Integrated Path Planning and Tracking Control of Marine Current Turbine in Uncertain Ocean Environments

Hasankhani, Arezoo; Ondes, Ertugrul Baris; Tang, Youxi; Sultan, Cornel; VanZwieten, James H.

doi:10.23919/acc53348.2022.9867485

Cited by 7 publications

(1 citation statement)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In such cases, the necessity for local planning with rapid computation becomes crucial to ensure timely goal attainment for the robot. In the work by Hasankhani et al [45], the path planner is crafted using reinforcement learning to tackle the highly nonlinear and uncertain oceanic environment. Nakrani and Joshi [46] introduced a fuzzy-based obstacle avoidance controller with ulstrasonic sensor outputs as inputs to the FL to accomplish autonomous parallel parking in the presence of static and dynamic obstacles.…”

mentioning

confidence: 99%

A Hybrid HHO-AVOA for Path Planning of a Differential Wheeled Mobile Robot in Static and Dynamic Environments

Loganathan,

Ahmad

2024

IEEE Access

View full text Add to dashboard Cite

This study presents a hybrid HHO-AVOA which is a novel optimization method that combines the strengths of Harris Hawks Optimization (HHO) and African Vulture Optimization Algorithm (AVOA) to address the path planning challenges encountered by differential wheeled mobile robots (DWMRs) navigating both static and dynamic environments, while accommodating kinematic constraints. By synergizing the strengths of both algorithms, the proposed hybrid method effectively mitigates the limitations of individual approaches, resulting in efficient and obstacle-avoiding navigation towards the target within reduced timeframes. To evaluate its efficiency, the proposed approach is compared against HHO and AVOA as well as other established methods which include whale optimization, grey wolf optimization and sine-cosine algorithms. Simulation results along with Monte Carlo analysis consistently demonstrate the superior performance of the hybrid method in both environments. In static scenarios, the hybrid algorithm achieves an average reduction of approximately 14% in path length and a 17% decrease in DWMR travel duration. In dynamic cases, it outperforms the rest with an average reduction of 27.6% in path length and a 27.2% decrease in travel duration. The algorithm's low computational complexity is also exhibited via its fast convergence during path optimization which is a crucial attribute for real-time implementation, particularly in dynamically changing environments that demand quick decision-making. The superiority of the proposed hybrid method to balance the exploration and exploitation is also affirmed through a Wilcoxon rank-sum test with a 95% confidence interval.

show abstract

mentioning

confidence: 99%