Pith. sign in

REVIEW 5 cited by

Enhancing Autonomous Vehicle Training with Language Model Integration and Critical Scenario Generation

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2404.08570 v1 pith:XBIUFHVW submitted 2024-04-12 cs.RO cs.AIcs.LG

Hanlin Tian , Kethan Reddy , Yuxiang Feng , Mohammed Quddus , Yiannis Demiris , Panagiotis Angeloudis This is my paper · ORCID
classification cs.ROcs.AIcs.LG
keywords criticaltraininggenerationlearningperformancesafetyanalysisautonomous
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This paper introduces CRITICAL, a novel closed-loop framework for autonomous vehicle (AV) training and testing. CRITICAL stands out for its ability to generate diverse scenarios, focusing on critical driving situations that target specific learning and performance gaps identified in the Reinforcement Learning (RL) agent. The framework achieves this by integrating real-world traffic dynamics, driving behavior analysis, surrogate safety measures, and an optional Large Language Model (LLM) component. It is proven that the establishment of a closed feedback loop between the data generation pipeline and the training process can enhance the learning rate during training, elevate overall system performance, and augment safety resilience. Our evaluations, conducted using the Proximal Policy Optimization (PPO) and the HighwayEnv simulation environment, demonstrate noticeable performance improvements with the integration of critical case generation and LLM analysis, indicating CRITICAL's potential to improve the robustness of AV systems and streamline the generation of critical scenarios. This ultimately serves to hasten the development of AV agents, expand the general scope of RL training, and ameliorate validation efforts for AV safety.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework

    cs.RO 2025-07 conditional novelty 7.0 of 10

    An agentic LLM framework augments real-world traffic scenarios from text instructions, with output quality close to human-generated scenarios in blind expert evaluation.

  2. From Failures to Fixes: LLM-Driven Scenario Repair for Self-Evolving Autonomous Driving

    cs.CV 2025-05 reject novelty 6.0 of 10

    SERA uses LLM-driven failure analysis and scenario retrieval to select training scenarios for few-shot fine-tuning, improving simulated autonomous driving scores.

  3. Realistic Corner Case Generation for Autonomous Vehicles with Multimodal Large Language Model

    cs.RO 2024-11 conditional novelty 6.0 of 10

    AutoScenario translates multimodal real-world driving data into controllable and diverse corner-case scenarios for autonomous vehicle testing using LLMs and SUMO/CARLA simulations.

  4. Preference-based Multi-Objective Reinforcement Learning

    cs.LG 2025-07 reject novelty 4.0 of 10

    Pb-MORL learns a multi-objective reward model from preference comparisons and claims to achieve Pareto-optimal policies, outperforming an oracle in energy and highway tasks.

  5. A Novel MLLM-based Approach for Autonomous Driving in Different Weather Conditions

    cs.RO 2024-11 reject novelty 3.0 of 10

    A closed-loop study in CARLA/LimSim++ evaluating a GPT-4o prompt-based driving agent across five weather conditions and several camera/LiDAR configurations.

Pith tools