The OpenCDA Open-Source Ecosystem for Cooperative Driving Automation Research

Abstract

Advances in Single-vehicle intelligence of automated driving has encountered great challenges because of limited capabilities in perception and interaction with complex traffic environments. Cooperative Driving Automation (CDA) has been considered a pivotal solution to next-generation automated driving and smart transportation. Though CDA has attracted much attention from both academia and industry, exploration of its potential is still in its infancy. In industry, companies tend to build their in-house data collection pipeline and research tools to tailor their needs and protect intellectual properties. Reinventing the wheels, however, wastes resources and limits the generalizability of the developed approaches since no standardized benchmarks exist. On the other hand, in academia, due to the absence of real-world traffic data and computation resources, researchers often investigate CDA topics in simplified and mostly simulated environments, restricting the possibility of scaling the research outputs to real-world scenarios. Therefore, there is an urgent need to establish an open-source ecosystem (OSE) to address the demands of different communities for CDA research, particularly in the early exploratory research stages, and provide the bridge to ensure an integrated development and testing pipeline that diverse communities can share. In this paper, we introduce the OpenCDA research ecosystem, a unified OSE integrated with a model zoo, a suite of driving simulators at various resolutions, large-scale real-world and simulated datasets, complete development toolkits for benchmark training/testing, and a scenario database/generator. We also demonstrate the effectiveness of OpenCDA OSE through example use cases, including cooperative 3D LiDAR detection, cooperative merge, cooperative camerabased map prediction, and adversarial scenario generation.

Hierarchical Interpretable Imitation Learning for End-to-End Autonomous Driving

“…Testing IVs in real systems often comes with potentially fatal safety risks. Therefore, algorithms in autonomous driving are often evaluated in artificial systems with the utilization of open-source datasets and simulation platforms [154].…”

V2V4Real: A Real-world Large-scale Dataset for Vehicle-to-Vehicle Cooperative Perception

“…The project belongs to OpenCDA ecosystem [48] and is funded in part by the Federal Highway Administration project and California RIMI Program. Special thanks go to Transportation Research Center Inc for their collaboration in experimental data collection and processing.…”

Multi-vehicle Platoon Overtaking Using NoisyNet Multi-Agent Deep Q-Learning Network

“…The cooperation of multiple vehicles is a promising way to improve traffic efficiency and reduce congestion, and many research works have been reported. By integrating CARLA [6] and SUMO [7], OpenCDA [8,9] was proposed, which supports both cooperative driving automation prototyping and regular autonomous driving components. Based on OpenCDA, a series of multi-vehicle collaboration works focused on various fields were studied, e.g., collaborative perception [1,2,[10][11][12][13][14], planning [15], localization, and safety system [16].…”