Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1097/MLR.0000000000000094 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Game-Theoretic Motion Planning with Perception Uncertainty and Right-of-Way Constraints.
Sensors (Basel)
December 2024
Mechanical and Mechatronics Engineering Department, University of Waterloo, 200 University Ave W, Waterloo, ON N2L 3G1, Canada.
This paper addresses two challenges in AV motion planning: adherence to right-of-way and handling uncertainties, using two game-theoretic frameworks, namely Stackelberg and Nash Bayesian (Bayesian). By modeling the interactions between road users as a hierarchical relationship, the proposed approach enables the AV to strategically optimize its trajectory while considering the actions and priorities of other road users. Additionally, the Bayesian equilibrium aspect of the framework incorporates probabilistic beliefs and updates them based on sensor measurements, allowing the AV to make informed decisions in the presence of uncertainty in the sensory system.
View Article and Find Full Text PDFA Framework for Optimizing Deep Learning-Based Lane Detection and Steering for Autonomous Driving.
Sensors (Basel)
December 2024
School of Computing and Information Science, Anglia Ruskin University, Cambridge CB1 1PT, UK.
Improving the ability of autonomous vehicles to accurately identify and follow lanes in various contexts is crucial. This project aims to provide a novel framework for optimizing a self-driving vehicle that can detect lanes and steer accordingly. A virtual sandbox environment was developed in Unity3D that provides a semi-automated procedural road and driving generation framework for a variety of road scenarios.
View Article and Find Full Text PDFTime-Series Representation Feature Refinement with a Learnable Masking Augmentation Framework in Contrastive Learning.
Sensors (Basel)
December 2024
School of Electrical Engineering, Korea University, Seoul 02841, Republic of Korea.
In this study, we propose a novel framework for time-series representation learning that integrates a learnable masking-augmentation strategy into a contrastive learning framework. Time-series data pose challenges due to their temporal dependencies and feature-extraction complexities. To address these challenges, we introduce a masking-based reconstruction approach within a contrastive learning context, aiming to enhance the model's ability to learn discriminative temporal features.
View Article and Find Full Text PDFMaximizing Nano-Silica Efficiency in Laboratory-Simulated Recycled Concrete Aggregate via Prior Accelerated Carbonation: An Effective Strategy to Up-Cycle Construction Wastes.
Molecules
December 2024
School of Civil Engineering, Putian University, Putian 351100, China.
Herein, the study explores a composite modification approach to enhance the use of recycled concrete aggregate (RCA) in sustainable construction by combining accelerated carbonation (AC) and nano-silica immersion (NS). RCA, a major source of construction waste, faces challenges in achieving comparable properties to virgin aggregates. Nano-silica, a potent pozzolan, is added to fill micro-cracks and voids in RCA, improving its bonding and strength.
View Article and Find Full Text PDFColloid-Forming Prodrug-Hydrogel Composite Prolongs Lower Intraocular Pressure in Rodent Eyes after Subconjunctival Injection.
Adv Mater
January 2025
Department of Chemical Engineering & Applied Chemistry, University of Toronto, 200 College Street, Toronto, ON, M5S 3E5, Canada.
Colloidal drug aggregates (CDAs) are challenging in drug discovery due to their unpredictable formation and interference with screening assays. These limitations are turned into a strategic advantage by leveraging CDAs as a drug delivery platform. This study explores the deliberate formation and stabilization of CDAs for local ocular drug delivery, using a modified smallmolecule glaucoma drug.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!