Dataset design process improves truck perception in city driving
Towards Safer Cities: A Design Process for Perception Datasets in Urban Driving Scenarios
Robotics
Summary
City streets are busy and complicated, making it hard for self-driving vehicles to see and understand everything around them. Most existing data used to teach these vehicles focuses only on passenger cars, ignoring trucks, buses, and trams which behave differently. The authors present a method to create better datasets using map information and real-world examples, especially for trucks in special urban situations. This helps plan what data to collect so self-driving trucks can operate more safely in cities.
What this means in practice
- •For automotive system developers: Create targeted datasets for truck perception tasks in complex urban scenarios, improving safety and reliability of automated heavy vehicles.
- •For urban transport planners: Plan sensor data collection efforts for various transport modes operating in pedestrian zones or specialized urban tasks to enhance automated vehicle operation.
Authors
Alexander Kroth, Cristian Martinez, Steven Peters
Abstract
Urban environments present significant challenges for the perception systems of automated driving due to their high complexity, characterized by dense traffic, diverse obstacles, or a wide range of possible scenarios. While numerous automotive datasets exist, few focus on urban settings, and the majority are acquired exclusively on passenger cars and overlook other transport modalities such as heavy-duty trucks, busses and trams. In contrast to passenger vehicles, these platforms operate under different geographical and operational constraints; including traversing pedestrian zones or platform-specific tasks such as movement of trailer or winter service. In this work a method is proposed for a guided dataset creation based on an analysis of existing datasets using user-generated map data. Furthermore, representative truck-specific use cases are identified and exemplified to demonstrate the applicability of the proposed methodology and to support targeted acquisition planning.