Scenario-Based Hierarchical Reinforcement Learning for Automated Driving Decision Making
This work addresses the problem of generalizability and learning efficiency in automated driving systems, though it appears incremental as it builds on existing hierarchical and scenario-based methods.
The paper tackles the challenge of developing decision-making algorithms for automated driving by introducing SAD-RL, a framework that integrates hierarchical reinforcement learning in a scenario-based environment, resulting in an agent that achieves safe behavior in both easy and challenging situations efficiently.
Developing decision-making algorithms for highly automated driving systems remains challenging, since these systems have to operate safely in an open and complex environments. Reinforcement Learning (RL) approaches can learn comprehensive decision policies directly from experience and already show promising results in simple driving tasks. However, current approaches fail to achieve generalizability for more complex driving tasks and lack learning efficiency. Therefore, we present Scenario-based Automated Driving Reinforcement Learning (SAD-RL), the first framework that integrates Reinforcement Learning (RL) of hierarchical policy in a scenario-based environment. A high-level policy selects maneuver templates that are evaluated and executed by a low-level control logic. The scenario-based environment allows to control the training experience for the agent and to explicitly introduce challenging, but rate situations into the training process. Our experiments show that an agent trained using the SAD-RL framework can achieve safe behaviour in easy as well as challenging situations efficiently. Our ablation studies confirmed that both HRL and scenario diversity are essential for achieving these results.