# Genetic-Algorithm-Based Proportional Integral Controller (GAPI) for ROV Steering Control

**Authors:** Ahsan Tanveer, Sarvat Mushtaq Ahmad  
**arXiv:** [2304.10137](https://arxiv.org/abs/2304.10137)  
**Date:** 2023-04-20  
**Summary page:** https://www.summarizepaper.com/en/paper/2304.10137v1/

## Key points

- Innovative approach: Genetic algorithm-based proportional integral controller (GAPI) for optimizing steering control of ROVs
- Comparison with other tuning methods: GAPI vs root-locus-tuned PI controller and simulated-annealing-based PI controller (SAPI)
- Performance evaluation: GAPI provides considerably better performance in terms of overshoot, peak time, and settling time
- Effectiveness of meta-heuristic optimization techniques: Genetic algorithms can optimize relatively straightforward controllers like PI controllers
- Potential for future research: Similar optimization techniques can be applied to develop advanced controllers for complex systems
- Authors' contributions: Conceptualization, methodology development, software implementation, validation, analysis, investigation, data curation, draft preparation, visualization, supervision, project administration
- Funding and approval information: No external funding or Institutional Review Board approval was involved in the research.

## Summary

This article presents an innovative approach to optimize steering control for remotely operated underwater vehicles (ROVs) using a genetic algorithm-based proportional integral controller (GAPI). The gain parameters of the PI controller are tuned using a genetic algorithm (GA), and the performance of GAPI is compared with that of a root-locus-tuned PI controller and a simulated-annealing-based PI controller (SAPI). The experimental response corresponding to the step waveform for the GA is obtained, and various response characteristics such as overshoot, peak time, and settling time are benchmarked. The findings indicate that GAPI provides considerably better performance compared to SAPI and the root-locus-tuned controller. This study highlights the effectiveness of using meta-heuristic optimization techniques like genetic algorithms in optimizing relatively straightforward controllers like PI controllers. It suggests that similar optimization techniques can be applied to develop more advanced controllers for sophisticated systems in future research. The authors' contributions include conceptualization, methodology development, software implementation, validation, formal analysis, investigation, data curation, original draft preparation, visualization, supervision, and project administration. All authors have read and agreed to the published version of the manuscript. It is worth noting that this research received no external funding or Institutional Review Board approval since it did not involve human subjects. In conclusion, this article demonstrates how GAPI outperforms other tuning methods like simulated annealing and root-locus tuning in terms of steering control for ROVs. This study opens up possibilities for further research on applying similar optimization techniques to develop advanced controllers for complex systems.