DRQN-based 3D Obstacle Avoidance with a Limited Field of View
This addresses autonomous navigation in partially observed environments for robotics, but it is incremental as it builds on existing DRL methods with specific improvements.
The paper tackles 3D obstacle avoidance for indoor mobile robots with a limited field of view by proposing a map-based end-to-end deep reinforcement learning approach, achieving a 15.5% higher success rate compared to existing DRL-based models.
In this paper, we propose a map-based end-to-end DRL approach for three-dimensional (3D) obstacle avoidance in a partially observed environment, which is applied to achieve autonomous navigation for an indoor mobile robot using a depth camera with a narrow field of view. We first train a neural network with LSTM units in a 3D simulator of mobile robots to approximate the Q-value function in double DRQN. We also use a curriculum learning strategy to accelerate and stabilize the training process. Then we deploy the trained model to a real robot to perform 3D obstacle avoidance in its navigation. We evaluate the proposed approach both in the simulated environment and on a robot in the real world. The experimental results show that the approach is efficient and easy to be deployed, and it performs well for 3D obstacle avoidance with a narrow observation angle, which outperforms other existing DRL-based models by 15.5% on success rate.