Creating AI for games with Unreal Engine 4

Kushnir, Vasyl; Koman, Bohdan

doi:10.30970/eli.9.113

Cited by 2 publications

(2 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By connecting the actors and agents, the simulation environment is built. e open-source unreal game engine [124] was found to be a popular game engine for building the simulation environment. Most simulation tools offer all kinds of basic sensors for modeling the AV perception.…”

Section: Cosimulationmentioning

confidence: 99%

Evolution of Traffic Microsimulation and Its Use for Modeling Connected and Automated Vehicles

Raju

Farah

2021

Journal of Advanced Transportation

View full text Add to dashboard Cite

Traffic microsimulation has a functional role in understanding the traffic performance on the road network. This study originated with intent to understand traffic microsimulation and its use in modeling connected and automated vehicles (CAVs). Initially, the paper focuses on understanding the evolution of traffic microsimulation and on examining the various commercial and open-source simulation platforms available and their importance in traffic microsimulation studies. Following this, current autonomous vehicle (AV) microsimulation strategies are reviewed. From the review analysis, it is observed that AVs are modeled in traffic microsimulation with two sets of strategies. In the first set, the inbuilt models are used to replicate the driving behavior of AVs by adapting the models’ parameters. In the second strategy, AV behavior is programmed with the help of externalities (e.g., Application Programming Interface (API)). Studies simulating AVs with inbuilt models used mostly VISSIM compared to other microsimulation platforms. In addition, the studies are heavily focused on AVs’ penetration rate impact on traffic flow characteristics and traffic safety. On the other hand, studies which simulated AVs with externalities focused on the communication aspects for traffic management. Finally, the cosimulation strategies for simulating the CAVs are explored, and the ongoing research attempts are discussed. The present study identifies the limitations of present CAV microsimulation studies and proposes prospects and improvements in modeling AVs in traffic microsimulation.

show abstract

Section: Cosimulationmentioning

confidence: 99%

Evolution of Traffic Microsimulation and Its Use for Modeling Connected and Automated Vehicles

Raju

Farah

2021

Journal of Advanced Transportation

View full text Add to dashboard Cite

show abstract

“…Considering that the perception of driving-related stimuli is impaired by the visual crowding, thus the altered saccades are preferred to improve the recognition in urban driving scenes. When a square of length 𝑤 contains 𝑛 𝑠 predicted EFLs with different centroid inside, the altered saccades are preferred as a relatively higher number of drivingrelated visual stimuli is clustered in this region, otherwise, the directed saccade is selected due to its biological simplicity and The proposed neural network takes the above 4 features as feature inputs were constructed to recommend either the altered and predicted saccades under 3 urban driving conditions, i.e., naturalistic, VR test using UE4 [29] (Unreal Engine 4 1 ) and other mixed driving task. Each driving condition included 12 driving video clips with 180 frames length in each clip using 2 types of manipulation (normal and reversed temporal order).…”

mentioning

confidence: 99%

The Alleviation of Perceptual Blindness During Driving in Urban Areas Guided by Saccades Recommendation

Zhang²,

Park³

et al. 2022

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

In advanced industrial applications, computational visual attention models (CVAMs) could predict visual attention very similarly to actual human attention allocation. This has been used as a very important component of technology in advanced driver assistance systems (ADAS). Given that the biological inspiration of the driving-related CVAMs could be obtained from skilled drivers in complex driving conditions, in which the driver's attention is constantly directed at various salient and informative visual stimuli by alternating the eye fixations via saccades to drive safely, this paper proposes a saccade recommendation strategy to enhance the driving safety under urban road environment, particularly when the driver's vision is often impaired by the visual crowding. The altered and directed saccades are collected and optimized by extracting four innate features from human dynamic vision. A neural network isdesigned to classify preferable saccades to reduce perceptual blindness due to visual crowding under urban scenes. A state-of-the-art CVAM is firstly adopted to localize the predicted eye fixation locations (EFLs) in driving video clips. Besides, human subjects' gaze at the recommended EFLs is measured via an eye-tracker. The time delays between the predicted EFLs and drivers' EFLs are analyzed under different driving conditions, followed by the time delays between the predicted EFLs and the driver's hand control. The visually safe margin is then measured by mediating the driving speed and the total delay. Experimental results demonstrate that the recommended saccades can effectively reduce the amount of perceptual blindness, which is known to be of help to further improve road driving safety [1].

show abstract

Creating AI for games with Unreal Engine 4

Cited by 2 publications

References 3 publications

Evolution of Traffic Microsimulation and Its Use for Modeling Connected and Automated Vehicles

Evolution of Traffic Microsimulation and Its Use for Modeling Connected and Automated Vehicles

The Alleviation of Perceptual Blindness During Driving in Urban Areas Guided by Saccades Recommendation

Contact Info

Product

Resources

About