Real-Time Dynamic Map With Crowdsourcing Vehicles in Edge Computing

Keyphrases

• Crowdsourcing 100%
• Edge Computing 100%
• Real-time Dynamics 100%
• Dynamic Map 100%
• Latency 50%
• Network Dynamics 50%
• Automated Vehicles 50%
• Connected Vehicles 50%
• Autonomous Driving 50%
• Network Simulation 50%
• Reinforcement Learning Algorithm 50%
• Network Simulator 50%
• Deep Reinforcement Learning (deep RL) 50%
• Latency Performance 50%
• Edge Network 50%
• Control Plane 50%
• Physical Network 50%
• Global Information 50%
• Individual Vehicle 50%
• Vehicle Data 50%
• Performance-based 50%
• Environmental Uncertainty 50%
• Physical Testbed 50%
• Sequential Computation 50%
• Vehicular Edge Computing 50%
• Perception Data 50%
• Real-time Perception 50%
• Extensive Evaluation 50%
• Coverage Performance 50%
• Line-of-sight Sensor 50%
• Vehicular Offloading 50%
• High-Density Microarray Patch (HD-MAP) 50%

Computer Science

• Edge Computing 100%
• Testbed 50%
• Autonomous Driving 50%
• High Definition 50%
• Deep Reinforcement Learning 50%
• Network Simulation 50%
• Network Simulator 50%
• Learning Technique 50%
• Global Information 50%
• Control Plane 50%
• Network Dynamic 50%