mlsanityData to 14 Oct 2026

Risk-Aware Human-in-the-Loop Framework with Adaptive Intrusion Response for Autonomous Vehicles

arXiv 2601.11781 ↗First posted 16 Jan 2026cs.AI cs.CVcited by 0

On the map: End-to-end autonomous driving → Reinforcement learning for driving

also in 1 more
Abstract (arXiv)

Autonomous vehicles must remain safe and effective when encountering rare long-tailed scenarios or cyber-physical intrusions during driving. We present RAIL, a risk-aware human-in-the-loop framework that turns heterogeneous runtime signals into calibrated control adaptations and focused learning. RAIL fuses three cues (curvature actuation integrity, time-to-collision proximity, and observation-shift consistency) into an Intrusion Risk Score (IRS) via a weighted Noisy-OR. When IRS exceeds a threshold, actions are blended with a cue-specific shield using a learned authority, while human override remains available; when risk is low, the nominal policy executes. A contextual bandit arbitrates among shields based on the cue vector, improving mitigation choices online. RAIL couples Soft Actor-Critic (SAC) with risk-prioritized replay and dual rewards so that takeovers and near misses steer learning while nominal behavior remains covered. On MetaDrive, RAIL achieves a Test Return (TR) of 360.65, a Test Success Rate (TSR) of 0.85, a Test Safety Violation (TSV) of 0.75, and a Disturbance Rate (DR) of 0.0027, while logging only 29.07 training safety violations, outperforming RL, safe RL, offline/imitation learning, and prior HITL baselines. Under Controller Area Network (CAN) injection and LiDAR spoofing attacks, it improves Success Rate (SR) to 0.68 and 0.80, lowers the Disengagement Rate under Attack (DRA) to 0.37 and 0.03, and reduces the Attack Success Rate (ASR) to 0.34 and 0.11. In CARLA, RAIL attains a TR of 1609.70 and TSR of 0.41 with only 8000 steps.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Reinforcement learning for driving, one of 9 directions in End-to-end autonomous driving. Builds on 20 of its 33 references that are in the map. First posted on arXiv 16 Jan 2026.

Builds on

20 of 33 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024HAIM-DRL: Enhanced Human-in-the-loop Reinforcement Learning for Safe and Efficient Autonomous Driving6 Jan
  2. 2022Efficient Learning of Safe Driving Policy via Human-AI Copilot Optimization17 Feb

Other references · 18

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  3. 2020Conservative Q-Learning for Offline Reinforcement Learningcited by 1,809
  4. 2016Generative Adversarial Imitation Learningcited by 1,597
  5. 2017Constrained Policy Optimizationcited by 983
  6. 2017Safe Reinforcement Learning via Shieldingcited by 449
  7. 2020Responsive Safety in Reinforcement Learning by PID Lagrangian Methodscited by 316
  8. 2018HG-DAgger: Interactive Imitation Learning with Human Expertscited by 266
  9. 2020Human-in-the-Loop Imitation Learning using Remote Teleoperationcited by 112
  10. 2020Learning to Walk in the Real World with Minimal Human Effortcited by 111
  11. 2017Trial without Error: Towards Safe Reinforcement Learning via Human Interventioncited by 103
  12. 2014Optimizing the CVaR via Samplingcited by 99
6 more
  1. 2015Policy Gradient for Coherent Risk Measurescited by 76
  2. 2022Efficient Risk-Averse Reinforcement Learningcited by 43
  3. 2023Risk-Averse Model Uncertainty for Distributionally Robust Safe Reinforcement Learningcited by 12
  4. 2023Distributional Model Equivalence for Risk-Sensitive Reinforcement Learningcited by 9
  5. 2018Intrusion Detection Systems for Networked Unmanned Aerial Vehicles: A Surveycited by 4
  6. 2024REACT: Autonomous Intrusion Response System for Intelligent Vehiclescited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Race to Recovery: Designing Advanced Safety Systems for Autonomous Driving via Learning Autonomous Racing
  2. 2026Threat-guided Policy-aware Scene Perturbation for Safe Autonomous Driving with Online Reinforcement Learning
  3. 2026World Engine: Towards the Era of Post-Training for Autonomous Driving
  4. 2026Self-Aware Active Learning Enables Continual Improvement in Autonomous Driving
  5. 2025Risk-Aware Reinforcement Learning for Autonomous Driving: Improving Safety When Driving through Intersection
  6. 2025Context-aware Risk Assessment and Its Application in Autonomous Driving
  7. 2026A Risk-Sensitive and Uncertainty-Aware Decision-Making and Control Framework for Safe and Robust Autonomous Driving
  8. 2025AED: Automatic Discovery of Effective and Diverse Vulnerabilities for Autonomous Driving Policy with Large Language Models