Intelligent Control of Electric Vehicle Drives using Swarm Robotics

Abstract

This study investigates the incorporation of swarm robotics into the control mechanism of electric vehicles (EVs), introducing an innovative intelligent control framework that utilizes the concepts of decentralized decision-making. The research entails a methodical inquiry that encompasses the design of system architecture, the creation of a model for swarm robotics, the modeling of electric vehicle drive, the integration of swarm robotics with EV control, the development of algorithms for intelligent control, and the execution of real-world tests. The fleet of electric cars, propelled by a collective of independent robotic entities, displayed remarkable flexibility in adjusting to fluctuating surroundings. Findings demonstrated disparities in operating duration, distance traversed, mean speed, and energy expenditure during several iterations, highlighting the system’s adeptness in promptly reacting to instantaneous inputs. Significantly, the swarm-propelled electric cars successfully attained varied operating durations, showcasing the system’s adaptability in accommodating environmental dynamics. The swarm-driven system demonstrated its navigation effectiveness by effectively covering various distances, highlighting its versatility and extensive coverage capabilities. The system’s ability to effectively balance energy economy and performance is shown by the collective regulation of average velocity. The energy consumption study demonstrated the system’s efficacy in optimizing energy use, with certain experiments showing significant savings. Percentage change studies have yielded valuable insights into the comparative enhancements or difficulties seen in each indicator, so illustrating the influence of decentralized decision-making on operational results. This study is a valuable contribution to the ever-changing field of intelligent transportation systems, providing insight into the immense potential of swarm-driven electric cars to completely transform sustainable and adaptable transportation. The results highlight the remarkable flexibility and optimization skills of swarm robotics in the management of electric vehicles, paving the way for future advancements in the quest for intelligent, energyefficient, and dynamically responsive transportation solutions.

AI Driven Approaches in Swarm Robotics - A review

“…This concise overview facilitates a comprehensive understanding of the diverse applications of AI in swarm robotics, alongside the testing environments and specific methodologies employed across the studies. -√ Large language model (LLM) [21] -√ RL algorithm [5] √ -Dueling Double Deep Q-Network (D3QN) [6] √ -Deep Learning Trained by Genetic Algorithm (DL-GA) [8] √ -3D StringNet herding [10] √ -Decision-making mechanisms [12] √ -Deep Imitation Reinforcement Learning (DIRL) [17] Augmented Lagrangian particle swarm optimization (ALPSO) [20] √ √ Automatic modular design approach (AutoMoDe) [24] Coordination -√ AudioLocNetv(deep learning module) [31] √ -Not specified [32] √ -End-to-end Neural Networks to train robots [27] √ -Mean-field feedback control [28] √ -Deep Neural Network (DNN) model [29] √ -variant of the crawling probabilistic road map motion planning algorithm [33] √ -distributed online reinforcement learning method [34] √ -coordination algorithm [51] Optimization -√ PSO algorithm [53] -√ streamlined algorithms [36] √ -Genetic algorithm (GA) [46] √ -Particle Swarm Optimization (PSO) [49] √ -Robot Bean Optimization Algorithm (RBOA) [50] √ -Automatic modular design method: AutoMoDe-Cedrata and AutoMoDe-Maple [52] √ -PPO algorithm [54] √ -Dijkstra algorithm [55] √ -WC and WET algorithms [44] √ √ Decentralized ergodic planning [35] Optimization and Navigation √ -YOLOv8 [41] √ -Quantum-based path-planning algorithm and Grover's search algorithm [42] √ -Genetic algorithms (GA) and Cellular automata techniques [9] √ -Mean-Field Control (MFC), deep reinforcement learning (RL), and collision avoidance algorithms [22] Optimization and Coordination √ -Knowledge-Based Neural Ordinary Differential Equations (KNODE) [23] √ -Surrogate models ...…”