Towards Walkable and Safe Areas: DRL-Based Redirected Walking Leveraging Spatial Walkability Entropy

Redirected walking (RDW) expands the virtually reachable areas within confined physical spaces by real-walking locomotion. However, existing RDW controllers struggle with extracting spatial features, hindering the improvement for physical obstacle avoidance. To overcome this, we propose a novel spatial walkability-aware redirection controller utilizing deep reinforcement learning (DRL), which learns to enhance obstacle avoidance capability by leveraging comprehensive spatial features. Based on information entropy, we innovatively introduce the spatial walkability entropy (SWE) metric to characterize the walkability and safety of each physical position by assessing the difficulty of reaching its surroundings. Guided by this, we design a novel joint reward that considers both the SWE distribution and the user's virtual-physical alignment, providing ample guidance for learning. Moreover, unlike existing controllers employing traditional reset strategies, we propose a novel reset method that maximizes regional entropy to guide users towards more open areas, reducing the re-collision risk. Extensive simulation experiments compare our controller with state-of-the-art (SOTA) redirection controllers. The results demonstrate that our controller significantly reduces physical collisions across various virtual-physical scenarios. Moreover, live user experiments confirm that our controller offers a superior roaming experience in practical settings.