A5091579598- Autonomous Vehicle Technology and Safety
- Fire effects on concrete materials
- Fire dynamics and safety research
- Traffic control and management
- Reinforcement Learning in Robotics
- Robotic Path Planning Algorithms
- Head and Neck Cancer Studies
- Structural Response to Dynamic Loads
- Brain Metastases and Treatment
- Structural Load-Bearing Analysis
- Nanoplatforms for cancer theranostics
- Smart Parking Systems Research
- Neural Networks Stability and Synchronization
- Lung Cancer Research Studies
- Head and Neck Surgical Oncology
- Radiomics and Machine Learning in Medical Imaging
- Hepatocellular Carcinoma Treatment and Prognosis
- Chaos control and synchronization
- Robotics and Sensor-Based Localization
- Infrared Thermography in Medicine
- Peptidase Inhibition and Analysis
- Boron Compounds in Chemistry
- Vehicular Ad Hoc Networks (VANETs)
- Molecular Sensors and Ion Detection
- Photodynamic Therapy Research Studies
Changsha University
2024
Tongji University
2019-2024
Hunan Cancer Hospital
2015-2024
Central South University
2015-2024
Sun Yat-sen University
2023
Sun Yat-sen University Cancer Center
2023
Beihang University
2019
China University of Petroleum, Beijing
2016
Shenyang University of Technology
2014
North Minzu University
2012-2013
Through vehicle-to-vehicle (V2V) communication, autonomizing a vehicle platoon can significantly reduce the distance between vehicles, thereby reducing air resistance and improving road traffic efficiency. The gradual maturation of control technology is enabling platoons to achieve basic driving functions, permitting large-scale scheduling planning, which essential for industrialized applications generates significant economic benefits. Scheduling planning are required in many aspects...
Motion planning for autonomous racing is a challenging task due to the safety requirement while driving aggressively. Most previous solutions utilize prior information or depend on complex dynamics modeling. Classical model-free reinforcement learning methods are based random sampling, which severely increases training consumption and undermines exploration efficiency. In this letter, we propose an efficient residual policy method high-speed named ResRace, leverages only real-time raw...
With the process of urbanization, problem insufficient parking spaces has become prominent. Adopting a high-density lot with robots can greatly improve land utilization rate lot. This article tackles multiple scheduling layout lots, including task execution sequence decision, robot allocation, and cooperative path planning. First, we mathematically describe problem. Existing approximation algorithms are often far from optimal solution. proposes an improved genetic algorithm time-enhanced A*...
The research focus of this paper is to improve the traditional A-star algorithm meet needs autonomous vehicles for path safety and smoothness. First, improved considers factor obstacle distance in heuristic function. This allows strike a balance between length security, as well avoiding searching redundant nodes that are too close obstacles. Besides, expansion mode 8-connection 20-connection, so sharpness turning at corner can be greatly reduced. And because there enough planned obstacles,...
Autonomous driving is a promising technology to reduce traffic accidents and improve efficiency. Although significant progress has been achieved, existing decision-making systems of autonomous vehicle still cannot meet the safety efficiency requirements in highly dynamic environments. In this work, we design discrete strategy based on soft actor-critic with sample filter algorithm (DSAC-SF) freeways dynamics traffic. Specifically, first propose method for actor-critic, which improves...
Accurate localization is an important component for the vehicle's autonomous navigation. The appearance of moving objects may lead to feature-matching error with map features, thereby causing a serious decline accuracy. Neuromorphic vision sensor (NeuroIV) kind dynamic sensor, properties high temporal resolution, movement capture, and lightweight computation. In view this, this research proposes combine NeuroIV LIDAR points acquire static landmark features robust navigation localization....
Rule-based traditional motion planning methods usually perform well with prior knowledge of the macro-scale environments but encounter challenges in unknown and uncertain environments. Deep reinforcement learning (DRL) is a solution that can effectively deal micro-scale Nevertheless, DRL unstable lacks interpretability. Therefore, it raises new challenge: how to combine effectiveness overcome drawbacks two while guaranteeing stability In this study, multi-constraint multi-scale method...
The first red AIE property fluorescent probe was used to detect endogenous and exogenous carbon monoxide.
Anticancer drug development is important for human health, yet it remains a tremendous challenge. Photodynamic therapy (PDT), which induces cancer cell apoptosis via light-triggered production of reactive oxygen species, promising method. However, has minimal efficacy in subcellular targeting, hypoxic microenvironments, and deep-seated malignancies. Here, we constructed breast photo-activable theranostic nanosystem through the rational design synthetic lysosomal-targeted molecule with...
Industries, such as manufacturing, are accelerating their embrace of the metaverse to achieve higher productivity, especially in complex industrial scheduling. In view growing parking challenges large cities, high-density vehicle spatial scheduling is one potential solutions. Stack-based lots utilize robots densely park vehicles vertical stacks like container stacking, which greatly reduces aisle area lot, but requires algorithms and take out vehicles. The existing (HDP) mainly heuristic...
Abstract Background Previous studies have demonstrated conflicting findings regarding the initial MRI patterns of radiotherapy-induced temporal lobe injury (RTLI) and evolution different RTLI patterns. The aim this study was to evaluate pattern in patients with nasopharyngeal carcinoma (NPC) by means a large cohort study. Methods Data were retrospectively collected from two hospitals between January 2011 December 2021. injured lobes categorized into three based on patterns: isolated white...
This paper discloses an early performed study on the fire-resistance design framework for cable-stayed bridges, including (1) identification of potential fire scenarios and calculation return periods, (2) computational fluid dynamics simulation environment analytical models flame dimensions, (3) coupling thermomechanical finite element to capture bridge response, (4) determination prevention protection measures. The was then utilized a two-level steel bridge. periods vehicle fires upper,...
Offline reinforcement learning (RL) algorithms promise to learn policies directly from offline data sets without environmental interaction. This arrangement enables successful RL applications in the real world, particularly robots and autonomous driving, where sampling is costly dangerous. However, existing suffer insufficient performance attributed extrapolation error caused by out-of-distribution (OOD) actions. In this work, we propose an algorithm with uncertain action constraint (UAC)....
Anticipating the trajectory of Autonomous Vehicles (AV) plays an important role in improving its driving safety. With rapid development learning-based method recent years, long short-term memory (LSTM) network for sequential data has achieved great success forecasting. However, previous LSTM only considered forward time cues and did not reason on motion intent rational agents. In this paper, we use planning-based methods follow a sense-reason-predict scheme which agents about intentions...
PURPOSE Tumor stage is crucial for prognostic evaluation and therapeutic decisions in locally advanced nasopharyngeal carcinoma (NPC) but imprecise. We aimed to propose a new system by integrating quantitative imaging features clinical factors. MATERIALS AND METHODS This retrospective study included 1,319 patients with III-IVa NPC between April 1, 2010, July 31, 2019, who underwent pretherapy magnetic resonance (MRI) received concurrent chemoradiotherapy or without induction chemotherapy....