This paper investigates a range of challenges faced in the design of a serious game aimed at teaching history in situ, through the use of an immersive, open virtual environment. In the context of this paper, such an environment is described as an exploratory, expansive virtual world within which a user may interact in a non-linear and situated fashion with the virtual characters that populate it. The main contribution of this paper consists of the introduction of the Levels of Interaction (LoI) framework, designed to assist in the creation of multiple forms of interaction between a user-driven avatar and synthetic characters. The LoI approach addresses the necessity for balancing computational efficiency with the need to provide believable and interactive virtual characters, allowing varying degrees of visual, interactive and behavioural fidelity. The Roma Nova project demonstrates a first implementation of the concept, showing in practice how the LoI are likely to foster more natural interactions between the player and the non-playing characters.
Abstract-This paper investigates a range of challenges faced in the design of a serious game, teaching history to a player immersed in an 'open' virtual environment. In the context of this paper, such an environment is described as an exploratory, expansive virtual world within which a user may interact in a non-linear, situated fashion with both the environment and virtual characters. The main contribution of this paper consists in the introduction of the levels of interaction (LoI), a novel framework designed to assist in the creation of interactions between the player and characters. The LoI approach also addresses the necessity for balancing computational efficiency with the need to provide believable and interactive virtual characters, by allowing varying degrees of animation, display and, ultimately, interaction detail. This paper demonstrates the challenges faced when implementing such a technique, as well as the potential benefits it brings.
This paper describes experimental results regarding the real time implementation of continuous time recurrent neural networks (CTRNN) and the dynamic back-propagation through time (BPTT) algorithm for the on-line learning control laws. Experiments are carried out to control the balance of a biped robot prototype in its standing posture. The neural controller is trained to compensate for external perturbations by controlling the torso's joint motions. Algorithms are embedded in the real time electronic unit of the robot. On-line learning implementations are presented in detail. The results on learning behavior and control performance demonstrate the strength and the efficiency of the proposed approach.
The purpose of the research addressed in this paper is to study the influence of the time window width in dynamic truncated BackPropagation Through Time BPTT(h) learning algorithms. Statistical experiments based on the identification of a real biped robot balancing mechanism are carried out to raise the link between the window width and the stability, the speed and the accuracy of the learning. The time window width choice is shown to be crucial for the convergence speed of the learning process and the generalization ability of the network. Although, a particular attention is brought to a divergence problem (gradient blow up) observed with the assumption where the net parameters are constant along the window. The limit of this assumption is demonstrated and parameters evolution storage, used as a solution for this problem, is detailed.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.