An HMDP�MPC Decision-Making Framework with Adaptive Safety Margins and Hysteresis for Autonomous Driving
Siyuan Li, Chengyuan Liu, Wen-Hua Chen
AI summary
Problem
Fixed safety thresholds in autonomous driving decision-making are brittle across heterogeneous traffic, while velocity-dependent margins cause oscillatory switching and solver infeasibility.
Approach
The framework jointly models ego and surrounding vehicles as hybrid Markov decision processes within an MPC optimizer, using adaptive safety margins paired with a frozen-release hysteresis mechanism to stabilize maneuvers and a two-layer recovery scheme to guarantee feasibility.
Key results
- Unified HMDP-MPC framework jointly models ego and surrounding vehicle maneuvers
- Frozen-release hysteresis mechanism suppresses oscillatory decision switching
- Two-layer recovery scheme ensures decision continuity under solver infeasibility
- Achieves 0.05% collision rate across 8,050 randomized trials with 98.77% nominal MPC resolution
Why it matters
Enables reliable, smooth, and computationally efficient high-level planning for autonomous vehicles in complex, real-world traffic environments.
Abstract
This paper presents a unified decision-making framework that integrates Hybrid Markov Decision Processes (HMDPs) with Model Predictive Control (MPC), augmented by velocity-dependent safety margins and a prediction-aware hys- teresis mechanism. Both the ego and surrounding vehicles are modeled as HMDPs, allowing discrete maneuver transition and kinematic evolution to be jointly considered within the MPC optimization. Safety margins derived from the Intelligent Driver Model (IDM) adapt to traffic context but vary with speed, which can cause oscillatory decisions and velocity fluctuations. To miti- gate this, we propose a frozen-release hysteresis mechanism with distinct trigger and release thresholds, effectively enlarging the reaction buffer and suppressing oscillations. Decision continuity is further safeguarded by a two-layer recovery scheme: a global bounded relaxation tied to IDM margins and a deterministic fallback policy. The framework is evaluated through a case study, an ablation against a no-hysteresis baseline, and large- scale randomized experiments across 18 traffic settings. Across 8,050 trials, it achieves a collision rate of only 0.05%, with 98.77% of decisions resolved by nominal MPC and minimal reliance on relaxation or fallback. These results demonstrate the robustness and adaptability of the proposed decision-making framework in heterogeneous traffic conditions.