Predicting User Intention as Next Direction in Redirected Walking
摘要
How to freely explore virtual space in a limited physical space is a technical challenge in virtual reality technology. In this paper, a new Redirected Walking (RDW) technique based on user intention prediction is proposed. By collecting the walking data of real users, the short-term future walking intention is inferred by utilizing the user’s motion characteristics. Then physical trajectory planning is performed based on the user’s intention to guide the user’s walking. Simulation experiments show that the method can effectively reduce the number of user resets due to collisions with physical obstacles. Based on user experiments with 20 real users, it is shown that the method significantly reduces the number of collision resets while effectively avoiding the strong discomfort of the user in the Virtual Reality (VR) task.