Learning Realistic and Reactive Traffic Agents

In recent years, remarkable strides have been made in the field of autonomous driving, with a particular focus on enhancing perception and prediction capabilities through the integration of big data and advanced deep learning algorithms. Despite these advancements, the persistent challenge of effectively validating the performance of autonomous vehicles (AVs) remains a critical issue. In the realm of microscopic traffic simulation, a noteworthy challenge persists – that of bridging the behavior gap between simulated scenarios and real-world driving situations. Efforts to define agent behavior in simulations manually or replay observed behaviors have proven to be inefficient and prone to inaccuracies, mainly because simulated agents often fail to authentically react to actions initiated by AVs. While rule-based traffic simulation models offer plausible behaviors, they exhibit limitations in adapting to diverse and data-driven behavior patterns within complex driving interactions. Addressing these challenges, we propose a learning-based method for traffic agent simulation, emphasizing realism and reactivity. This involves learning data-driven agent models from real-world driving data with detailed interaction information and high-definition (HD) maps. Utilizing a convolutional neural network (CNN), we extract features and predict future trajectories, achieving realism and reactivity through closed-loop simulation at inference. The proposed model is evaluated using real-world data, demonstrating its effectiveness in simulating diverse and realistic traffic behaviors, like stopping at red traffic lights, yielding to other vehicles during right-turn-on-red, and car following.