Deep Neural Network Compression for Aircraft Collision Avoidance Systems
Deep Neural Network Compression for Aircraft Collision Avoidance Systems
复制标题
DOI：
10.2514/1.g003724
复制
发表时间：
2019-03-01
影响因子：
2.6
通讯作者：
Owen, Michael P.
中科院分区：
文献类型：
--
作者：
Julian, Kyle D.;Kochenderfer, Mykel J.;Owen, Michael P.
为飞机防撞系统设计决策逻辑的一种方法将问题描述为马尔可夫决策过程，并使用动态规划来优化系统。由此产生的碰撞避免策略可以表示为数字表。该方法已用于开发有人机和无人机的机载防撞系统 X 系列防撞系统，但状态空间的高维性导致表格非常大。为了提高存储效率，使用深度神经网络来近似该表。通过使用非对称损失函数和梯度下降算法，可以训练该网络的参数以提供表值的准确估计，同时保留每个状态可能建议的相对偏好。通过训练多个网络来表示子表，网络还减少了计算防撞建议所需的运行时间。仿真研究表明，该网络提高了防撞系统的安全性和效率。由于只需要存储网络参数，所需的存储空间减少了1000倍，使得防撞系统能够使用当前的航空电子系统进行操作。
One approach to designing decision-making logic for an aircraft collision avoidance system frames the problem as a Markov decision process and optimizes the system using dynamic programming. The resulting collision avoidance strategy can be represented as a numeric table. This methodology has been used in the development of the Airborne Collision Avoidance System X family of collision avoidance systems for manned and unmanned aircraft, but the high-dimensionality of the state space leads to very large tables. To improve storage efficiency, a deep neural network is used to approximate the table. With the use of an asymmetric loss function and a gradient descent algorithm, the parameters for this network can be trained to provide accurate estimates of table values while preserving the relative preferences of the possible advisories for each state. By training multiple networks to represent subtables, the network also decreases the required runtime for computing the collision avoidance advisory. Simulation studies show that the network improves the safety and efficiency of the collision avoidance system. Because only the network parameters need to be stored, the required storage space is reduced by a factor of 1000, enabling the collision avoidance system to operate using current avionics systems.