Collaborative virtual training with physical and communicative autonomous agents

Abstract

Virtual agents are a real asset in Collaborative Virtual Environment for Training (CVET) as they can replace missing team members. Collaboration between such agents and users, however, is generally limited. We present here a whole integrated model of CVET focusing on the abstraction of the real or virtual nature of the actor to define a homogenous collaboration model. First, we define a new collaborative model of interaction. This model notably allows to abstract the real or virtual nature of a teammate. Moreover, we propose a new role exchange approach so that actors can swap their roles during training. The model also permits the use of physically based objects and characters animation to increase the realism of the world. Second, we design a new communicative agent model which aims at improving collaboration with other actors using dialogue to coordinate their actions and to share their knowledge. Finally, we evaluated the proposed model to estimate the resulting benefits for the users and we show this is integrated in existing CVET applications.

An overview of self-adaptive technologies within virtual reality training

“…Autonomous agents provide many benefits for virtual training courses, such as: being viable alternative to lecturers (Li et al, 2015), collaborating and sharing knowledge between each other, replacing missing team members (Lopez et al, 2014), acting as pedagogical assistants, interacting with trainees to facilitate training (Bouras et al, 2000).…”

“…Autonomous agents can collaborate and share knowledge to replace missing team members in collaborative virtual environment for training (CVET) (Lopez et al, 2014).…”

Approximate resolution of asynchronous conflicts among sequential collaborations in dynamic virtual environments

“…Subsequently, User B adds a road o 2 , which manages the paths of the players, into the work set W 2 as displayed in Figure 10 (B). Then, User C deploys two buildings o 3 and o 4 on the shared game design space at time t = 3. These buildings are also registered to both W 3 and O as indicated in Figure 10 Approximate resolution of asynchronous conflicts J. Lee et al Figure 11.…”

Hybrid Teamwork: Consideration of Teamwork Concepts to Reach Naturalistic Interaction between Humans and Conversational Agents

“…Furthermore, CAs serving the role of a peer were examined in five studies. In accordance to their role, these CAs behave and communicate in the manner of an autonomous team member and are capable of coordinating actions, specifying goals with a human member and monitoring task progress [51][52][53]. Furthermore, the CAs are capable of proactively managing conflicts and creating shared mental models [54,55].…”

“…In line with this concept, the CA assists team members in finding support (taking over specific activities) by notifying other members that workers with a high workload need support completing their (sub-) task. The CA by Lopez et al [52] is equipped with a knowledge representation about the task, the team and itself. Due to this technological architecture, the CA is able to reactively respond to human team members' oral questions about current plans to accomplish goals.…”