Accurate prediction of agent motion trajectories is crucial for ensuring the safety and reliability of autonomous driving systems. Current research predominantly focuses on traditional deep learning methods, including...
详细信息
This paper investigates the pursuit-evasion problem involving one evader and multiple pursuers with limited sensing capability, where the evader tries to maximize the distance with the pursuers, while the pursuers hav...
This paper investigates the pursuit-evasion problem involving one evader and multiple pursuers with limited sensing capability, where the evader tries to maximize the distance with the pursuers, while the pursuers have different objectives based on whether they can receive the information of the evader. The subgroup of pursuers who can observe the evader(called leaders) tries to be close to the evader, and the other subgroup of pursuers(called followers) tries to synchronize with their neighbors. When the subgraph formed by all leaders is complete, sufficient conditions are given to guarantee that the pursuers capture the evader and the pursuit-evasion game composed of the evader and leaders reaches Nash equilibrium. Furthermore, for the incomplete subgraph case, the distributed observers are proposed to estimate the relative positions between the evader and all leaders. It is shown that the distributed control strategy based on the observers converges exponentially to the Nash equilibrium solution, and makes the pursuers capture the evader. Finally, simulation examples are provided to verify the effectiveness of the proposed strategies.
The method [K]control of Adaptive Multiple-timescale systems (KAMS) has been used as a method of adaptive control for systems with states that evolve at vastly different rates and with uncertain parameters. Prior rese...
详细信息
This article focuses on discussing the effects of inter-vehicular communication on the performance of platoon control. Different from the existing results established under a critical assumption that the fading channe...
详细信息
Electronic medical records and doctor-patient conversations contain a wealth of useful information, such as disease symptoms, drug names, and cure cycles. Traditional deep learning approaches utilize bidirectional rec...
详细信息
Car-following is the most common driving scenario where a following vehicle follows a lead vehicle in the same lane. One crucial factor of car-following behavior is driving style which affects speed and gap selection,...
详细信息
Car-following is the most common driving scenario where a following vehicle follows a lead vehicle in the same lane. One crucial factor of car-following behavior is driving style which affects speed and gap selection, acceleration pattern, and fuel consumption. However, existing car-following research used limited categories of driving style through pre-defined patterns and failed to encode driving style into data-driven car-following models. To address these limitations, we propose the Aggressiveness Informed Car-Following (AICF) modeling approach, which embeds driving style as a dynamic input feature in data-driven car-following models. In detail, We design driving aggressiveness tokens using four physical quantities (jerk, acceleration, relative speed, and relative spacing) to capture the heterogeneity of driving aggressiveness. These tokens were then embedded into a physics-informed Long Short-Term Memory (LSTM) based car-following model for trajectory prediction. To evaluate the effectiveness of our approach, we conducted extensive experiments based on 12,540 car-following events extracted from the HighD dataset and 24,093 events from the Lyft dataset. Compared to models devoid of considerations for driving aggressiveness levels, AICF exhibits superior efficacy in mitigating the Mean Square Error (MSE) of spacing and collision rate. To the best of our knowledge, this is the first work to directly incorporate real-time driving aggressiveness tokens as input features into data-driven car-following models, enabling a more comprehensive understanding of aggressiveness in car-following behavior. IEEE
Cloud-based energy management systems (EMS) in smart grids face privacy challenges, as existing methods based on traditional homomorphic encryption support limited operations and are vulnerable to quantum attacks. We ...
详细信息
The evaluation of regional geological hazard susceptibility is of great significance to the prevention and control of geological hazard. In this paper, the "4-20"Lushan earthquake disaster area as the resear...
详细信息
Optimal control of constrained unmanned aerial vehicle (UAV) trajectory optimization problem is one of the frontiers and hotspots of UAV research. The various constraints generated by physical limitations and obstacle...
详细信息
Trust evaluation and trust establishment play crucial roles in the management of trust within a multi-agent system. When it comes to collaboration systems, trust becomes directly linked to the specific roles performed...
详细信息
暂无评论