A Social Serious Game Concept for Green, Fluid and Collaborative Driving

Bellotti, Francesco; Berta, Riccardo; Gloria, Alessandro De

doi:10.1007/978-3-319-04370-8_15

Cited by 6 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DGBL is considered a valuable instructional methodology that is based on suggested positive effects on knowledge retention (Barbieri et al, 2014), engagement, motivation, and learning effectiveness (Kebritchi et al, 2010). DGBL approach uses SG, computer games designed for learning as a primary goal (Bellotti et al, 2014), with a specific purpose of engaging players to develop new knowledge and skills (Corti, 2006) and enabling learners to undertake tasks and experience situations. From the business management perspective, SG can be an effective self-learning tool providing practice in safe environments (Vlachopoulos, 2017) and easily accessible, low-cost, yet effective alternative training method (Verkuyl et al, 2019;Wilson, 2009) to a broad spectrum of skills ranging from health, military, and supply chain sectors.…”

Section: Dgbl and Serious Gamesmentioning

confidence: 99%

The Impact of Technology Medium on Learning Effectiveness: Comparison of Animated Video-based Scenario, Game Movie and Serious Game

Djafarova

2024

Preprint

View full text Add to dashboard Cite

Many proponents of the digital game-based learning (DGBL) approach believe that learning through games can revolutionize education. Indeed, DGBL is recognized as having the potential to enhance the learning experience, but it is not well researched how it improves learning effectiveness. This study compares the efficacy between the game and video-based learning tools. Based on Self-Determination Theory and Flow Theory of Optimal Experience, we investigated a relationship between learning tools, motivation, flow, and learning outcomes. We used the experimental data collection method under controlled conditions with 340 university students. Results showed significantly higher learning outcomes for those who learned through learning tools designed using instructional design methodologies. We suggest that the application of instructional design practices matters, and well-designed game-based and videobased learning tools can be equally effective. It should not be assumed that one format of learning tool is more effective than another.

show abstract

Section: Dgbl and Serious Gamesmentioning

confidence: 99%

The Impact of Technology Medium on Learning Effectiveness: Comparison of Animated Video-based Scenario, Game Movie and Serious Game

Djafarova

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Results demonstrate the multidimensionality and complexity of the concept of driving styles. Bellotti et al [27] illustrate a serious game whose goal is to reward and coach the driver after processing vehicular data. The relative score is displayed on the automotive dashboard, and it is designed to enhance and improve driving skills and behavior.…”

Section: Related Workmentioning

confidence: 99%

Implementing Deep Reinforcement Learning (DRL)-based Driving Styles for Non-Player Vehicles

Forneris,

Pighetti,

Lazzaroni

et al. 2023

IJSG

View full text Add to dashboard Cite

We propose a new, hierarchical architecture for behavioral planning of vehicle models usable as realistic non-player vehicles in serious games related to traffic and driving. These agents, trained with deep reinforcement learning (DRL), decide their motion by taking high-level decisions, such as “keep lane”, “overtake” and “go to rightmost lane”. This is similar to a driver’s high-level reasoning and takes into account the availability of advanced driving assistance systems (ADAS) in current vehicles. Compared to a low-level decision making system, our model performs better both in terms of safety and speed. As a significant advantage, the proposed approach allows to reduce the number of training steps by more than one order of magnitude. This makes the development of new models much more efficient, which is key for implementing vehicles featuring different driving styles. We also demonstrate that, by simply tweaking the reinforcement learning (RL) reward function, it is possible to train agents characterized by different driving behaviors. We also employed the continual learning technique, starting the training procedure of a more specialized agent from a base model. This allowed significantly to reduce the number of training steps while keeping similar vehicular performance figures. However, the characteristics of the specialized agents are deeply influenced by the characteristics of the baseline agent.

show abstract

“…The TEAM applications (as described in Table 1) are the virtual sensors and they feed inputs to respective strategy in the game logic. The SG-CB application intends to support a community of road users, who share results and various information [12]. The SG-CB contributes for all the three game logics (virtual bank, competitions and snake & ladders).…”

Section: Serious Game System Architecturementioning

confidence: 99%