… separated from the effectiveness of navigation and collisionfree motion. In addition, dynamic
path … This paper proposes a Deep Reinforcement Learning (DRL) based collision free path …

… We may calculate the average interval of all these distances by realizing the collision-free
distance for each participating agent. When all of the agent velocities are chosen at the same …

… As a result, the only feasible, collision-free solution for the autonomous vehicle might be
to stay stationary which incurs other costs (such as increased time to achieve the goal and …

… train the vehicle. It has been shown in our approach that after some iterations, the virtually
created vehicle generates collision-free movement and performs the same driving behaviour …

… As a result, the model will output a higher probability of collision in collision-free cases. By
setting an appropriate value of △T, the neural network can be trained to predict the probability …

… and control (IDC) framework for automated vehicles at complex intersections, which …
IDC framework for automated vehicles at intersections. The IDC framework decomposes the …

… -efficient and collision-free motion planning issue for underwater vehicles in fading channel
and obstacle environment. We first develop a model-based integral reinforcement learning (…

… As the results in the following Section indicate, the agent detected collision-free trajectories
even without this extra step, so we did not fine-tuned the agent with a collision term in the …

… autonomous surface vehicles in an obstacle-free environment. Thanks to reinforcement
learning… In comparison to traditional deep reinforcement learning methods, our proposed learning…

… and speed of the autonomous ship and dynamic … reinforcement learning (DRL) considering
the CR and COLREGs is proposed to navigate the collision-free path of an autonomous …