Reinforcement learning-based vehicle travel path reconstruction from sparse automatic licence plate recognition data by Qiuping Li, Hui Meng, Li Zhuo

“…First, the maximum entropy inverse reinforcement learning (MaxEnt IRL) method is employed to learn vehicle path selection strategy, i.e. the reward function, from the real data. Then, a comprehensive reward function is formulated by integrating destination rewards. …”
Get full text

Dynamic Monitoring of Goaf Stress Field and Rock Deformation Driven by Optical Diber Sensing Technology by Jing Chai, Zhe Yan, Yibo Ouyang, Dingding Zhang, Jianfeng Yang, Gaoyi Yang, Chenyang Ma

“…By coupling the fracture mechanics model of the critical layer and the settlement trajectory function model, the dynamic transformation of the pre-fracture and post-fracture stages is realized, and the stress evolution can be monitored and predicted in real time. …”
Get full text

Vehicle Recognition and Driving Information Detection with UAV Video Based on Improved YOLOv5-DeepSORT Algorithm by Binshuang Zheng, Jing Zhou, Zhengqiang Hong, Junyao Tang, Xiaoming Huang

“…By coding, the coordinate information of the vehicle trajectory is extracted, the trajectory is smoothed, and the frame difference method is used to calculate the real-time speed information, which is convenient for the establishment of a real driver model.…”
Get full text

Technique for target recognition based on intuitionistic fuzzy c-means clustering and kernel matching pursuit by Yang LEI, Wei-wei KONG, Ying-jie LEI

“…Kernel matching pursuit requires every step of searching process be global optimal searching in the redundant dictionary of function.Namely,the dictionary learning time of KMP was too long.To the above drawbacks,a novel technique for KMP based on IFCM was proposed to substitute local searching for global searching by the property superiority of dynamic clustering performance,which was also the superiority in Intuitionistic fuzzy c-means algorithm.Then two testing including classification and effectiveness were carried out towards four real sample data.Subsequently,high resolution range profile (HRRP)was selected from the classical properties of target recognition in e middle ballistic trajectory,which were extracted for getting sub-range profile.Finally,three algorithms including FCM,KMP,IFCM-KMP were carried out respectively towards different kinds of sub-range profile samples in emulation platform,the conclusion of which fully demonstrates that the IFCM-KMP algorithm is superior over FCM and KMP when it comes to target recognition in the middle ballistic trajectory.…”
Get full text

A DMPC-based three-dimensional cooperative guidance scheme with impact time and impact angle constraints by Zijie Jiang, Xiuxia Yang, Cong Wang, Yi Zhang, Hao Yu

“…By introducing the assumed state trajectory, the DMPC controller (of each interceptor) can simultaneously employ the zebra optimization algorithm (ZOA) to solve the constrained optimization problem, and generate the real-time guidance commands with no need of any global information. …”
Get full text

Event-triggered iterative learning control for output constrained multi-agent systems. by Wei Cao, Huanhuan Li, Jinjie Qiao, Yi Zhu

“…Then, the event-triggered iterative learning control algorithm is constructed using the estimated PPD, the trigger condition and the measurement error, and the convergence of the algorithm is proved by using the Lyapunov function, and the proposed algorithm can make the output constrained multi-agent system consistently and completely tracking on the desired trajectory without the need of real-time communication conditions. …”
Get full text

Goal-oriented autonomous decision-making for social robots via collaborative interactive inverse reinforcement learning approach by Mingyue Luo, Hui Li, Wanbo Luo, Hewei Li, Jianan Li

“…However, social robots typically have clear navigation goals, and the practicality of the aforementioned methods is debatable. Moreover, trajectory prediction at longer distances also poses significant challenges for such trajectory planning methods. …”
Get full text

Mamba-DQN: Adaptively Tunes Visual SLAM Parameters Based on Historical Observation DQN by Xubo Ma, Chuhua Huang, Xin Huang, Wangping Wu

“…In this paper, we select the key parameters of visual SLAM to construct the agent action space. The reward function is constructed based on the absolute trajectory error (ATE), and the Mamba history observer is built within the agent to learn the observation trajectory, aiming to improve the quality of the agent’s decisions. …”
Get full text

Performance Optimization of Synchronous Reluctance Motor using Adaptive MTPA Curve Fitting with Anti-Windup Current Control by Alex V, Rammohan A

“…In this study, a curve-fitting approach integrated with anti-windup control is employed, where an analytical function is developed to closely approximate the optimal current trajectory. …”
Get full text

CALCULATION OF WEIGHT COEFFICIENTS IN CONTINUOUS PARTICLE FILTER by K. A. Rybakov

“…Along with the representation by a continuous function, it is shown that the path of the weight function can be presented by a piecewise constant function with nonnegative real values and also by a piecewise constant function with nonnegative integer values. …”
Get full text

Opticool: Cutting-edge transgenic optical tools. by Kelli D Fenelon, Julia Krause, Theodora Koromila

“…Optogenetic, genetically encoded optically controlled manipulation systems have gained traction in the biological research community and facilitate single-cell, real-time modulation of protein function in vivo in ever broadening, novel applications. …”
Get full text

Clutch Online Adaptive Engagement Control of ISG Type Hybrid Electric Vehicle by Yan Ting, Yang Lin, Chen Liang

“…Meanwhile,clutch speed synchronization is accomplished by engine target speed trajectory tracking control. Test results show that the proposed method can be applied on-board in real time and can restrain impact and decrease engagement time effectively in comparison to other control methods.…”
Get full text

CALCULATION AND SIMULATION OF THE CLEARANCE FOR FLEXIBLE HIGH-SPEED BEATING-UP SYSTEM CONSIDERING RESISTANCE EFFECT by QIU HaiFei

“…The beating-up resistance from sley was transformed into an equivalent torque on rocking shaft by use of step function. The results of contact dynamics simulation with different clearance states show that there are obvious differences between flexible body simulation and rigid body simulation, and the former can better reflect the real situation of beating-up; The clearance of 0.03 mm and 0.06 mm has a great influence on sley vibration which is not conducive to reduce vibration and noise for loom system; 0.09 mm clearance will not only cause high-frequency reaction force on main shaft bearing, but also aggravate contact and collision between crank and connecting rod; There are many overlaps between centroid trajectory of flexible main shaft with clearance and ideal trajectory, because of that, multi-point contact collision occurs in the crank bearing. …”
Get full text

An efficient smoothing algorithm for range external guidance data based on dynamic threshold and adaptive interpolation by Shixue Zhang, Huihui Cai, Houfeng Wang, Shuai Liu, Qiang He

“…First, to address outliers in the external guidance data, a method for dynamically calculating sample variance using an influence function is introduced. This approach establishes an adaptive threshold for real-time outlier detection in real time. …”
Get full text

并联机器人的新型趋近率滑模控制研究 by 石明明, 高国琴, 牛雪梅

“…Secondly,the stability of the controller is analyzed and proved theoretically by a Lyapunov function. Finally,the simulation experiments of the parallel mechanism dynamics model and control are carried out by using MATLAB.Comparing with a computed torque control and a conventional reaching law sliding mode control,the results show that the established dynamics model is suitable for the real- time dynamic control of the parallel mechanism and the designed control method has the better performance.…”
Get full text

A Data-Driven and Personalized Stance Symmetry Controller for Robotic Ankle-Foot Prostheses: A Preliminary Investigation by Christopher Prasanna, Jonathan Realmuto, Anthony Anderson, Eric Rombokas, Glenn Klute

“…Our controller uses a virtual setpoint trajectory within an impedance-inspired formula to adjust the dynamics of the robotic ankle-foot prosthesis as a function of stance phase. …”
Get full text

Two-Stage Learning of CPG and Postural Reflex Toward Quadruped Locomotion on Uneven Terrain With Simple Reward by Ryosei Seto, Guanda Li, Kyo Kutsuzawa, Dai Owaki, Mitsuhiro Hayashibe

“…Among them, the Central Pattern Generator-Reinforcement Learning (CPG-RL) framework, which combines Central Pattern Generators (CPG) with reinforcement learning (RL), offers key advantages such as accelerated learning, improved Sim-to-Real transfer, and the ability to learn with a simplified reward function. …”
Get full text

Pei-Wo Drone: a home-based exercise guidance system with a drone for older adults by Kanjana Chaitika, Hsiao-Feng Chieh, Kai-Nan An, Chien-Ju Lin, Fong-Chin Su

“…By following the drone’s trajectory and receiving real-time feedback, users can ensure correct movements and make necessary adjustments. …”
Get full text

Novel 3D UAV Path Planning for IoT Services Based on Interactive Cylindrical Vector Teaching–Learning Optimization Algorithm by Xinghe Jiang, Xuanyu Wu, Zhifeng Zhang, Zhaoxi Hong, Xi Xiao, Yixiong Feng

“…The ICVTLBO is compared with other classical and novel algorithms on the CEC2022 benchmark function suite, demonstrating its effectiveness and reliability in solving complex optimization problems. …”
Get full text

Mobile crowd sensing coverage and energy optimization in smart coalmine by Chaowei WANG, Ting LIU, Tianyu WANG, Weidong WANG

“…Mobile crowd sensing (MCS) is a promising diagram for the environmental information collection based on the smart mobile terminal.Nowadays,vehicles with multiple embedded sensors are increasingly being considered as participants to complete various sensing tasks.In order to better perceive the data in the coalmine environment,the coverage quality and energy consumption of the perception data of sensing terminals were studied based on MCS.A new sensing coverage quality indicator called utility function F(Ω) jointly considering the coverage percentage and coverage density was defined.The selection of vehicles as an optimization problem to improve the coverage quality was formulated,then an improved greedy algorithm-coverage quality optimization (CQO) algorithm was proposed.The proposed algorithm with the real vehicle trajectory dataset was formulated and several factors influencing the coverage quality were studied.The experiment results show that the proposed algorithm achieves a better coverage quality.…”
Get full text