Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
11,847
result(s) for
"Automobile customizing"
Sort by:
A Hierarchical NMPC and TD3-Based Framework for Seamless Cruise-to-Park Automated Valet Parking
Automated valet parking requires reliable long-range slot searching and precise low-speed docking in confined structured lots. This paper proposes a hierarchical cruise-to-park framework that combines nonlinear model predictive control (NMPC) for predefined-route cruising with a Twin Delayed Deep Deterministic Policy Gradient (TD3) agent for terminal parking. The system is implemented in a structured Simulink environment with Unreal Engine-based geometry-aware sensing modules. During cruising, a camera-based module detects available slots and triggers the transition to parking. The NMPC uses a custom cost function to improve tracking on curved approaches, while the TD3 policy uses LiDAR feedback and reward shaping with an explicit time penalty to encourage efficient, stable docking. Simulation results demonstrate smooth phase transition, accurate cruising, and effective terminal parking in the training slot. Validation on six previously unseen target slots within the same parking-lot environment shows encouraging intra-lot target-slot transferability without retraining. Additional PPO and SAC comparisons and a time-penalty ablation further evaluate the relative learning performance and the effect of reward design, supporting the proposed architecture as a practical baseline for integrated cruise-to-park automated valet parking studies.
Journal Article
Vacant Parking Slot Detection in the Around View Image Based on Deep Learning
Due to the complex visual environment, such as lighting variations, shadows, and limitations of vision, the accuracy of vacant parking slot detection for the park assist system (PAS) with a standalone around view monitor (AVM) needs to be improved. To address this problem, we propose a vacant parking slot detection method based on deep learning, namely VPS-Net. VPS-Net converts the vacant parking slot detection into a two-step problem, including parking slot detection and occupancy classification. In the parking slot detection stage, we propose a parking slot detection method based on YOLOv3, which combines the classification of the parking slot with the localization of marking points so that various parking slots can be directly inferred using geometric cues. In the occupancy classification stage, we design a customized network whose size of convolution kernel and number of layers are adjusted according to the characteristics of the parking slot. Experiments show that VPS-Net can detect various vacant parking slots with a precision rate of 99.63% and a recall rate of 99.31% in the ps2.0 dataset, and has a satisfying generalizability in the PSV dataset. By introducing a multi-object detection network and a classification network, VPS-Net can detect various vacant parking slots robustly.
Journal Article
Forecasting the Demand for Electric Vehicles: Accounting for Attitudes and Perceptions
In the context of the arrival of electric vehicles on the car market, new mathematical models are needed to understand and predict the impact on the market shares. This research provides a comprehensive methodology to forecast the demand of a technology that is not widespread yet, such as electric cars. It aims at providing contributions regarding three issues related to the prediction of the demand for electric vehicles: survey design, model estimation, and forecasting. We develop a stated preferences (SP) survey with personalized choice situations involving standard gasoline/diesel cars and electric cars. We specify a hybrid choice model accounting for attitudes toward leasing contracts or practical aspects of a car in the decision-making process. A forecasting analysis based on the collected SP data and additional market information is performed to evaluate the future demand for electric cars.
Journal Article
Methodology of mixed load customized bus lines and adjustment based on time windows
Custom bus routes need to be optimized to meet the needs of a customized bus for personalized trips of different passengers. This paper introduced a customized bus routing problem in which trips for each depot are given, and each bus stop has a fixed time window within which trips should be completed. Treating a trip as a virtual stop was the first consideration in solving the school bus routing problem (SBRP). Then, the mixed load custom bus routing model was established with a time window that satisfies its requirement and the result were solved by Cplex software. Finally, a simple network diagram with three depots, four pickup stops, and five delivery stops was structured to verify the correctness of the model, and based on the actual example, the result is that all the buses ran 124.42 kilometers, the sum of kilometers was 10.35 kilometers less than before. The paths and departure times of the different busses that were provided by the model were evaluated to meet the needs of the given conditions, thus providing valuable information for actual work.
Journal Article
General two-level framework for demand-responsive transport optimization
This paper proposes a generalized optimization framework for demand-responsive transport (DRT), a modern form of transport organization in which services are planned and provided directly in response to the client demand. The developed framework has a two-level structure. The first level includes basic features essential to every DRT system. The second level takes into account the electric vehicle energy consumption and charging, predefined initial parts of vehicle routes for combining consecutive vehicle planning windows, as well as special passenger requests, such as a dedicated space for disabled people or Wi-Fi network availability. Three variants of models have been prepared, differing in how vehicles move between bus stops: freely point-to-point planning (General), restricted sections of the vehicle path (Sections) and fixed routes of every vehicle (Routes). During experiments, the developed model was thoroughly tested, in particular, its effectiveness in the basic version and with additional extensions was evaluated. The tests were performed on a dataset created based on the real public transport system of Rzeszow, Poland, from which 64 bus stops were mapped. The optimization process involved 200 passengers. The experiments confirmed the usefulness of the proposed solution.
Journal Article
Disassembly Automation for Recycling End-of-Life Lithium-Ion Pouch Cells
Rapid advances in the use of lithium-ion batteries (LIBs) in consumer electronics, electric vehicles, and electric grid storage have led to a large number of end-of-life (EOL) LIBs awaiting recycling to reclaim critical materials and eliminate environmental hazards. This article studies automatic mechanical separation methodology for EOL pouch LIBs with Z-folded electrode-separator compounds (ESC). Customized handling tools are designed, manufactured, and assembled into an automatic disassembly system prototype that consists of three modules. Verification experiments utilizing dummy cells prove that the main components of pouch LIBs (cathode sheets, anode sheets, separators, and polymer-laminated aluminum film housing) can be automatically separated and extracted with well-preserved integrity using our proposed disassembly strategy.
Journal Article
Bangladeshi Native Vehicle Classification Based on Transfer Learning with Deep Convolutional Neural Network
Vehicle type classification plays an essential role in developing an intelligent transportation system (ITS). Based on the modern accomplishments of deep learning (DL) on image classification, we proposed a model based on transfer learning, incorporating data augmentation, for the recognition and classification of Bangladeshi native vehicle types. An extensive dataset of Bangladeshi native vehicles, encompassing 10,440 images, was developed. Here, the images are categorized into 13 common vehicle classes in Bangladesh. The method utilized was a residual network (ResNet-50)-based model, with extra classification blocks added to improve performance. Here, vehicle type features were automatically extracted and categorized. While conducting the analysis, a variety of metrics was used for the evaluation, including accuracy, precision, recall, and F1 − Score. In spite of the changing physical properties of the vehicles, the proposed model achieved progressive accuracy. Our proposed method surpasses the existing baseline method as well as two pre-trained DL approaches, AlexNet and VGG-16. Based on result comparisons, we have seen that, in the classification of Bangladeshi native vehicle types, our suggested ResNet-50 pre-trained model achieves an accuracy of 98.00%.
Journal Article
An Initial Investigation of the Effects of a Fully Automated Vehicle Fleet on Geometric Design
This paper investigates the potential changes in the geometric design elements in response to a fully autonomous vehicle fleet. When autonomous vehicles completely replace conventional vehicles, the human driver will no longer be a concern. Currently, and for safety reasons, the human driver plays an inherent role in designing highway elements, which depend on the driver’s perception-reaction time, driver’s eye height, and other driver related parameters. This study focuses on the geometric design elements that will directly be affected by the replacement of the human driver with fully autonomous vehicles. Stopping sight distance, decision sight distance, and length of sag and crest vertical curves are geometric design elements directly affected by the projected change. Revised values for these design elements are presented and their effects are quantified using a real-life scenario. An existing roadway designed using current AASHTO standards has been redesigned with the revised values. Compared with the existing design, the proposed design shows significant economic and environmental improvements, given the elimination of the human driver.
Journal Article
Superior High‐Rate Ni‐Rich Lithium Batteries Based on Fast Ion‐Desolvation and Stable Solid‐Electrolyte Interphase
The fast charging‐discharging performance of power batteries has very practical significance. In terms of electrochemistry, this requires fast and stable kinetics for electrochemical reaction processes. Despite the great complexity of kinetics, it is clear that lithium‐ion desolvation and a subsequent step of crossing through cathode‐electrolyte interphase (CEI) are crucial to high‐rate performance, in which the two key steps depend heavily on the working electrolyte formula. In this work, a customized electrolyte is developed to coordinate ion desolvation and interphase formation by introducing vinylene carbonate (VC), triphenylboroxin (TPBX), and fluoroethylene carbonate (FEC) but excluding ethylene carbonate (EC). Serving Ni‐rich cathodes, the customized electrolyte generates a double‐layered CEI, LiF‐dominated inorganics inner layer, and ROCOOLi‐dominated organics outer layer, which is not only stable and very efficient for lithium ion transport. Meanwhile, a PF6− ${\\mathrm{PF}}_6^ - $ ‐dominated solvation structure is induced and effectively decreases the desolvation energy to 29.72 kJ mol−1, supporting fast lithium ion transport in the cathode interfacial processes. Consequently, the Ni‐rich lithium‐ion battery achieves a stable long cycle at a superior high rate of 10 C. A customized electrolyte for coordinating ion desolvation and interphase formation of superior high‐rate Ni‐rich lithium batteries is developed. A stable double‐layered CEI is generated, and a PF6− ${\\mathrm{PF}}_6^ - $ ‐dominated solvation structure is induced to effectively decrease the desolvation energy, both of which support fast lithium ion transport in the cathode interfacial processes.
Journal Article