The Experts below are selected from a list of 327 Experts worldwide ranked by ideXlab platform
Alessandro Rucco - One of the best experts on this subject based on the ideXlab platform.
-
ECC - A moving path following approach for trajectory optimization of UAVs: An application for Target tracking of marine Vehicles
2016 European Control Conference (ECC), 2016Co-Authors: Alessandro Rucco, A. Pedro Aguiar, Fernando Lobo Pereira, Joao Borges De SousaAbstract:In this paper we propose a novel numerical approach to the design of smooth trajectories for fixed-wing Unmanned Aerial Vehicles (UAVs) with applications to Target tracking of marine Vehicles. Given a desired geometric path with respect to a possible moving Target Vehicle, we are interested in computing a feasible UAV trajectory that best approximates in L 2 sense the desired geometric moving path with a specified airspeed profile assigned on it. Due to communication range limitations (e.g., the UAV is operating as a wireless communication relay between a Target Vehicle and a ground station), the UAV trajectory needs to satisfy given path constraints. Space-varying wind is also taken into account. We address this problem by taking a Virtual Target Vehicle (VTV) perspective. We set up a suitable optimal control problem based on the error coordinates between the UAV and the VTV. We solve the optimal control problem numerically by using PRONTO, a very versatile control optimization tool enabling to deal with a wide variety of trajectory functionals and constraints. We provide and discuss numerical computations based on a practical scenario where an Autonomous Surface Vehicle (the Target Vehicle) transmits data to the UAV which sends them back to a ground station.
-
trajectory optimization for constrained uavs a virtual Target Vehicle approach
International Conference on Unmanned Aircraft Systems, 2015Co-Authors: Alessandro Rucco, Pedro A Aguiar, J HauserAbstract:In this paper we propose a novel approach for trajectory optimization for constrained Unmanned Aerial Vehicles (UAVs). With regard to the classical trajectory optimization problem, we take a Virtual Target Vehicle (VTV) perspective by introducing a virtual Target that plays the role of an additional control input. Based on a nonlinear projection operator optimal control technique and extending the concepts of the maneuver regulation framework, we propose a trajectory optimization based strategy to compute, for any given desired path with a specified desired speed profile, the (local) optimal feasible trajectory that best approximates the desired one. The optimization procedure takes explicitly into account the extra flexibility of the VTV by changing (during the transient period) the velocity of the virtual Target with the benefit of improving the convergence of the solver to obtain the optimal feasible path, and also avoid the singularities that occur in some maneuver regulation techniques described in the literature. We provide numerical computations for three testing scenarios that illustrates the effectiveness of the proposed strategy.
Joao Borges De Sousa - One of the best experts on this subject based on the ideXlab platform.
-
ECC - A moving path following approach for trajectory optimization of UAVs: An application for Target tracking of marine Vehicles
2016 European Control Conference (ECC), 2016Co-Authors: Alessandro Rucco, A. Pedro Aguiar, Fernando Lobo Pereira, Joao Borges De SousaAbstract:In this paper we propose a novel numerical approach to the design of smooth trajectories for fixed-wing Unmanned Aerial Vehicles (UAVs) with applications to Target tracking of marine Vehicles. Given a desired geometric path with respect to a possible moving Target Vehicle, we are interested in computing a feasible UAV trajectory that best approximates in L 2 sense the desired geometric moving path with a specified airspeed profile assigned on it. Due to communication range limitations (e.g., the UAV is operating as a wireless communication relay between a Target Vehicle and a ground station), the UAV trajectory needs to satisfy given path constraints. Space-varying wind is also taken into account. We address this problem by taking a Virtual Target Vehicle (VTV) perspective. We set up a suitable optimal control problem based on the error coordinates between the UAV and the VTV. We solve the optimal control problem numerically by using PRONTO, a very versatile control optimization tool enabling to deal with a wide variety of trajectory functionals and constraints. We provide and discuss numerical computations based on a practical scenario where an Autonomous Surface Vehicle (the Target Vehicle) transmits data to the UAV which sends them back to a ground station.
Chengliang Yin - One of the best experts on this subject based on the ideXlab platform.
-
Lateral State Estimation of Preceding Target Vehicle Based on Multiple Neural Network Ensemble
2019 IEEE Intelligent Vehicles Symposium (IV), 2019Co-Authors: Yafei Wang, Zhisong Zhou, Wenqiang Jin, Chengliang YinAbstract:Preceding Target Vehicle (PTV) motion recognition play a pivotal role in autonomous Vehicles. Motion states such as yaw rate, longitudinal and lateral velocity are critical for ego Vehicle decision-making and control. However, lateral states of a PTV can hardly be measured directly by common onboard sensors and the PTV lateral state estimation has been seldom addressed in existing literatures. In this paper, a novel estimation scheme based on multiple neural network ensemble is proposed for PTV lateral state estimation. First, PTV lateral kinematics is presented based on Vehicle-road relationship and a novel PTV lateral motion model is constructed to interpret the PTV lateral motion. Then, neural network observer with the PTV lateral kinematics as prior knowledge is designed and training data are collected in simulation environment. The neural network observer is trained using Levenberg-Marquardt backpropagation with Bayesian regularization (LMBR) to improve the generalization capability. Finally, to further improve the performance of the neural network estimation method, multiple neural network observers are integrated by weighted averaging strategy. The effectiveness of proposed approach is verified through hardware-in-the-Ioop (HiL) experiments conducted in designed verification scenarios, and compared with model-based method and other three learning methods. The experiment results reveal that the proposed method outperforms other typical methods and achieves accurate estimation of the PTV lateral states.
-
Host–Target Vehicle Model-Based Lateral State Estimation for Preceding Target Vehicles Considering Measurement Delay
IEEE Transactions on Industrial Informatics, 2018Co-Authors: Yafei Wang, Zhisong Zhou, Chongfeng Wei, Yahui Liu, Chengliang YinAbstract:Automated Vehicle control requires full knowledge of motion behavior of the preceding Target Vehicles (PTVs), and the states such as longitudinal/lateral velocity and yaw rate are critical for the PTV behavior description. However, the PTV's lateral states estimation have seldom been addressed in the state-of-the-art literatures. Aimed at providing reliable PTV lateral states, this paper presents a novel combined model-based estimation scheme. Different from the conventional PTV models, the proposed model is constructed based on the host–Target Vehicle dynamics and road constraints. Specifically, steering angle of the PTV is included in the state vector. The measurements, such as heading angle, road curvature, and lateral distance to the lane center, are available from an onboard vision system. As a vision system inevitably has measurement delay, a modified Kalman filter is developed to address the sampling issue. To verify the proposed approach, hardware-in-the-loop experiments are conducted in designed testing scenarios.
Hu Yasen - One of the best experts on this subject based on the ideXlab platform.
-
Sensitive Detection of Target-Vehicle-Motion using Vision Only
2020 IEEE Intelligent Vehicles Symposium (IV), 2020Co-Authors: Mehdi Syed B, Hu YasenAbstract:For safe driving in parking lots, differentiating the few moving Vehicles from the many parked is essential but also challenging. Vehicles tend to move at slow speeds in parking areas and, therefore, low-cost sensors including cameras and radars cannot detect their motion using conventional object-localization and speed-measurement methods. This paper presents a novel method of detecting motion of a Target Vehicle by equating it to rotation of the Vehicle's wheels. Using a monocular 2MP camera, the algorithm is demonstrated to detect motion as slow as 0.1 mph at distances of up to 30 meters away while the host Vehicle itself moves at speeds up to 15 mph. Test results also promise an easy and cost-effective path to further increasing the range of the algorithm.
Yafei Wang - One of the best experts on this subject based on the ideXlab platform.
-
Lateral State Estimation of Preceding Target Vehicle Based on Multiple Neural Network Ensemble
2019 IEEE Intelligent Vehicles Symposium (IV), 2019Co-Authors: Yafei Wang, Zhisong Zhou, Wenqiang Jin, Chengliang YinAbstract:Preceding Target Vehicle (PTV) motion recognition play a pivotal role in autonomous Vehicles. Motion states such as yaw rate, longitudinal and lateral velocity are critical for ego Vehicle decision-making and control. However, lateral states of a PTV can hardly be measured directly by common onboard sensors and the PTV lateral state estimation has been seldom addressed in existing literatures. In this paper, a novel estimation scheme based on multiple neural network ensemble is proposed for PTV lateral state estimation. First, PTV lateral kinematics is presented based on Vehicle-road relationship and a novel PTV lateral motion model is constructed to interpret the PTV lateral motion. Then, neural network observer with the PTV lateral kinematics as prior knowledge is designed and training data are collected in simulation environment. The neural network observer is trained using Levenberg-Marquardt backpropagation with Bayesian regularization (LMBR) to improve the generalization capability. Finally, to further improve the performance of the neural network estimation method, multiple neural network observers are integrated by weighted averaging strategy. The effectiveness of proposed approach is verified through hardware-in-the-Ioop (HiL) experiments conducted in designed verification scenarios, and compared with model-based method and other three learning methods. The experiment results reveal that the proposed method outperforms other typical methods and achieves accurate estimation of the PTV lateral states.
-
Host–Target Vehicle Model-Based Lateral State Estimation for Preceding Target Vehicles Considering Measurement Delay
IEEE Transactions on Industrial Informatics, 2018Co-Authors: Yafei Wang, Zhisong Zhou, Chongfeng Wei, Yahui Liu, Chengliang YinAbstract:Automated Vehicle control requires full knowledge of motion behavior of the preceding Target Vehicles (PTVs), and the states such as longitudinal/lateral velocity and yaw rate are critical for the PTV behavior description. However, the PTV's lateral states estimation have seldom been addressed in the state-of-the-art literatures. Aimed at providing reliable PTV lateral states, this paper presents a novel combined model-based estimation scheme. Different from the conventional PTV models, the proposed model is constructed based on the host–Target Vehicle dynamics and road constraints. Specifically, steering angle of the PTV is included in the state vector. The measurements, such as heading angle, road curvature, and lateral distance to the lane center, are available from an onboard vision system. As a vision system inevitably has measurement delay, a modified Kalman filter is developed to address the sampling issue. To verify the proposed approach, hardware-in-the-loop experiments are conducted in designed testing scenarios.
