Rover path planning with obstacle avoidance has always been a popular research topic. The paper proposes a new agricultural rover path planning model, integrating a Super Rapid-exploration Random Tree (RRT) Star with an Enhanced Probabilistic Roadmap (EPRM). This model combines the intelligent node sampling and adaptive connection strategies of the EPRM method with the efficiency of the Super RRT Star algorithm. The model enhances farming operations’ sustainability and efficiency, tackling major obstacles in agricultural navigation. The proposed model’s efficacy is demonstrated by experimental data. The model achieves a 67.89 -degree angle of deflection and an average travel length of $\mathbf{9. 6 5}$ meters with an energy cost of 6.43 kWh and a total time of 8.06 seconds. These outperform traditional approaches in terms of results. The composite model’s improved performance demonstrates how it may transform agricultural rover navigation and advance economic growth and food security.
Machine Learning-based Obstacle Avoidance Path Planning of Agricultural Rover
2024-12-14
921302 byte
Conference paper
Electronic Resource
English
Path tracking, obstacle avoidance and dead reckoning by an autonomous planetary rover
Automotive engineering | 1998
|Path tracking, obstacle avoidance and dead reckoning by an autonomous planetary rover
Tema Archive | 1998
|