Development of hierarchical models for validating automated driving functions in adaptive traffic simulations

Context

Validation of automated driving functions requires realistic traffic simulations to reliably test behavior in complex scenarios. Traditional simulation approaches based on pre-recorded trajectories are limited because they cannot respond to the behavior of automated vehicles. This leads to inaccurate results and makes it difficult to evaluate driving systems in dynamic traffic situations.
Hierarchical Reinforcement Learning (HRL) offers the potential to develop dynamic and reactive traffic agents. Through its hierarchical structure, complex decision-making processes can be organized at multiple levels, allowing agents to respond adaptively to the behavior of automated vehicles. This enables the generation of critical traffic scenarios in real time and facilitates a more precise study of the behavior of automated vehicles under challenging conditions, helping to improve their robustness.

Goals

• Conceptualization and implementation of a hierarchical agent system for simulating traffic agents
• Use of reinforcement learning to develop adaptive traffic agents that efficiently process relevant information at various levels of abstraction
• Investigation and development of approaches for simulating critical scenarios for automated vehicles
• Validation of the system through simulation and analysis of traffic situations

Requirements

• Interest in the topics of Hierarchical Reinforcement Learning and traffic simulation
• Programming skills in Python, ideally with experience in ML libraries (e.g., PyTorch)
• Motivation and creative thinking