Empowering Microscopic Traffic Simulators with Realistic Perception using Surrogate Sensor Models

TL;DR

Results show that MIDAR generates more realistic detection outputs as well as application-level performance metrics than simplified perception models while introducing minimal computational overhead, enabling seamless integration into large-scale, real-time traffic simulations.

Abstract

Simulation is central to the evaluation of intelligent transportation system (ITS) applications. As ITS increasingly incorporates autonomous vehicle (AV) technologies as fleet vehicles and/or mobile sensors, accurate modeling of their perception capabilities becomes essential in high-fidelity simulations. While game-engine-based simulators reproduce realistic perception environments through 3D scene rendering and raw sensor data generation, they face scalability challenges in simulating traffic networks with a large number of AVs due to high computational cost. In contrast, microscopic traffic simulators (MTS) can scale efficiently but lack perception modeling capabilities. To bridge this gap, we propose MIDAR, a surrogate LiDAR detection model that mimics realistic LiDAR detections using only high-level features readily available from MTS. Specifically, MIDAR predicts true-positive and false-negative LiDAR detections based on the relative positions and dimensions of surrounding objects. To capture LiDAR visibility and occlusion effects, MIDAR introduces a ray-hit feature and a Refined Multi-hop Line-of-Sight (RM-LoS) graph processed by a geometry-aware Graph Transformer. MIDAR achieves an AUC of 0.94 in approximating LiDAR detection results using CARLA-generated point cloud data, and an AUC of 0.86 with real-world data from the nuScenes dataset. Two ITS applications, cooperative-perception-based adaptive signal control and vehicle trajectory reconstruction, are integrated with MIDAR to further validate its realism and necessity. Results show that MIDAR generates more realistic detection outputs as well as application-level performance metrics than simplified perception models while introducing minimal computational overhead, enabling seamless integration into large-scale, real-time traffic simulations. The code and data are publicly available at https://github.com/Purdue-CART-Lab/MIDAR.

Figures (8)

• Figure 1: Illustration of sensor data generation and detection in different types of simulatorsa. Game-engine-based simulators provide raw sensor signals, to which object detection algorithms can be directly applied to produce detection results. b. Microscopic traffic simulators apply simplified detection models such as perfect detection and random drop. c. Rule-based approach for microscopic traffic simulators to incorporate geometry-based physical visibility.
• Figure 2: The proposed MIDAR framework.a. Construction of the Refined Multi-hop Line-of-Sight (RM-LoS) graph. b. Calculation of the ray-hit feature using a Height-aware Azimuthal Ray Casting (HARC) approach. c. MIDAR workflow.
• Figure 3: Data Preparation for MIDAR Evaluation.a. Data collection area in CARLA-SUMO co-simulation. b. Construction of MIDAR training and evaluation dataset.
• Figure 4: Comparison between MIDAR and two baseine models
• Figure 5: Study area of CP-based adaptive TSC.a. A real-world intersection at Commonwealth Avenue and North Buona Vista Road in Singapore. b. The intersection in SUMO.