This paper proposes a Linear Parameter Varying (LPV) based steering control design method, which contains data aided control elements, e.g., learning-based agents. The framework is based on a supervisory control struc...
This paper proposes a Linear Parameter Varying (LPV) based steering control design method, which contains data aided control elements, e.g., learning-based agents. The framework is based on a supervisory control structure, which contains a supervisor, a LPV controller and the data aided control element. The goal of this paper is to provide a safe steering control, with which the human steering intervention can be effectively imitated. Moreover, in the proposed framework the data aided control can be adapted to the actual requirements on driving style, without re-designing the LPV control. Thus, a general control structure with performance guarantees on path following constraints is provided, in which the data aided steering control element can be varied. The effectiveness of the proposed method through driver-in-the-loop scenarios is illustrated, in which different settings on the control system are analyzed.
The paper discusses a data science competition centered around the development of an anomaly detection system for IoT devices. The competition utilized a unique environment that allowed for the operation and monitorin...
详细信息
With rapid urban population growth and urban-ization, along with increasing demand for developing the low- altitude economy, urban air mobility (UAM) is seen as a way to alleviate ground traffic congestion and promote...
详细信息
ISBN:
(数字)9798350377675
ISBN:
(纸本)9798350377682
With rapid urban population growth and urban-ization, along with increasing demand for developing the low- altitude economy, urban air mobility (UAM) is seen as a way to alleviate ground traffic congestion and promote the low-altitude economy. Due to frequent data computation, low latency require-ments, and limited energy, effective computation offloading and resource management are urgently needed. This paper assumes UAM aircraft transmit semantic information and proposes a computation offloading and resource allocation strategy based on edge computing (EC). In case of edge server failure, relay UAV s assist in information transmission, enabling UAM aircraft to offload tasks to other edge servers. We formulated an op-timization problem to minimize delay and energy consumption and designed the Federated- Td3algorithm, combining federated learning (FL) and twin delayed deep deterministic policy gradient (TD3). Compared to two baseline algorithms, our algorithm reduced delay by 9.9% and 3.3%, and energy consumption by 14.1 % and 4.5%.
Indoor mobile robots require reliable solutions for mapping, localization, and navigation tasks. This paper presents a mobile robot system that implements the ability to realize mapping using visual SLAM with ORB-SLAM...
详细信息
This paper is devoted to the development and research of a new compression technology based on Weyl-Heisenberg bases (WH-technology) for modifying the JPEG compression standard and improving its characteristics. For t...
详细信息
This paper presents a data-driven state feedback control law, based on a linear quadratic regulator (LQR) design, for systems with exogenous inputs. In general, this framework is referred to as a data-driven min-max c...
详细信息
ISBN:
(数字)9781665406734
ISBN:
(纸本)9781665406741
This paper presents a data-driven state feedback control law, based on a linear quadratic regulator (LQR) design, for systems with exogenous inputs. In general, this framework is referred to as a data-driven min-max controller, and is more robust to disturbances than the standard LQR controllers. Instead of relying on system models, in this work, the state feedback control law is computed directly from the knowledge of the inputs and the states. The LQR gain is parametrized with matrices that are directly estimated using open-loop experiment data of the system. We experimentally validate our results by implementing the data driven controller for performance management of a web-server hosted on a private cloud.
To achieve low joint-angle drift and avoid mutual collision between dual redundant manipulators (DRMs) when they are doing collaboration works, a recurrent neural network based bicriteria repetitive motion collision a...
详细信息
This research focuses on controlling the motion trajectory of autonomous vehicles by using a combination of two high-performance control methods: Linear Parameter Varying (LPV) and Reinforcement Learning (RL). First, ...
详细信息
One major goal of digital twin technology applied in the Architecture, Engineering, and Construction (AEC) Industry is the mapping of roads and road environments with their associated information. Such digital twins c...
One major goal of digital twin technology applied in the Architecture, Engineering, and Construction (AEC) Industry is the mapping of roads and road environments with their associated information. Such digital twins can support cost-effective testing, simulations, and the production of mapping backgrounds for automated vehicles and generally for Cooperative, Connected and Automated Mobility (CCAM) developments. The efficient workflow that leads from data acquisition to finished products depends on a number of requirements and knowledge sets. The main contribution of the paper is a general methodology of creating HD-map from point cloud and image data set. Accordingly, the most widely used survey techniques are presented and the requirements for the objects to be derived are summarized. The paper then outlines a general implementation procedure as an expert knowledge through a real-life example, where the results obtained for the ZalaZONE Automotive Proving Ground are demonstrated.
Provable data possession (PDP) is a crucial means of protecting the integrity of data in the domain of cloud storage. In the post-quantum era, the PDP scheme that uses lattices relies too heavily on the third-party au...
详细信息
暂无评论