Agent navigation using deep learning with agent space heat map for crowd simulation. (20th May 2019)

• Record Type: Journal Article
• Authors: Oshita, Masaki
• Is Part Of: Computer animation and virtual worlds. Volume 30:Number 3/4(2019)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2019-05-20
• Subjects: agent navigation -- crowd simulation -- deep learning -- neural network; Computer animation -- Periodicals; Visualization -- Periodicals; 006.6
• DOI: 10.1002/cav.1878
• Languages: English
• ISSNs: 1546-4261

Abstract

Abstract: We propose a novel method of crowd simulation that employs a deep learning technique for controlling individual agents. We use a convolutional neural network to learn agent space heat maps that are generated from example crowd animations. A heat map contains the positions and speeds of nearby agents and the temporary target position that indicates an appropriate heading direction for the agent to reach the final target position efficiently. When controlling an agent, an agent space heat map that contains possible temporary target positions is estimated from the trained model and the agent space heat map that contains only the positions and speeds of nearby agents. In addition, evaluation functions are used to choose a temporary target position from the estimated heat map. Individual agents are controlled using a force‐based model so that they move toward the estimated temporary target position. Our approach realizes human‐like navigation by combining the intuitive and logical aspects of decision‐making. Abstract : We propose a crowd simulation method that employ a convolutional neural network to learn agent space heat maps that are generated from example crowd animations. When controlling an agent, an agent space heat map that contains possible temporary target positions is estimated from the trained model and the agent space heat map that contains only the positions and speeds of nearby agents. Individual agents are controlled using a force‐based model so that they move toward the estimated temporary target position.