Ali El Romeh

Multi-robot exploration in unknown environments is a challenging optimization task. Although many optimization algorithms exist, there has been limited exploration of Large Language Models (LLMs) in the literature to enhance these methods. This study investigates the use of LLMs to improve optimization strategies for robotic exploration considering two main approaches: zero-shot and few-shot learnings. In the former case, the LLM generates solutions based on a problem description alone. In the latter, few-shot learning, the LLM refines solutions based on initial results as well as a problem description. Using models like GPT, Gemini, and Claude, we created enhanced variants of Particle Swarm Optimization (PSO) to improve exploration efficiency and help robots navigate complex environments to address PSO’s common issues such as local optima. Experimental results demonstrate the strong potential of LLMs in refining optimization strategies for multi-robot exploration.

This work introduces the Advanced Multi-Objective Salp Swarm Algorithm Exploration Technique (AMET), which is a novel optimization framework designed to enhance the efficiency and robustness of multi-robot exploration. AMET combines the deterministic structure of Coordinated Multi-Robot Exploration (CME) with the adaptive search capabilities of the Multi-Objective Salp Swarm Algorithm (MSSA) to achieve a balanced trade-off between exploration efficiency and mapping accuracy. To validate its effectiveness, AMET is compared to both multi-objective and single-objective exploration strategies, including CME combined with Multi-Objective Grey Wolf Optimizer (CME-MGWO), Multi-Objective Ant Colony Optimization (CME-MACO), Multi-Objective Dragonfly Algorithm (CME-MODA), and the single-objective CME with traditional Salp Swarm Algorithm (CME-SSA). The evaluation focuses on four critical performance metrics: runtime efficiency, exploration area coverage, mission completion resilience, and the reduction of redundant exploration. Experimental results across multiple case studies demonstrate that AMET consistently outperforms both single-objective and multi-objective counterparts, achieving superior area coverage, reduced computational overhead, and enhanced exploration coordination. These findings highlight the potential of AMET as a scalable and efficient approach for robotic exploration, providing a foundation for future advancements in multi-robot systems. The proposed method opens new possibilities for applications in search-and-rescue operations, planetary surface exploration, and large-scale environmental monitoring.

Efficient exploration in multi-robot systems is significantly influenced by the initial start positions of the robots. This paper introduces the hybrid cheetah exploration technique with intelligent initial configuration (HCETIIC), a novel strategy explicitly designed to optimize exploration efficiency across varying initial start configurations: uniform distribution, centralized position, random positions, perimeter positions, clustered positions, and strategic positions. To establish the effectiveness of HCETIIC, we engage in a comparative analysis with four other prevalent hybrid methods in the domain. These methods amalgamate the principles of coordinated multi-robot exploration (CME) with different metaheuristic algorithms and have demonstrated compelling results in their respective studies. The performance comparison is based on essential measures such as runtime, the percentage of the explored area, and failure rate. The empirical results reveal that the proposed HCETIIC method consistently outperforms the compared strategies across different start positions, thereby emphasizing its considerable potential for enhancing efficiency in multi-robot exploration tasks across a wide range of real-world scenarios. This research underscores the critical, yet often overlooked, role of the initial robot configuration in multi-robot exploration, establishing a new direction for further improvements in this field.

Multi-robot exploration means constructing a finite map using a group of robots in an obstacle chaotic space. Uncertainties are reduced by distributing search tasks to robots and computing the best action in real time. Many previous methods are based on deterministic or meta-heuristic algorithms, but limited work has combined both techniques to consolidate both classes’ benefits and alleviate their drawbacks. This paper proposes a new hybrid method based on deterministic coordinated multi-robot exploration (CME) and the meta-heuristic salp swarm algorithm (SSA) to perform the search of a space. The precedence of adjacent cells around a robot is determined by deterministic CME using cost and utility. Then, the optimization process of the search space, improving the overall solution, is achieved utilizing the SSA. Three performance measures are considered to evaluate the performance of the proposed method: run time, percentage of the explored area, and the number of times when a method failed to continue a complete run. Experimental results compared four different methods, CME-GWO, CME-GWOSSA, CME-SCA, and CME, over seven maps with extra complexity varying from simple to complex. The results demonstrate how the proposed CME-SSA can outperform the four other methods. Moreover, the simulation results demonstrate that the proposed CME-SSA effectively distributes the robots over the search space to run successfully and obtain the highest exploration rate in less time.