Figure 4 - available via license: Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International
Content may be subject to copyright.
Download
View publication
Standard deviation of the energy expenditure against speed and inflow angle for the current-informed A* path planner (C.I. A * ), current-informed neural network (C.I. NN ), wake-informed A* path planner (W.I. A * ) and wake-informed neural network (W.I. NN )

Standard deviation of the energy expenditure against speed and inflow angle for the current-informed A* path planner (C.I. A * ), current-informed neural network (C.I. NN ), wake-informed A* path planner (W.I. A * ) and wake-informed neural network (W.I. NN )

Source publication
Figure 1: Front side view of the domain. Larger vehicle geometry...
Figure 2: Bottom view of the approach. Larger vehicle geometry...
Figure 3: Front side view of the domain with multiple trajectories...
Figure 4: Standard deviation of the energy expenditure against speed...
Figure 5: Median trajectory length against speed and inflow angle for...
Wake-Informed 3D Path Planning for Autonomous Underwater Vehicles Using A* and Neural Network Approximations
Preprint
Full-text available
  • Feb 2025
Autonomous Underwater Vehicles (AUVs) encounter significant energy, control and navigation challenges in complex underwater environments, particularly during close-proximity operations, such as launch and recovery (LAR), where fluid interactions and wake effects present additional navigational and energy challenges. Traditional path planning method...
Cite
Download full-text

Contexts in source publication

Context 1
... A* planner (W.I. A * ), and the wake-informed neural network (W.I.NN) is provided. The evaluation metrics are the energy expenditure (E), path length (L), the number of high-velocity cells encountered (n H,vel ), turbulent cell count (n turb. ), and computational time (t) of each trajectory. The results are summarized in Table 1, with Fig. 4, 5 and 6 provided to further substantiate the results. The most optimal results are bolded for clarity in Table ...
Context 2
... planner. The increased energy expenditure (ranging between 10.03-13.12%) in the neural network counterparts may be attributed to approximation errors inherent in learning-based approaches, where it remains challenging to capture the optimality of the A* algorithm in path planning, especially in the presence of complex wake structures. Provided in Fig. 4 is a depiction of the variation in standard deviation against speed and angle for both planners and networks. It can be seen that the current-informed NN has significant variation in path energy, indicating it may struggle to understand how best to traverse the domain, particularly at high ...