Multi-Objective Multi-Learner Robot Trajectory Prediction Method for IoT Mobile Robot Systems

Peng, Fei; Li, Zheng; Zhu, Daiyin; Lei, Yu

doi:10.3390/electronics11132094

Cited by 9 publications

(5 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It abandons the crowding-distance sorting mechanism often used in NSGA-II and introduces a new sorting mechanism based on reference points [26]. The NSGA-III is especially designed to deal with multi-objective optimization issues that have three or more objectives [27]. When compared with the NSGA-II algorithm, the NSGA-III not only significantly reduces the computational complexity but also excels in preserving diversity.…”

Section: Feature Selection: Multi-objective Optimization: Nsga-iii Al...mentioning

confidence: 99%

An Ensemble Model for PM2.5 Concentration Prediction Based on Feature Selection and Two-Layer Clustering Algorithm

Wu,

Wen,

Zhu

2023

Atmosphere

View full text Add to dashboard Cite

Determining accurate PM2.5 pollution concentrations and understanding their dynamic patterns are crucial for scientifically informed air pollution control strategies. Traditional reliance on linear correlation coefficients for ascertaining PM2.5-related factors only uncovers superficial relationships. Moreover, the invariance of conventional prediction models restricts their accuracy. To enhance the precision of PM2.5 concentration prediction, this study introduces a novel integrated model that leverages feature selection and a clustering algorithm. Comprising three components—feature selection, clustering, and integrated prediction—the model first employs the non-dominated sorting genetic algorithm (NSGA-III) to identify the most impactful features affecting PM2.5 concentration within air pollutants and meteorological factors. This step offers more valuable feature data for subsequent modules. The model then adopts a two-layer clustering method (SOM+K-means) to analyze the multifaceted irregularity within the dataset. Finally, the model establishes the Extreme Learning Machine (ELM) weak learner for each classification, integrating multiple weak learners using the AdaBoost algorithm to obtain a comprehensive prediction model. Through feature correlation enhancement, data irregularity exploration, and model adaptability improvement, the proposed model significantly enhances the overall prediction performance. Data sourced from 12 Beijing-based monitoring sites in 2016 were utilized for an empirical study, and the model’s results were compared with five other predictive models. The outcomes demonstrate that the proposed model significantly heightens prediction accuracy, offering useful insights and potential for broadened application to multifactor correlation concentration prediction methodologies for other pollutants.

show abstract

Section: Feature Selection: Multi-objective Optimization: Nsga-iii Al...mentioning

confidence: 99%

An Ensemble Model for PM2.5 Concentration Prediction Based on Feature Selection and Two-Layer Clustering Algorithm

Wu,

Wen,

Zhu

2023

Atmosphere

View full text Add to dashboard Cite

show abstract

“…Current papers focus on the application of the following architectures: multilayer fully connected networks [32], recurrent neural networks in the form of long short-term memory (LSTM) [33,34], and gated recurrent units (GRUs) [35]. We note a comprehensive study on UAV trajectory prediction comparing five machine learning models [36]. Despite the obtained achievements, modern approaches to motion prediction do not always satisfy the limitations imposed on the computing power of onboard computers, while increasing autonomy requires the implementation of basic algorithms directly on board.…”

Section: Related Workmentioning

confidence: 99%

“…W ω gz /w x (s) = −0.007s−0.057 0.139s 2 +0.537s+1 ; W ω gz /w y (s) = 0.355s 0.139s 2 +0.537s+1 (36) For lateral dynamics, the resulting transfer functions from the control action of the rudder ∆δ r and the wind component w z to the yaw angular velocity ω gy have the following form:…”

Section: Planar Casementioning

confidence: 99%

Modeling the Solution of the Pursuit–Evasion Problem Based on the Intelligent–Geometric Control Theory

Khachumov,

Khachumov

2023

Mathematics

View full text Add to dashboard Cite

An important action-planning problem is considered for participants of the pursuit–evasion game with multiple pursuers and a high-speed evader. The objects of study are mobile robotic systems and specifically small unmanned aerial vehicles (UAVs). The problem is complicated by the presence of significant wind loads that affect the trajectory and motion strategies of the players. It is assumed that UAVs have limited computing resources, which involves the use of computationally fast and real-time heuristic approaches. A novel and rapidly developing intelligent–geometric theory is applied to address the discussed problem. To accurately calculate the points of the participant’s rapprochement, we use a geometric approach based on the construction of circles or spheres of Apollonius. Intelligent control methods are applied to synthesize complex motion strategies of participants. A method for quickly predicting the evader’s trajectory is proposed based on a two-layer neural network containing a new activation function of the “s-parabola” type. We consider a special backpropagation training scheme for the model under study. A simulation scheme has been developed and tested, which includes mathematical models of dynamic objects and wind loads. The conducted simulations on pursuit–evasion games in close to real conditions showed the prospects and expediency of the presented approach.

show abstract

“…In the dynamic path planning problem, the constraints count the number of collisions the robot could have when using a given vector p in Bug0 within the same prediction horizon h discussed in the previous section. Then, the dynamic optimization problem only considers equality constraints as follows: [42,43].…”

Section: Constraintsmentioning

confidence: 99%

Dynamic Path Planning for the Differential Drive Mobile Robot Based on Online Metaheuristic Optimization

et al. 2022

View full text Add to dashboard Cite

Mobile robots are relevant dynamic systems in recent applications. Path planning is an essential task for these robots since it allows them to move from one location to another safely and at an affordable cost. Path planning has been studied extensively for static scenarios. However, when the scenarios are dynamic, research is limited due to the complexity and high cost of continuously re-planning the robot’s movements to ensure its safety. This paper proposes a new, simple, reliable, and affordable method to plan safe and optimized paths for differential mobile robots in dynamic scenarios. The method is based on the online re-optimization of the static parameters in the state-of-the-art deterministic path planner Bug0. Due to the complexity of the dynamic path planning problem, a metaheuristic optimization approach is adopted. This approach utilizes metaheuristics from evolutionary computation and swarm intelligence to find the Bug0 parameters when the mobile robot is approaching an obstacle. The proposal is tested in simulation, and well-known metaheuristic methods are compared, including Differential Evolution (DE), the Genetic Algorithm (GA), and Particle Swarm Optimization (PSO). The dynamic planner based on PSO generates paths with the best performances. In addition, the results of the PSO-based planner are compared with different Bug0 configurations, and the former is shown to be significantly better.

show abstract

Multi-Objective Multi-Learner Robot Trajectory Prediction Method for IoT Mobile Robot Systems

Cited by 9 publications

References 57 publications

An Ensemble Model for PM2.5 Concentration Prediction Based on Feature Selection and Two-Layer Clustering Algorithm

An Ensemble Model for PM2.5 Concentration Prediction Based on Feature Selection and Two-Layer Clustering Algorithm

Modeling the Solution of the Pursuit–Evasion Problem Based on the Intelligent–Geometric Control Theory

Dynamic Path Planning for the Differential Drive Mobile Robot Based on Online Metaheuristic Optimization

Contact Info

Product

Resources

About