Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Extending Adaptive Cruise Control with Machine Learning Intrusion Detection Systems

Lotfi Ben Othmane, Yasaswini Konapalli, Naga Prudhvi Mareedu

TL;DR

It is proved that augmenting ACC with an IDS, under assumed detection-performance and latency constraints, can mitigate these attacks and help preserve ACC's collision-avoidance guarantees.

Abstract

An Adaptive Cruise Control (ACC) system automatically adjusts the host vehicle's speed to maintain a safe following distance from a lead vehicle. In typical implementations, a feedback controller (e.g., a Proportional-Integral-Derivative (PID) controller) computes the host vehicle's acceleration using a target speed and a spacing error, defined as the difference between the measured inter-vehicle distance and a desired safe distance. ACC is often assumed to be resilient to fault-injection attacks because a Kalman filter (KF) can smooth noisy speed measurements. However, we show--through analytical proofs and simulation results--that a KF can tolerate injected speed values only up to a bounded threshold. When injected values exceed this threshold, the filter can be driven off track, causing the ACC controller to make unsafe acceleration decisions and potentially leading to collisions. Our main contribution is to augment the PID-based controller with Intrusion Detection System (IDS) outputs, yielding Intrusion Detection Systems-Based Adaptive Cruise Control (ACC-IDS). The ACC-IDS controller is simple and implementable: a binary intrusion flag switches the control law to emergency braking. We prove that augmenting ACC with an IDS, under assumed detection-performance and latency constraints, can mitigate these attacks and help preserve ACC's collision-avoidance guarantees.

Extending Adaptive Cruise Control with Machine Learning Intrusion Detection Systems

TL;DR

It is proved that augmenting ACC with an IDS, under assumed detection-performance and latency constraints, can mitigate these attacks and help preserve ACC's collision-avoidance guarantees.

Abstract

An Adaptive Cruise Control (ACC) system automatically adjusts the host vehicle's speed to maintain a safe following distance from a lead vehicle. In typical implementations, a feedback controller (e.g., a Proportional-Integral-Derivative (PID) controller) computes the host vehicle's acceleration using a target speed and a spacing error, defined as the difference between the measured inter-vehicle distance and a desired safe distance. ACC is often assumed to be resilient to fault-injection attacks because a Kalman filter (KF) can smooth noisy speed measurements. However, we show--through analytical proofs and simulation results--that a KF can tolerate injected speed values only up to a bounded threshold. When injected values exceed this threshold, the filter can be driven off track, causing the ACC controller to make unsafe acceleration decisions and potentially leading to collisions. Our main contribution is to augment the PID-based controller with Intrusion Detection System (IDS) outputs, yielding Intrusion Detection Systems-Based Adaptive Cruise Control (ACC-IDS). The ACC-IDS controller is simple and implementable: a binary intrusion flag switches the control law to emergency braking. We prove that augmenting ACC with an IDS, under assumed detection-performance and latency constraints, can mitigate these attacks and help preserve ACC's collision-avoidance guarantees.
Paper Structure (23 sections, 3 theorems, 51 equations, 8 figures, 2 tables)

This paper contains 23 sections, 3 theorems, 51 equations, 8 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Overview of the Adaptive Cruise Control Model
  3. Safe Following Distance
  4. Tracking Errors
  5. Control Objectives
  6. PID Controller
  7. Related work
  8. Limitation of Adaptive Cruise Control with Kalman Filter
  9. Prediction of Host-Vehicle Speed Using the Kalman Filter
  10. Step 1: Prediction to time $t+ \Delta t$
  11. Step 2: Update using the measurement $z(t+ \Delta t)$
  12. Identifying the Host-Vehicle Speed Threshold That Violates ACC
  13. Measured Host-Vehicle Speed Values Exceeding the Threshold in the Presence of a Kalman Filter
  14. Extending Adaptive Cruise Control with Intrusion Detection Systems
  15. Augmenting ACC with IDS (ACC-IDS)
  16. ...and 8 more sections

Key Result

Lemma 4.1

A host vehicle maintains a safe distance to the lead vehicle, as formulated in Eq. eq:safedistance, if its speed $v_h^+(t)$ is less than or equal to the threshold

Figures (8)

  • Figure 1: The ACC system uses radar or LiDAR to measure the distance to the lead vehicle and compares it to a safe following distance.
  • Figure 2: Upper- and lower-level controllers in the ACC architecture JOS2024.
  • Figure 3: Block diagram of the ACC system.
  • Figure 4: Block diagram of ACC with IDS. The model augments the conventional ACC controller with an intrusion flag and a confidence value provided by the IDS.
  • Figure 5: Simulation of Adaptive Cruise Control of a host vehicle and lead vehicle where the host vehicle uses Kalman Filter (KF) for the speed readings.
  • ...and 3 more figures

Theorems & Definitions (3)

  • Lemma 4.1: ACC speed violation at next-step gap
  • Lemma 4.2: ACC speed violation with a Kalman filter
  • Theorem 5.1: IDS braking-distance assures collision avoidance