Proximal Policy Optimization–Based Deep Reinforcement Learning for Intelligent Test Case Generation in Autonomous Vehicles
Bibliographic record
Abstract
Autonomous Vehicles (AVs) require extensive and diverse testing to ensure safe and reliable operation under complex real-world driving conditions.Existing test case generation methods, including random sampling and rule-based scenario construction, cannot often adaptively expose rare and safety-critical events.This paper proposes a Proximal Policy Optimization (PPO)-based Deep Reinforcement Learning (DRL) framework for intelligent test case generation in autonomous driving systems.The problem is formulated as a Markov Decision Process (MDP), allowing a DRL agent to interact with the CARLA Simulation (CARLA) platform and iteratively synthesize challenging driving scenarios.The agent learns to adjust key parameters such as traffic density, vehicle behaviors, and environmental conditions to maximize the discovery of safety-critical events.PPO is adopted to ensure stable and sample-efficient policy learning during scenario generation.The framework is evaluated on thousands of simulated driving episodes across diverse urban and highway scenarios using metrics including safetycritical event detection rate, test coverage, and scenario diversity.Experimental results demonstrate over a 38% improvement in detecting safety-critical events compared with random testing and rule-based baselines, highlighting the effectiveness of the proposed system for improving AV validation and reliability.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".