MAN Truck & Bus has become the first truck manufacturer to publish a comprehensive 747-scene set of sensor and vehicle data from development drives for autonomous driving. The open exchange of such freely accessible data sets among various stakeholders—manufacturers, universities, and software developers—accelerates development and promotes the standardization of data formats. This standardization enables a consistent comparison of results and methods, Open Data Sharing in Autonomous Vehicle Development serving as a reference for scientific studies and simplifying collaboration with external development partners.

“Data sets like MAN TruckScenes are crucial for data-driven development. While numerous publicly available data sets exist for the passenger car sector, the truck sector has been lacking. With MAN TruckScenes, we are moving forward to fill this gap,” says Dr. Frederik Zohm, Executive Board Member for Research and Development at MAN Truck & Bus.

Development Basis for Autonomous Hub-to-Hub Transportation
The data set published by MAN primarily covers driving operations on German highways and associated feeder routes, as well as terminal environments. This addresses the demand for hub-to-hub transportation between logistics hubs, which MAN is focusing on as a scenario for driverless driving. The sensor set includes data from four cameras, six lidars, six radars, two inertial measurement units (IMUs) for determining position in surrounding space, and high-precision global navigation satellite system (GNSS) data.
MAN TruckScenes is the first data set to include 4D radar data with 360° coverage, making it the largest radar data set with annotated 3D bounding boxes. The 747 scenes included in the data set capture various weather conditions and are divided into training, test, and validation sets. Each scene contains sensor and vehicle data from a single driving sequence, along with corresponding annotations. These annotations describe the driving situation, environmental conditions, and object markings around the vehicle, forming the basis for machine learning in the development of neural networks for autonomous driving. Public data sets also allow for standardized evaluation of environment recognition performance, facilitating continuous improvements.

MAN Truck & Bus on the Road to Autonomous Trucks
MAN is advancing autonomous driving through various research and development projects. From 2018 to 2020, MAN developed and tested a driverless truck for container handling at the Port of Hamburg in collaboration with Hamburger Hafen und Logistik AG. From 2019 to 2023, the ANITA project, in partnership with Deutsche Bahn, Fresenius University of Applied Sciences, and Götting KG, focused on the complete digital integration of an autonomous truck into the logistics process from road to rail.
Since 2022, MAN has been working with eleven partners in the ATLAS-L4 funding project to develop an autonomous truck for highway transport between logistics hubs. This project specifically addresses the autonomous driving law passed in Germany in 2021, which allows driverless driving on defined routes with technical supervision. By the end of the project in 2025, practical test drives of the prototype with a safety driver on the highway are planned. Autonomous driving for trucks is expected to enter series production by the end of the decade.
Comments