Navigating Assistance System for Quadcopter with Deep Reinforcement Learning

TL;DR

This paper introduces a deep reinforcement learning approach for quadcopter navigation that combines path planning and collision avoidance, enabling the drone to bypass obstacles and reach its destination.

Contribution

It proposes a dual-function control system using deep Q-networks for both navigation and collision avoidance, enhancing quadcopter obstacle handling capabilities.

Findings

Collision rate reduced to 14% after 500 flights

Deep Q-network enables vertical maneuvering for obstacle bypass

Combines path planning with collision avoidance for improved navigation

Abstract

In this paper, we present a deep reinforcement learning method for quadcopter bypassing the obstacle on the flying path. In the past study, the algorithm only controls the forward direction about quadcopter. In this letter, we use two functions to control quadcopter. One is quadcopter navigating function. It is based on calculating coordination point and find the straight path to the goal. The other function is collision avoidance function. It is implemented by deep Q-network model. Both two function will output rotating degree, the agent will combine both output and turn direct. Besides, deep Q-network can also make quadcopter fly up and down to bypass the obstacle and arrive at the goal. Our experimental result shows that the collision rate is 14% after 500 flights. Based on this work, we will train more complex sense and transfer model to the real quadcopter.