Interaction of Autonomous and Manually Controlled Vehicles Multiscenario Vehicle Interaction Dataset

2024-03-13

IEEE Intelligent Transportation Systems Magazine

AI Summary

To address the scarcity of high-quality multimodal interaction data, high annotation costs, and poor cross-sensor generalization in autonomous driving, this work introduces IAMCV—the first open multimodal vehicle-to-vehicle interaction dataset covering representative German traffic scenarios, including roundabouts, intersections, urban/rural roads, and highways. It systematically captures and synchronously annotates long-term, multimodal sensor data (LiDAR, multi-camera, IMU-GPS, and CAN bus) from mixed human-driven and autonomous vehicles. We propose a novel ROS-based online camera calibration framework and an unsupervised trajectory clustering paradigm, reducing calibration error by 12%. We further demonstrate YOLOv8’s strong transferability for cross-resolution LiDAR object detection, with mAP variation under 3.5%. The dataset is publicly released to support research in perception modeling, motion pattern recognition, and interactive behavior understanding.

Technology Category

• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Multimodal Learning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

The acquisition and analysis of high-quality sensor data constitute an essential requirement in shaping the development of fully autonomous driving systems. This process is indispensable for enhancing road safety and ensuring the effectiveness of the technological advancements in the automotive industry. This study introduces the Interaction of Autonomous and Manually Controlled Vehicles (IAMCV) dataset, a novel and extensive dataset focused on intervehicle interactions. The dataset, enriched with a sophisticated array of sensors such as lidar, cameras, inertial measurement unit/Global Positioning System, and vehicle bus data acquisition, provides a comprehensive representation of real-world driving scenarios that include roundabouts, intersections, country roads, and highways, recorded across diverse locations in Germany. Furthermore, the study shows the versatility of the IAMCV dataset through several proof-of-concept use cases. First, an unsupervised trajectory clustering algorithm illustrates the dataset’s capability in categorizing vehicle movements without the need for labeled training data. Second, we compare an online camera calibration method with the Robot Operating System-based standard, using images captured in the dataset. Finally, a preliminary test employing the YOLOv8 object-detection model is conducted, augmented by reflections on the transferability of object detection across various lidar resolutions. These use cases underscore the practical utility of the collected dataset, emphasizing its potential to advance research and innovation in the area of intelligent vehicles.

Problem

• Develop a comprehensive dataset for autonomous and manual vehicle interactions.
• Enhance road safety and autonomous driving system effectiveness.
• Demonstrate dataset utility through trajectory clustering and object detection.

Innovation

• IAMCV dataset with diverse sensor integration
• Unsupervised trajectory clustering for vehicle movement
• YOLOv8 object-detection model testing across LIDAR resolutions