# Deep Neural Network Compression for Aircraft Collision Avoidance Systems

arXiv: https://arxiv.org/abs/1810.04240 · HTML: https://mlsanity.com/paper/1810.04240/

## Key facts

- Cited by 58 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Oct 2018.

## Built on by (most cited first, 30 of 58)

- [Marabou 2.0: A Versatile Formal Analyzer of Neural Networks](https://mlsanity.com/paper/2401.14461/) (2024)
- [Causality-based Neural Network Repair](https://mlsanity.com/paper/2204.09274/) (2022)
- [Provable Repair of Deep Neural Networks](https://mlsanity.com/paper/2104.04413/) (2021)
- [Towards Formal XAI: Formally Approximate Minimal Explanations of Neural Networks](https://mlsanity.com/paper/2210.13915/) (2022)
- [Neural Network Verification with Proof Production](https://mlsanity.com/paper/2206.00512/) (2022)
- [Backward Reachability Analysis of Neural Feedback Loops: Techniques for Linear and Nonlinear Systems](https://mlsanity.com/paper/2209.14076/) (2022)
- [Incremental Verification of Neural Networks](https://mlsanity.com/paper/2304.01874/) (2023)
- [Sound and Complete Neural Network Repair with Minimality and Locality Guarantees](https://mlsanity.com/paper/2110.07682/) (2021)
- [MDPFuzz: Testing Models Solving Markov Decision Processes](https://mlsanity.com/paper/2112.02807/) (2021)
- [Incremental Randomized Smoothing Certification](https://mlsanity.com/paper/2305.19521/) (2023)
- [Abstraction and Refinement: Towards Scalable and Exact Verification of Neural Networks](https://mlsanity.com/paper/2207.00759/) (2022)
- [Architecture-Preserving Provable Repair of Deep Neural Networks](https://mlsanity.com/paper/2304.03496/) (2023)
- [SyReNN: A Tool for Analyzing Deep Neural Networks](https://mlsanity.com/paper/2101.03263/) (2021)
- [Backward Reachability Analysis for Neural Feedback Loops](https://mlsanity.com/paper/2204.08319/) (2022)
- [QEBVerif: Quantization Error Bound Verification of Neural Networks](https://mlsanity.com/paper/2212.02781/) (2022)
- [Neural Network Compression of ACAS Xu Early Prototype is Unsafe: Closed-Loop Verification through Quantized State Backreachability](https://mlsanity.com/paper/2201.06626/) (2022)
- [Verifying Low-dimensional Input Neural Networks via Input Quantization](https://mlsanity.com/paper/2108.07961/) (2021)
- [Toward Certification of Machine-Learning Systems for Low Criticality Airborne Applications](https://mlsanity.com/paper/2209.13975/) (2022)
- [A Hybrid Partitioning Strategy for Backward Reachability of Neural Feedback Loops](https://mlsanity.com/paper/2210.07918/) (2022)
- [Towards a Certified Proof Checker for Deep Neural Network Verification](https://mlsanity.com/paper/2307.06299/) (2023)
- [DeepCDCL: An CDCL-based Neural Network Verification Framework](https://mlsanity.com/paper/2403.07956/) (2024)
- [Static analysis of ReLU neural networks with tropical polyhedra](https://mlsanity.com/paper/2108.00893/) (2021)
- [Discrete-Event Controller Synthesis for Autonomous Systems with Deep-Learning Perception Components](https://mlsanity.com/paper/2202.03360/) (2022)
- [Generating Probabilistic Safety Guarantees for Neural Network Controllers](https://mlsanity.com/paper/2103.01203/) (2021)
- [Self-Correcting Neural Networks For Safe Classification](https://mlsanity.com/paper/2107.11445/) (2021)
- [Repairing Deep Neural Networks Based on Behavior Imitation](https://mlsanity.com/paper/2305.03365/) (2023)
- [System Safety Monitoring of Learned Components Using Temporal Metric Forecasting](https://mlsanity.com/paper/2405.13254/) (2024)
- [Proof Minimization in Neural Network Verification](https://mlsanity.com/paper/2511.08198/) (2025)
- [A Robust Optimisation Perspective on Counterexample-Guided Repair of Neural Networks](https://mlsanity.com/paper/2301.11342/) (2023)
- [PICID: Proof-Driven Clause Learning in Neural Network Verification](https://mlsanity.com/paper/2503.12083/) (2025)

## Abstract (arXiv)

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 (ACAS 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.