A Markov Decision Process Model for a Reinforcement Learning-based Autonomous Pedestrian Crossing Protocol

Hamdani, Sara El; Loudari, Salaheddine; Novotný, Stanislav; Bouchner, Petr; Benamar, Nabil

doi:10.1109/menacomm50742.2021.9678310

Cited by 4 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It provides a mathematical framework for representing environments in reinforcement learning applications. [10] For our application, we define a quadruple MDP (Markov decision process) to represent the environment as follows:…”

Section: Problem Definitionmentioning

confidence: 99%

See 1 more Smart Citation

Traffic Signal Control System Using Contour Approximation Deep Q-Learning

Ramya,

Bharath,

Revanth Krishna

et al. 2024

Cc 2023

View full text Add to dashboard Cite

show abstract

Section: Problem Definitionmentioning

confidence: 99%

“…1. We propose an off-policy end-to-end deep reinforcement learning [10] based traffic signal control system to control dynamic traffic efficiently at intersections with top priority for emergency vehicles.…”

Section: Introductionmentioning

confidence: 99%

Traffic Signal Control System Using Contour Approximation Deep Q-Learning

Ramya,

Bharath,

Revanth Krishna

et al. 2024

Cc 2023

View full text Add to dashboard Cite

show abstract

“…Driving simulator technology is one of the most sophisticated applications of computer-aided kinematic and dynamic simulations [ 1 ] designed to simulate the various physical and visual characteristics of driving [ 2 ] and widely employed to explore diverse aspects of the transportation landscape [ 3 ]. For instance, simulators can play a significant role in testing future innovations such as Autonomous Vehicles (AVs) [ 4 ] and evaluating performance as well as passenger experience [ 5 ] in different driving scenarios (i.e., road conditions, weather, traffic [ 6 ], vulnerable road users [ 7 , 8 ]) which is crucial for the development and validation of these technologies before deploying them in real-world use [ 9 ].…”

Section: Introductionmentioning

confidence: 99%

Fidelity Assessment of Motion Platform Cueing: Comparison of Driving Behavior under Various Motion Levels

Hamdani

Bouchner

Kunclova

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

The present paper focuses on vehicle simulator fidelity, particularly the effect of motion cues intensity on driver performance. The 6-DOF motion platform was used in the experiment; however, we mainly focused on one characteristic of driving behavior. The braking performance of 24 participants in a car simulator was recorded and analyzed. The experiment scenario was composed of acceleration to 120 km/h followed by smooth deceleration to a stop line with prior warning signs at distances of 240, 160, and 80 m to the finish line. To assess the effect of the motion cues, each driver performed the run three times with different motion platform settings–no motion, moderate motion, and maximal possible response and range. The results from the driving simulator were compared with data acquired in an equivalent driving scenario performed in real conditions on a polygon track and taken as reference data. The driving simulator and real car accelerations were recorded using the Xsens MTi-G sensor. The outcomes confirmed the hypothesis that driving with a higher level of motion cues in the driving simulator brought more natural braking behavior of the experimental drivers, better correlated with the real car driving test data, although exceptions were found.

show abstract