This paper considers the use of deep learning models to enhance optimization algorithms for transit network design. Transit network design is the problem of determining routes for transit vehicles that minimize travel...
详细信息
ISBN:
(纸本)9798350399462
This paper considers the use of deep learning models to enhance optimization algorithms for transit network design. Transit network design is the problem of determining routes for transit vehicles that minimize travel time and operating costs, while achieving full service coverage. State-of-the-art meta-heuristic search algorithms give good results on this problem, but can be very time-consuming. In contrast, neural networks can learn sub-optimal but fast-to-compute heuristics based on large amounts of data. Combining these approaches, we develop a fast graph neural network model for transit planning, and use it to initialize state-of-the-art search algorithms. We show that this combination can improve the results of these algorithms on a variety of metrics by up to 17%, without increasing their run time;or they can match the quality of the original algorithms while reducing the computing time by up to a factor of 50.
In this study, we propose a novel approach for investigating optimization performance by flexible robot coordination in automated warehouses with multi-agent reinforcement learning (MARL)-based control. Automated syst...
详细信息
ISBN:
(纸本)9781665491907
In this study, we propose a novel approach for investigating optimization performance by flexible robot coordination in automated warehouses with multi-agent reinforcement learning (MARL)-based control. Automated systems using robots are expected to achieve efficient operations compared with manual systems in terms of overall optimization performance. However, the impact of overall optimization on performance remains unclear in most automated systems due to a lack of suitable control methods. Thus, we proposed a centralized training-and-decentralized execution MARL framework as a practical overall optimization control method. In the proposed framework, we also proposed a single shared critic, trained with global states and rewards, applicable to a case in which heterogeneous agents make decisions asynchronously. Our proposed MARL framework was applied to the task selection of material handling equipment through automated order picking simulation, and its performance was evaluated to determine how far overall optimization outperforms partial optimization by comparing it with other MARL frameworks and rule-based control methods.
This study proposes an enhanced wireless 6G communications architecture for context-aware systems to enable adaptive u-learning environments for music education. A centralised data processing centre at edge nodes anal...
详细信息
This study proposes an enhanced wireless 6G communications architecture for context-aware systems to enable adaptive u-learning environments for music education. A centralised data processing centre at edge nodes analyses user behaviours and network conditions to enable coordinated control across the core network, transport network, and radio access network, which fully exploits the feature of edge intelligence. The architecture supports self-consistent capabilities within each network function entity and flexible multi-level couplings between entities based on real-time user needs. For radio resource management, an AI-driven intelligentcontroller is introduced to enable intelligent and automated management of wireless resources. Experiments compared learning effectiveness between groups with and without the proposed enhanced 6G context-aware capabilities in an adaptive u-learning music learning environment. Results demonstrated significantly improved task completion times and learning accuracy with the 6G-enhanced context-aware system in adaptive u-learning environments for music education via edge intelligence.
Due to the complex interactions between agents, learning multi-agent control policy often requires a prohibitive amount of data. This paper aims to enable multi-agent systems to effectively utilize past memories to ad...
详细信息
ISBN:
(纸本)9798350377712;9798350377705
Due to the complex interactions between agents, learning multi-agent control policy often requires a prohibitive amount of data. This paper aims to enable multi-agent systems to effectively utilize past memories to adapt to novel collaborative tasks in a data-efficient fashion. We propose the Multi-Agent Coordination Skill Database, a repository for storing a collection of coordinated behaviors associated with key vectors distinctive to them. Our Transformer-based skill encoder effectively captures spatio-temporal interactions that contribute to coordination and provides a unique skill representation for each coordinated behavior. By leveraging only a small number of demonstrations of the target task, the database enables us to train the policy using a dataset augmented with the retrieved demonstrations. Experimental evaluations demonstrate that our method achieves a significantly higher success rate in push manipulation tasks compared with baseline methods like few-shot imitation learning. Furthermore, we validate the effectiveness of our retrieve-and-learn framework in a real environment using a team of wheeled robots.
The CoM-ZMP model represents the dominant behaviour of bipedal locomotion with surface contact. However, once the centre of mass (CoM) position goes out of a predefined spatial plane, the horizontal dynamics of the mo...
详细信息
ISBN:
(纸本)9798350377712;9798350377705
The CoM-ZMP model represents the dominant behaviour of bipedal locomotion with surface contact. However, once the centre of mass (CoM) position goes out of a predefined spatial plane, the horizontal dynamics of the model can couple with its vertical dynamics to be nonlinear. This study theoretically investigates the properties of the 3-dimensional zero moment point (ZMP), lying apart from the actual ground to resolve the coupling. The presented discussion includes the compatibility of the 3D ZMP with ZMPs used in preceding research, such as the linear inverted pendulum mode, the existence of a virtual repellent point considering the arbitrary vertical CoM motion, the parameter invariance of the CoM-ZMP model, and feasible regions of the ZMP.
Digital Twin is an emerging innovative technology that can be used in the era of Industry 4.0 and Generative AI, where both the physical assets and digital technology worlds meet. The virtual replicas of physical asse...
详细信息
This paper introduces a control architecture for real-time and onboard control of Unmanned Aerial Vehicles (UAVs) in environments with obstacles using the Model Predictive Path Integral (MPPI) methodology. MPPI allows...
详细信息
ISBN:
(纸本)9798350377712;9798350377705
This paper introduces a control architecture for real-time and onboard control of Unmanned Aerial Vehicles (UAVs) in environments with obstacles using the Model Predictive Path Integral (MPPI) methodology. MPPI allows the use of the full nonlinear model of UAV dynamics and a more general cost function at the cost of a high computational demand. To run the controller in real-time, the sampling-based optimization is performed in parallel on a graphics processing unit onboard the UAV. We propose an approach to the simulation of the nonlinear system which respects low-level constraints, while also able to dynamically handle obstacle avoidance, and prove that our methods are able to run in real-time without the need for external computers. The MPPI controller is compared to MPC and SE(3) controllers on the reference tracking task, showing a comparable performance. We demonstrate the viability of the proposed method in multiple simulation and real-world experiments, tracking a reference at up to 44 km h(-1) and acceleration close to 20 m s(-2), while still being able to avoid obstacles. To the best of our knowledge, this is the first method to demonstrate an MPPI-based approach in real flight.
In Industry 4.0, achieving semantic interoperability is a significant problem due to the complexities of current automation systems and the numerous standards involved. The study explores how Artificial Intelligence (...
详细信息
ISBN:
(纸本)9798350361261;9798350361278
In Industry 4.0, achieving semantic interoperability is a significant problem due to the complexities of current automation systems and the numerous standards involved. The study explores how Artificial Intelligence (AI) and semantic interoperability connect within the Internet of Things (IoT) framework to overcome barriers to technology adoption. The main goal is to analyze how AI's adaptive and predictive abilities might transform semantic interoperability by studying AI-driven methodologies to provide a flexible and efficient solution. The main objective of the paper is to leverage Named Entity Recognition (NER) AI models to streamline the identification of entities within the Internet of Things (IoT) for achieving semantic interoperability. It tests a Natural Language Processing (NLP) translator on data representations not seen during training, and the outcome highlights the efficiency of NLP in correctly understanding and processing these representations.
This paper designs a novel trajectory planning approach to resolve the computational efficiency and safety problems in uncoordinated methods by exploiting vehicle-to-everything (V2X) technology. The trajectory plannin...
详细信息
This paper presents a discrete predictive controller for a class of discrete time-delayed systems. The most time-delayed system, especially a highly unstable unmanned helicopter, has severe difficulties in stability a...
详细信息
ISBN:
(纸本)9798350355376;9798350355369
This paper presents a discrete predictive controller for a class of discrete time-delayed systems. The most time-delayed system, especially a highly unstable unmanned helicopter, has severe difficulties in stability and performance. Furthermore, the presence of disturbance more critically affects the stability of time-delayed systems since the delayed control input may lose the ability to stabilize the state. The proposed controller employs precise prediction of the future state, incorporating exponential stability for predicting future disturbance. In particular, the proposed state prediction can effectively compensate for disturbance effects without any robust control terms. The performance of the proposed controller is validated by numerical simulations. The results can verify the feasibility and performance of the proposed controller in the presence of significant time delay for the unmanned helicopter.
暂无评论