Sharing information between connected and autonomous vehicles (CAVs) fundamentally improves the performance of collaborative object detection for self-driving. However, CAVs still have uncertainties on due to practical challenges, which will affect later modules in self-driving such as planning control. Hence, uncertainty quantification is crucial safety-critical systems CAVs. Our work first estimate detection. We propose a novel method, called Double- M Quantification, tailors moving block...

Object detection and multiple object tracking (MOT) are essential components of self-driving systems. Accurate uncertainty quantification both critical for onboard modules, such as perception, prediction, planning, to improve the safety robustness autonomous vehicles. Collaborative (COD) has been proposed accuracy reduce by leveraging viewpoints agents. However, little attention paid how leverage from COD enhance MOT performance. In this letter, first attempt address challenge, we design an...

Class <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$E^2$</tex-math></inline-formula> DC–DC converter composed of notation="LaTeX">$E$</tex-math></inline-formula> power amplifier (PA) and rectifier is a promising candidate for MHz wireless transfer. It soft-switching based able to achieve high efficiency at frequency. However, the implemented through traditional static design sensitive variations operation...

With the development of sensing and communication technologies in networked cyber-physical systems (CPSs), multi-agent reinforcement learning (MARL)-based methodologies are integrated into control process physical demonstrate prominent performance a wide array CPS domains, such as connected autonomous vehicles (CAVs). However, it remains challenging to mathematically characterize improvement CAVs with cooperation capability. When each individual vehicle is originally self-interest, we can...

The recent advancements in wireless technology enable connected autonomous vehicles (CAVs) to gather information about their environment by vehicle-to-vehicle (V2V) communication. In this work, we design an information-sharing-based multi-agent reinforcement learning (MARL) framework for CAVs, take advantage of the extra when making decisions improve traffic efficiency and safety. safe actor-critic algorithm propose has two new techniques: truncated <inline-formula...

Communication technologies enable coordination among connected and autonomous vehicles (CAVs). However, it remains unclear how to utilize shared information improve the safety efficiency of CAV system in dynamic complicated driving scenarios. In this work, we propose a framework constrained multi-agent reinforcement learning (MARL) with parallel Safety Shield for CAVs challenging scenarios that includes unconnected hazard vehicles. The mechanisms proposed MARL include sharing cooperative...

In real-world multi-agent reinforcement learning (MARL) applications, agents may not have perfect state information (e.g., due to inaccurate measurement or malicious attacks), which challenges the robustness of agents' policies. Though is getting important in MARL deployment, little prior work has studied uncertainties MARL, neither problem formulation nor algorithm design. Motivated by this issue and lack corresponding studies, we study with uncertainty work. We provide first attempt...

Various methods for Multi-Agent Reinforcement Learning (MARL) have been developed with the assumption that agents' policies are based on accurate state information. However, learned through Deep (DRL) susceptible to adversarial perturbation attacks. In this work, we propose a State-Adversarial Markov Game (SAMG) and make first attempt investigate different solution concepts of MARL under uncertainties. Our analysis shows commonly used optimal agent policy robust Nash equilibrium do not...

Reward design is a key component of deep reinforcement learning, yet some tasks and designer's objectives may be unnatural to define as scalar cost function. Among the various techniques, formal methods integrated with DRL have garnered considerable attention due their expressiveness flexibility reward requirements for different states actions agent. However, how leverage Signal Temporal Logic (STL) guide multi-agent learning remains unexplored. Complex interactions, heterogeneous goals...

Hybrid traffic which involves both autonomous and human-driven vehicles would be the norm of vehicles’ practice for a while. On one hand, unlike vehicles, could exhibit sudden abnormal behaviors such as unpredictably switching to dangerous driving modes—putting its neighboring under risks; undesired mode arise from numbers human driver factors, including fatigue, drunkenness, distraction, aggressiveness, so on. other modern vehicle-to-vehicle (V2V) communication technologies enable...

Behaviour-based distributed energy management for charging electric vehicles (EVs) in photovoltaic (PV) station (CS) has been introduced this paper. Based on the provider or consumer of power, CS and EVs are modeled as independent players with different preferences. The distribution problem is a noncooperative stackelberg game existence equilibrium among proofed at each control instant. Update Charging powers fashion implemented through utilising learning-based consensus network. Static...

To improve battery cell balancing speed, a novel switched capacitor (SC) circuit combining the conventional SC and optimized is proposed in this paper. It has advantage that speed independent of number increase as well initial voltage variation cells. The equivalent model developed analyzed Compared with circuit, doubled. Simulation comparisons under different numbers voltages cells are carried out PSIM environment. results show 82% 50% decrement time averagely compared respectively.

In recent years, there are more and situations that need robots to do dangerous complex works instead of human, improve the efficiency reduce risk. Path planning for multi-robot systems is one most important problems solve in practice. As improvements communication control technology robots, an algorithm proposed using Particle Swarm Optimization Critical Schedule Method path reach targets without collision not only between but also environment. Different from traditional method, a schedule...

As communication technologies develop, an autonomous vehicle will receive information not only from its own sensing system but also infrastructures and other vehicles through communication. This paper discusses how to exploit a sequence of future that is shared among vehicles, including the planned positions, velocities lane numbers. A hybrid model constructed, control policy designed utilize for making navigation decisions. For high-level discrete state transitions, used determine when...

This paper introduces a distributed energy management for islanded DC microgrids with electric vehicles (EVs) penetration. The problem is divided into two stages. first, named as filtering stage, controlled through wavelet filter using the ultracapacitor. second one modeled noncooperative stackelberg game, where battery storage system designed leader and EVs followers. preference of to extend its cycle life while each EV's maximize charging power. consensus network utilised reach Nash...

As various smart services are increasingly deployed in modern cities, many unexpected conflicts arise due to physical world couplings. Existing solutions for conflict resolution often rely on centralized control enforce predetermined and fixed priorities of different services, which is challenging the inconsistent private objectives services. Also, miss opportunities more effectively resolve according their spatiotemporal locality conflicts. To address this issue, we design a decentralized...

As various smart services are increasingly deployed in modern cities, many unexpected conflicts arise due to physical world couplings. Existing solutions for conflict resolution often rely on centralized control enforce predetermined and fixed priorities of different services, which is challenging the inconsistent private objectives services. Also, miss opportunities more effectively resolve according their spatiotemporal locality conflicts. To address this issue, we design a decentralized...

The recent advancements in wireless technology enable connected autonomous vehicles (CAVs) to gather information about their environment by vehicle-to-vehicle (V2V) communication. In this work, we design an information-sharing-based multi-agent reinforcement learning (MARL) framework for CAVs, take advantage of the extra when making decisions improve traffic efficiency and safety. safe actor-critic algorithm propose has two new techniques: truncated Q-function action mapping. utilizes shared...

Central task plays a vitally important role in all the work of university.Other should serve central for time being at each stage.The teaching and research university is long-term, complex, never-ending systematic work.In stage process, we locate accurately, arrange every coordinately considerate comprehensively.Based on understanding correctly, need to avoid error 'Only Task' focus main points Big Data era.In this way, can really do good job.Taking synthesis Hong Kong as an example, know...

This paper studies an energy management problem for isolated microgrid including photovoltaic panels, wind turbines, batteries and ultracapacitors. A normal form game is proposed the to maximize utilization ratio of renewable sources, extend battery life keep ultracapacitors able compensate dynamic variations. The solution this represented by Nash equilibrium analytically derived proved be existing unique. simulation platform using data in second established study approach based on...

Traditional botnet attacks leverage large and distributed numbers of compromised internet-connected devices to target overwhelm other with internet packets. With increasing consumer adoption high-wattage internet-facing "smart devices", a new "power botnet" attack emerges, where such are used power grid unusual load demand. We introduce variant this attack, the power-botnet weardown-attack, which does not intend cause blackouts or short-term acute instability, but instead forces expensive...

To promote the cooperation of Zhuhai-Macao in Big Data era, it is important not only to find out present critical problems and major reasons from complex history realities, but also put forward new feasible solutions based on numerous research results.We collect relevant information as much possible, build Research Database, take advantage mining technology such data attribute label, fragmentation, analysis statistics for mass data.Our recent drew conclusions that had same cultural root a...

This document explains and demonstrates how to redefine reclassify the Literature Review under Big Data environment.We compared three typical traditional definitions by Cooker, Fink Machi-McEvoy, found that their have not adapted present age.According new requirements about Review, we put forward a redefinition for it.Our includes 11 attributes, which are essence, objects, objectives, patterns or forms, procedures, requirements, results, contents, scope, significance technique.In addition,...