Believable NPCs in serious games: HTN planning approach based on visual perception

On the way of the creation of virtual autonomous characters that are lifelike, intelligent and convey empathy, a strategic planning architecture is presented in the domain of serious games, where games are designed and built for an educational primary purpose other than pure entertainment. Our serious game is in the domain of emergency management; firefighters and first responders in accidents situations. Two contributions are presented in this paper; firstly, a visual perception system for non-player characters (NPCs) along with a short-term memory (working memory) are implemented so that NPCs will have access to only limited information and have to build their plans and make their decisions based on what they can perceive from their surrounding environment. Secondly, an HTN planning approach is implemented based on SHOP for the domain of our serious game. Five modules were developed in this part; Controller, World Model, Domain, Interface and HTN Planner. The plan is generated online based on the information gathered from the visual perception system and stored in the working memory. Our experiment shows the effectiveness of the proposed approach to create believable NPC behavior.