HumanSim: Human-Like Multi-Agent Novel Driving Simulation for Corner Case Generation
Keywords: Autonomous driving, Corner case, Large language models
TL;DR: We propose HumanSim, a human-like multi-agent novel simulator that leverages large language models to simulate human-like driving behaviors and is convenient to construct corner cases.
Subject: Corner case mining and generation for autonomous driving
Confirmation: I have read and agree with the submission policies of ECCV 2024 and the W-CODA Workshop on behalf of myself and my co-authors.
Abstract: Autonomous driving research faces challenges in generating corner case data, which is crucial yet costly. While current methods like diffusion models and Neural Radiance Field (NeRF) have effectively generated visual-level corner cases, they fall short in creating planning-level scenarios. To address this, we propose HumanSim, a Human-Like Multi-Agent Novel simulator that leverages large language models (LLMs) to simulate human-like driving behaviors. This approach offers exceptional adaptability, granularity, and situational awareness, enhancing the realism of simulations. HumanSim facilitates the construction of complex corner cases, such as swerving driving or emergency aircraft landing, and balances transparency with efficiency in decision-making. The experiments show its effectiveness in replicating human driving, and the integration of LLMs brings convenience for humans to understand decisions of agents and construct corner cases. HumanSim provides a comprehensive platform for testing and refining next-generation autonomous driving technologies. Visit our website for more details: https://humansim.github.io/.
Submission Number: 9
Loading