A Tabu list strategy based DQN for AAV mobility in indoor single-path environment: Implementation and performance evaluation

Saito, Nobuki; Oda, Tetsuya; Hirata, Aoto; Nagai, Yuki; Hirota, Masaharu; Katayama, Kengo; Barolli, Leonard

doi:10.1016/j.iot.2021.100394

Cited by 21 publications

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ru et al [12] proposed an intelligent path planning method based on deep reinforcement learning, which solved the problem of vehicle tracking error and over-dependence in traditional intelligent driving vehicle path planning. Saito et al [13] proposed and evaluated a Tabu list-based DQN (TLS-DQN) for AAV mobility control; Yang et al [14] studied the application of the DQN algorithm in deep reinforcement learning algorithms. Combining the Q-learning algorithm with the experience playback mechanism, the target Q value is generated to solve the multi-robot path planning problem; Yi et al [15] improved DQN as a typical deep reinforcement learning method.…”

Section: Introductionmentioning

confidence: 99%

Improved DQN for Dynamic Obstacle Avoidance and Ship Path Planning

Yang

Han

2023

Algorithms

View full text Add to dashboard Cite

The avoidance of collisions among ships requires addressing various factors such as perception, decision-making, and control. These factors pose many challenges for autonomous collision avoidance. Traditional collision avoidance methods have encountered significant difficulties when used in autonomous collision avoidance. They are challenged to cope with the changing environment and harsh motion constraints. In the actual navigation of ships, it is necessary to carry out decision-making and control under the constraints of ship manipulation and risk. From the implementation process perspective, it is a typical sequential anthropomorphic decision-making problem. In order to solve the sequential decision problem, this paper improves DQN by setting a priority for sample collection and adopting non-uniform sampling, and it is applied to realize the intelligent collision avoidance of ships. It also verifies the performance of the algorithm in the simulation environment.

show abstract