Verifying Aircraft Collision Avoidance Neural Networks Through Linear Approximations of Safe Regions

03/02/2019
by   Kyle D. Julian, et al.
0

The next generation of aircraft collision avoidance systems frame the problem as a Markov decision process and use dynamic programming to optimize the alerting logic. The resulting system uses a large lookup table to determine advisories given to pilots, but these tables can grow very large. To enable the system to operate on limited hardware, prior work investigated compressing the table using a deep neural network. However, ensuring that the neural network reliably issues safe advisories is important for certification. This work defines linearized regions where each advisory can be safely provided, allowing Reluplex, a neural network verification tool, to check if unsafe advisories are ever issued. A notional collision avoidance policy is generated and used to train a neural network representation. The neural networks are checked for unsafe advisories, resulting in the discovery of thousands of unsafe counterexamples.

READ FULL TEXT

page 3

page 4

page 5

page 7

research
10/09/2018

Deep Neural Network Compression for Aircraft Collision Avoidance Systems

One approach to designing decision making logic for an aircraft collisio...
research
01/17/2022

Neural Network Compression of ACAS Xu Early Prototype is Unsafe: Closed-Loop Verification through Quantized State Backreachability

ACAS Xu is an air-to-air collision avoidance system designed for unmanne...
research
03/01/2021

Generating Probabilistic Safety Guarantees for Neural Network Controllers

Neural networks serve as effective controllers in a variety of complex s...
research
11/06/2019

End to end collision avoidance based on optical flow and neural networks

Optical flow is believed to play an important role in the agile flight o...
research
08/17/2019

A Symbolic Neural Network Representation and its Application to Understanding, Verifying, and Patching Networks

Analysis and manipulation of trained neural networks is a challenging an...
research
08/18/2021

Verifying Low-dimensional Input Neural Networks via Input Quantization

Deep neural networks are an attractive tool for compressing the control ...
research
07/13/2020

Neural Network Verification through Replication

A system identification based approach to neural network model replicati...

Please sign up or login with your details

Forgot password? Click here to reset