Local Path Generation for Autonomous Navigation on Public Roads Based on Low-Definition Topological Maps
Simone Specchia, Emanuele Frizzi, Riccardo Pieroni, Luca Crotti, Giulio Panzani, Matteo Corno, Sergio M. Savaresi · 2025
Path planning is one of the most challenging aspects for the development of self-driving vehicles, due to the complexity and variety of contexts of urban and suburban environments. Prior knowledge of the navigation environment, in the form of highly accurate maps, is therefore often exploited in order to simplify this task. The need for detailed a-priori maps represents one of the major limiting factors for the widespread adoption of autonomous vehicles beyond small areas, for which managing and updating such maps is feasible in terms of resources required. For this reason, in the last years a growing interest has been put towards developing navigation approaches that are based on topological maps databases, for which many providers are already available. These types of maps are however less accurate, therefore requiring the implementation of a local planner that combines this information with online observations from a perception module, in order to generate trajectories that traverse the road safely. This paper presents a two-phase planning algorithm that exploits the OpenStreetMap database and an on-board perception system, and considers the vehicle’s handling characteristics to generate feasible trajectories. The approach is validated with an experimental session on public roads open to traffic.