• Corpus ID: 204960781

Learning a Safety Verifiable Adaptive Cruise Controller from Human Driving Data

@article{Lin2019LearningAS,
  title={Learning a Safety Verifiable Adaptive Cruise Controller from Human Driving Data},
  author={Qin Lin and Sicco Verwer and John M. Dolan},
  journal={ArXiv},
  year={2019},
  volume={abs/1910.13526}
}
Imitation learning provides a way to automatically construct a controller by mimicking human behavior from data. For safety-critical systems such as autonomous vehicles, it can be problematic to use controllers learned from data because they cannot be guaranteed to be collision-free. Recently, a method has been proposed for learning a multi-mode hybrid automaton cruise controller (MOHA). Besides being accurate, the logical nature of this model makes it suitable for formal verification. In this… 

Figures and Tables from this paper

References

SHOWING 1-10 OF 26 REFERENCES

Verisig: verifying safety properties of hybrid systems with neural network controllers

This paper presents Verisig, a hybrid system approach to verifying safety properties of closed-loop systems using neural networks as controllers. We focus on sigmoid-based networks and exploit the

Efficiency analysis of formally verified adaptive cruise controllers

TLDR
Combining formal verification techniques for hybrid systems with a wireless communication model, this work analyzes how the expected efficiency of a provably-safe adaptive cruise control system is affected by the value of this timeout parameter.

Towards formal verification of adaptive cruise controller using SpaceEx

  • A. MishraS. Roy
  • Computer Science, Engineering
    2016 International Conference on VLSI Systems, Architectures, Technology and Applications (VLSI-SATA)
  • 2016
A formal mathematical model of an Adaptive Cruise Controller (ACC) in SpaceEx is presented with a view to formally verify it to ensure its safety critical behavior. SpaceEx (an academic open source

Parallelizable Reachability Analysis Algorithms for Feed-Forward Neural Networks

TLDR
This paper presents a reachability analysis method for feed-forward neural networks (FNN) that employ rectified linear units (ReLUs) as activation functions that relies on three reachable-set computation algorithms, namely exact schemes, lazy-approximate schemes, and mixing schemes.

Human-Like Adaptive Cruise Control Systems through a Learning Machine Approach

In this work an Adaptive Cruise Control (ACC) model, with human-like driving capabilities,based on a learning machine approach, is proposed. The system is based on a neural network approach and is

The Algorithmic Analysis of Hybrid Systems

Efficient Identification of Timed Automata: Theory and practice

TLDR
This thesis investigates the difficulty of automatically identifying models from observations and proposes a different method that uses the time information directly in order to produce a timed model, called the timed automaton (TA).

SpaceEx: Scalable Verification of Hybrid Systems

We present a scalable reachability algorithm for hybrid systems with piecewise affine, non-deterministic dynamics. It combines polyhedra and support function representations of continuous sets to

PHAVer: algorithmic verification of hybrid systems past HyTech

  • Goran Frehse
  • Computer Science
    International Journal on Software Tools for Technology Transfer
  • 2007
TLDR
This work addresses the main problems of HyTech with PHAVer, a new tool for the exact verification of safety properties of hybrid systems with piecewise constant bounds on the derivatives, so-called linear hybrid automata.