| Summary/Abstract |
Addressing the need for exploration of benthic zones utilising autonomous underwater vehicles, this paper presents a simulation for an optimised path planning from the source node to the destination node of the autonomous underwater vehicle SLOCUM Glider in near-bottom ocean environment. Near-bottom ocean current data from the Bedford Institute of Oceanography, Canada, have been used for this simulation. A cost function is formulated to describe the dynamics of the autonomous underwater vehicle in near-bottom ocean currents. This cost function is then optimised using various biologically-inspired algorithms such as genetic algorithm, Ant Colony optimisation algorithm and particle swarm optimisation algorithm. The simulation of path planning is also performed using Q-learning technique and the results are compared with the biologically-inspired algorithms. The results clearly show that the Q-learning algorithm is better in computational complexity than the biologically-inspired algorithms. The ease of simulating the environment is also more in the case of Q-learning techniques. Hence this paper presents an effective path planning technique, which has been tested for the SLOCUM glider and it may be extended for use in any standard autonomous underwater vehicle.
|