray-level merging problems that arise with the traditional algorithm. It is experimentally verified that the AICHE algorithm can significantly improve the histogram segmentation effect and enhance the contrast and detail information while protecting the average brightness of the input image, and thus the image quality is significantly increased.

Reparameterization of B-spline surface and its application in ship hull modeling

NURBS are widely used in the design of free curves and surfaces and have been the industrial standard for product design in CAD/CAM. Ship hull surfaces are complex doubly-curved surfaces and usually decomposed into patches based on feature curves. Due to the topologically rectangular limitations of tensor-product NURBS surfaces and the inevitable problem of surface merging caused by decomposition, the reconstruction of ship hull still remains a complicated problem. The theoretical research of merging NURBS surfaces is relatively comprehensive, but the difficulty lies in how to merge surfaces defined in different knot vectors at the common boundary curve since control meshes form T-junctions. This paper proposes a methodology of reparameterizing B-spline surfaces, using a fast progressive-iterative approximation (FPIA) method to refit section curves or isoparametric curves with constraints, thus making the topological structure of control meshes regular, uniform and orthogonal. Subsequently, a KCS container ship with bulbous bow and stern is utilized as an illustration for reconstructing with B-splines. The lighting effects and lines plan derived from the hull surface demonstrate that this approach can achieve fair, smooth and watertight surfaces. The approach exhibits strong robustness, versatility and generalization ability, and provides theoretical innovation and practical design methods for representing and reconstructing complex ship hull.

The Multiple Model Poisson Multi-Bernoulli Mixture Filter for Extended Target Tracking

In an intelligent transportation system (ITS), the single motion model is not enough to meet the needs of simulation systems (or practical applications) and guarantee good tracking performance for multiple maneuvering extended target tracking (ETT). This paper presents multiple models Poisson multi-Bernoulli mixture (MM-PMBM) filter for extended target tracking to address this problem. To make multiple models transform in an accurate manner, the jump Markov system (JMS) is timely introduced in filtering recursion. After that, the model probability of target is recursively updated and used to estimate the target position. In addition, we derive the closed-form solution to the proposed filter based on the Gamma Gaussian inverse-Wishart (GGIW) implementation. The approach to handling the merging problem of GGIW components via Kullback-Leibler divergence (KLD) minimization is also presented, resulting in better utilization of available components. Simulation results demonstrate that the proposed filter has superior performance in comparison to several state-of-the-art multi-target filters.

AutoScaleDSE: A Scalable Design Space Exploration Engine for High-Level Synthesis

High-Level Synthesis (HLS) has enabled users to rapidly develop designs targeted for FPGAs from the behavioral description of the design. However, to synthesize an optimal design capable of taking better advantage of the target FPGA, a considerable amount of effort is needed to transform the initial behavioral description into a form that can capture the desired level of parallelism. Thus, a design space exploration (DSE) engine capable of optimizing large complex designs is needed to achieve this goal. We present a new DSE engine capable of considering code transformation, compiler directives (pragmas), and the compatibility of these optimizations. To accomplish this, we initially express the structure of the input code as a graph to guide the exploration process. To appropriately transform the code, we take advantage of ScaleHLS based on the multi-level compiler infrastructure (MLIR). Finally, we identify problems that limit the scalability of existing DSEs, which we name the “design space merging problem.” We address this issue by employing a Random Forest classifier that can successfully decrease the number of invalid design points without invoking the HLS compiler as a validation tool. We evaluated our DSE engine against the ScaleHLS DSE, outperforming it by a maximum of 59×. We additionally demonstrate the scalability of our design by applying our DSE to large-scale HLS designs, achieving a maximum speedup of 12× for the benchmarks in the MachSuite and Rodinia set.

Cascade aircraft flows merging with multiple order changes

Nowadays, the problem of safe aircraft flows merging is considered usually as one-stage. However, real air-route schemes assume often a tree-like structure when primary flows are merged at some points and the resultant flows are merged further. In this case, the safety of merging should be controlled not only at the final point, but also at some intermediate ones. With that, aircraft can change their order between these merge points by means of usage of holding areas and/or path alignments. In this paper, the authors suggest a mixed integer linear programming formalization of such a problem. The suggested procedure is realized as a computational program with the optimization Gurobi library. Results of numerical simulations are presented.

Modeling of co-axial bubbles coalescence under moderate Reynolds regimes: A Bi-phase SPH approach

Phenomena involving bubble flow play a significant role in numerous industrial, natural, and scientific systems. Thus, liquid–gas interfaces must be considered the influence of surface tension and buoyancy. This work analyzes a complete numerical study for bi-fluid flow problems in the deformation evolution of two bubbles coalescing in a viscous liquid. This study discusses diverse configurations of the coalescence bubbles process and their effect on the displacement of the center of mass, velocity, streamlines, and evolution of the morphologies’ deformation. The resulting simulations revealed the process of the coalescence bubbles regarding three stages: approaching, drainage, and rupture of the interface. These steps reach different morphologies, defined as oblate ellipsoid, prolate ellipsoid, and ellipsoidal cap shapes between the trailing, leading, and merging bubbles. Likewise, an approximated bi-phase 2D methodology using the Navier–Stokes equations with Smoothed Particle Hydrodynamics (SPH) method and associated with the Continuous Surface Force (CSF) method was employed to approach the interaction between the bubbles, the surrounding liquid, and cavity walls. This approach with SPH and CSF for fused bubbles and their liquid interaction are validated employing numerical benchmarks in situations with high and moderate regimes of the Reynolds (Re) and Eötvös (Eo) numbers, and different sizes of diameter between coalescence bubbles. Correspondingly, examples of bubbles merging around a liquid owing to gravitational are rarely treated in the literature of mesh-free methods, especially to characterize different viscosity, density and surface tension regimes at the bubble–liquid interface, the effect of the method precision (distance between particles, Δx), the size of the surrounding liquid cavity and the initial distance between lighter domains. According to the bubbles deformation, during the coalescence is observed significant influence of Δx resolution and the cavity size, there are instances of instabilities, such as lateral tails, droplets inside the lighter domain, break-up, and satellite bubble formation. Finally, it is provided a robust numerical study of the coalescence process with a bi-phase SPH for different surfaces tension regimes (5≤Eo≤200), viscosity and density ratios (5≤λ,Φ≤100) and initial conditions in merging bubbles problems with moderates Reynolds numbers (5≤Re≤50).

Large-Scale Multiple Sequence Alignment and the Maximum Weight Trace Alignment Merging Problem.

MAGUS is a recent multiple sequence alignment method that provides excellent accuracy on large challenging datasets. MAGUS uses divide-and-conquer: it divides the sequences into disjoint sets, computes alignments on the disjoint sets, and then merges the alignments using a technique it calls the Graph Clustering Method (GCM). To understand why MAGUS is so accurate, we show that GCM is a good heuristic for the NP-hard MWT-AM problem (Maximum Weight Trace, adapted to the Alignment Merging problem). Our study, using both biological and simulated data, establishes that MWT-AM scores correlate very well with alignment accuracy and presents improvements to GCM that are even better heuristics for MWT-AM. This study suggests a new direction for large-scale MSA estimation based on improved divide-and-conquer strategies, with the merging step based on optimizing MWT-AM. MAGUS and its enhanced versions are available at https://github.com/vlasmirnov/MAGUS.

Adaptive Merging on Phase Change Memory

Indexing is a well-known database technique used to facilitate data access and speed up query processing. Nevertheless, the construction and modification of indexes are very expensive. In traditional approaches, all records in the database table are equally covered by the index. It is not effective, since some records may be queried very often and some never. To avoid this problem, adaptive merging has been introduced. The key idea is to create an index adaptively and incrementally as a side-product of query processing. As a result, the database table is indexed partially depending on the query workload. This paper faces the problem of adaptive merging for phase change memory (PCM). The most important features of this memory type are limited write endurance and high write latency. As a consequence, adaptive merging should be investigated from the scratch. We solve this problem in two steps. First, we apply several PCM optimization techniques to the traditional adaptive merging approach. We prove that the proposed method (eAM) outperforms a traditional approach by 60%. After that, we invent the framework for adaptive merging (PAM) and propose a new variant of the PCM-optimized index. It further improves the system performance by 20% for databases where search queries interleave with data modifications.

Safety-Critical and Flexible Cooperative On-Ramp Merging Control of Connected and Automated Vehicles in Mixed Traffic

Cooperative on-ramp merging control for connected and automated vehicles (CAVs) can effectively improve traffic throughput and vehicle fuel efficiency at highway on-ramp merging bottlenecks. However, in the mixed traffic scenario where CAVs and human-driven vehicles (HDVs) coexist, the uncertain maneuvers of human drivers pose a major challenge to merging control in terms of safety and flexibility. To this end, this paper proposes a hierarchical cooperative on-ramp merging control strategy for CAVs to optimize flexible trajectories with safety guarantees in mixed traffic. First, the on-ramp merging control problem for CAVs is considered in the case of a three-vehicle coordination, resulting in an optimal control problem (OCP) coordinating on-ramp and main-lane CAVs for efficient operation while satisfying multiple safety-critical constraints. Second, a two-level hierarchical control architecture is developed to solve the OCP with mixed state-control constraints. The upper-level planner solves an unconstrained OCP with Pontryagin’s Minimum Principle to calculate an expected merging position, which is embedded in the variable time headway of safe merging constraints in the lower-level controller. Then, the controller converts the nonlinear OCP with safety-critical constraints to a quadratic programing (QP) problem by exploiting Control Barrier Functions (CBFs) and Control Lyapunov Functions (CLFs). By solving the QP efficiently, the time and energy efficient trajectory for each CAV is obtained. In addition, a receding horizon control framework is employed, which enables CAVs to determine flexible merging opportunity and tackle the disturbances caused by HDVs. Finally, comprehensive simulation results show that the proposed cooperative on-ramp merging strategy has potential in enabling merging flexibility, improving traffic efficiency and energy economy in real time.

ORSI Salient Object Detection via Cross-Scale Interaction and Enlarged Receptive Field

Due to the diversity of scales and shapes, the uncertainty of object position, and the complexity of edge details, the recent merging problem of salient object detection in optical remote sensing images (RSI-SOD) is a considerably challenging topic. To cope with the challenges, we propose a new cross-scale interaction network (CIFNet) equipped with the enlarged receptive field, which mainly contains three modules in an encoder-decoder architecture, including a furcate skip connection module, a global leading attention Module, and an expansion-integration module. First, FSCM uses dilated convolutions to enlarge the receptive field and furcate skip connections to capture more multi-scale contextual information, both of which facilitate the adaptability of the model to different sizes, shapes, and quantities of the target objects. Second, on the low-resolution branch, GLM locates the potentially significant object positions in the feature map from a global semantic perspective. Finally, through an attention-guided cascade structure, EIM seeks more delicate characteristics by refining the features in a coarse-to-fine fashion. Extensive experiments are conducted on two RSI-SOD datasets, from which superior results can be achieved by our CIFNet, outperforming the other state-of-the-art methods. Compared with the second-best method, the performance gain of our method reaches 3.45% on MAE and 1.38% on <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">F</i> <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">adp</sup> <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">β</sub> . Notably, the proposed CIF-Net runs with 40.40M parameters, 14.8 GFLOPs computational complexity, and 58 fps inference speed, which guarantees high efficiency.

An integrated two‐dimensional merging trajectory optimization model for automated vehicles considering mixed traffic flow

Recently, automated vehicles have been recognized as a promising tool to address the problem of on-ramp merging. However, the complexity of the problem includes ignorance of the vehicle's lateral dynamics, the limitation of the fixed merging point, the mismatch problem caused by the sequential optimization scheme, and the fixed terminal states assumption. These factors make it intractable in practical driving scenarios. This paper proposed an integrated optimization model for on-ramp automated vehicles, which can guide the vehicle to complete the merging behaviour from the ramp lane to the main lane safely and efficiently. A merging path is first constructed in the two-dimensional plane with two critical parameters recommended by a neural network predictor, enabling it to incorporate both longitudinal and lateral dynamics. Then, an integrated Mixed Integer Quadratic Program (MIQP) model is built to determine the optimal velocity profiles and merging gap simultaneously while considering the safety and efficiency factors. Specifically, with the introduction of discretization and linearization techniques, linear collision avoidance constraints and smooth transition constraints can be built, which can address the challenging computational problem. The effectiveness of the proposed model is validated through the microscopic and macroscopic numerical results under different levels of mixed traffic.

Battery-Aware Cooperative Merging Strategy of Connected Electric Vehicles Based on Reinforcement Learning With Hindsight Experience Replay

Cooperative control of connected and automated electric vehicles (CAEVs) offers a great potential for a safe, high-efficient, sustainable transportation system. Among them, coordinated on-ramp merging based on an on-ramp merging vehicle and a mainline facilitating is a hot spot to lighten the impact of shockwave on highway junctions. Reinforcement learning (RL) is a promising solution to address this problem for its strong adaptiveness and self-learning ability. The existing methods are dedicatedly designed to circumvent the sparse reward problem of long-term merging safety but restrict the optimization space and neglect individual costs, especially irreversible loss, such as battery aging. In this article, a hindsight experience replay RL coordinated freeway on-ramp merging frame is proposed to face the sparse reward problem in ramp merging problem and, meanwhile, co-optimize traffic efficiency, energy-saving, and battery health performance. Compared with the existing optimization-based strategy, it fundamentally avoids abundant expert knowledge and elaborate design for reward shaping and model construction while ensuring the nature of merging tasks without excessive simplification. Numerical experiments are conducted to verify the optimality, adaptability, and self-learning ability of the proposed strategy. With comparison experiment, the proposed strategy surpasses state-of-the-art RL methods more than 13% in overall index throughput with 12% energy consumption while easing individual battery aging during the merging process.