ITSC 2025 Paper Abstract

Sense, Comprehend, Plan, Act: Design and Experimental Verification of a Situation-Aware Driving Function

Scheduled for presentation during the Regular Session "S27a-Safety and Risk Assessment for Autonomous Driving Systems" (TH-LM-T27), Thursday, November 20, 2025, 11:10−11:30, Broadbeach 3

2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), November 18-21, 2025, Gold Coast, Australia

This information is tentative and subject to change. Compiled on October 18, 2025

Keywords Autonomous Vehicle Safety and Performance Testing, Real-world ITS Pilot Projects and Field Tests, Real-time Motion Planning and Control for Autonomous Vehicles in ITS Networks

Abstract

To progress from the currently available advanced driver-assistance systems to more advanced automation levels, automated vehicles must possess situational awareness. This capability enables the vehicle to interpret its surroundings, analyze information, and formulate appropriate driving tactics. In this study, we introduce a situation-aware driving feature comprising three elements. Initially, a neural network is utilized to detect and classify objects in the vehicle's vicinity, including stationary objects, pedestrians, and other vehicles. Following this, a knowledge graph is employed to structure the data from the vehicle perception and make deductions about current driving circumstances. By means of this deduction, the vehicle assesses the potential whether it needs to change its behavior in relation to other entities (characterized, among other factors, by their category and motion) and determines if, for example, specific social norms or traffic regulations should be followed at that time. These social norms and traffic rules are enforced by a trajectory planner, which adjusts the risk associated with objects and crossing road markings, essentially molding the risk level of the outcomes of actions involving crossing these markings. We showcase the functionality using an actual experimental vehicle in a range of scenarios, from overtaking static objects to encountering pedestrians at crossings. The empirical findings indicate that the vehicle can accurately assess the situations and exhibit the intended behavior in various real-world scenarios.