☆ 4.7 Article

An Adaptive Human Driver Model for Realistic Race Car Simulations

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS (2023)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Multidisciplinary Sciences

Outracing champion Gran Turismo drivers with deep reinforcement learning

Peter R. Wurman et al.

Summary: This study explains how agents for Gran Turismo were trained to compete with the world's best e-sports drivers by combining deep reinforcement learning algorithms with mixed-scenario training to learn an integrated control policy that combines exceptional speed with impressive tactics. The agents were able to win a head-to-head competition against four of the world's best Gran Turismo drivers, showcasing the possibilities and challenges of using these techniques to control complex dynamical systems in domains where agents must respect imprecisely defined human norms.

NATURE (2022)

添加到收藏夹

Article Engineering, Mechanical

Identification and modelling of race driving styles

Stefan Loeckel et al.

Summary: The paper presents a holistic approach to identify and model individual race driving styles with the Driver Identification and Metric Ranking Algorithm (DIMRA) and Probabilistic Modeling of Driver Behavior (ProMoD). Evaluation shows the capability of deriving metrics describing human race driving styles and generating competitive laps with human-like controls.

VEHICLE SYSTEM DYNAMICS (2022)

添加到收藏夹

Article Automation & Control Systems

A Probabilistic Model for Driving-Style-Recognition-Enabled Driver Steering Behaviors

Zejian Deng et al.

Summary: This study classified drivers into different styles using PCA and K-means clustering, established a driver steering model based on model predictive control, and calibrated driver characteristics using the maximum lateral acceleration and probabilistic models. Point estimation and interval estimation models were then used to determine driving style and adjust constraints in the steering model based on stochastic programming. Simulation experiments demonstrated variations in actual output trajectories between aggressive and cautious drivers.

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS (2022)

添加到收藏夹

Article Engineering, Civil

Driving Behavior Modeling Using Naturalistic Human Driving Data With Inverse Reinforcement Learning

Zhiyu Huang et al.

Summary: This paper presents a driving model based on internal reward functions that mimics human decision-making mechanisms. The use of maximum entropy inverse reinforcement learning allows for the inference of reward function parameters from naturalistic human driving data. The results demonstrate that the learned reward functions effectively capture the preferences of different drivers and improve the accuracy of the modeling process.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2022)

添加到收藏夹

Article Robotics

Super-Human Performance in Gran Turismo Sport Using Deep Reinforcement Learning

Florian Fuchs et al.

Summary: Autonomous car racing presents a major challenge in robotics, but a learning-based system using high-fidelity car simulation, proxy rewards, and deep reinforcement learning has shown impressive performance, surpassing human players and built-in AI in Gran Turismo Sport.

IEEE ROBOTICS AND AUTOMATION LETTERS (2021)

添加到收藏夹

Article Robotics

Imitation Learning of Hierarchical Driving Model: From Continuous Intention to Continuous Trajectory

Yunkai Wang et al.

Summary: The study introduces a hierarchical driving model that includes continuous intention and continuous dynamics modules, aiming to reduce the gap between machine level driving and human level driving. Through the use of a continuous function approximator network, the research achieves smoother trajectory generation and more accurate displacement and velocity prediction.

IEEE ROBOTICS AND AUTOMATION LETTERS (2021)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

End-to-End Urban Driving by Imitating a Reinforcement Learning Coach

Zhejun Zhang et al.

Summary: This paper introduces a method for training end-to-end driving agents supervised by a reinforcement learning expert, which effectively improves driving performance and learning efficiency, as well as the generalization ability under different town and weather conditions.

2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021) (2021)

添加到收藏夹

Article Robotics

A Probabilistic Framework for Imitating Human Race Driver Behavior

Stefan Lockel et al.

IEEE ROBOTICS AND AUTOMATION LETTERS (2020)

添加到收藏夹

Article Robotics

Learning-Based Model Predictive Control for Autonomous Racing

Juraj Kabzan et al.

IEEE ROBOTICS AND AUTOMATION LETTERS (2019)

添加到收藏夹

Review Computer Science, Artificial Intelligence

Manual Control Cybernetics: State-of-the-Art and Current Trends

Max Mulder et al.

IEEE TRANSACTIONS ON HUMAN-MACHINE SYSTEMS (2018)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Using probabilistic movement primitives in robotics

Alexandros Paraschos et al.

AUTONOMOUS ROBOTS (2018)

添加到收藏夹

Article Multidisciplinary Sciences

Differences between racing and non-racing drivers: A simulator study using eye-tracking

Peter M. van Leeuwen et al.

PLOS ONE (2017)

添加到收藏夹

Article Automation & Control Systems

A Driver Steering Model With Personalized Desired Path Generation

Scott Schnelle et al.

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS (2017)

添加到收藏夹

Article Automation & Control Systems

Evaluating Driving Styles by Normalizing Driving Behavior Based on Personalized Driver Modeling

Bin Shi et al.

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS (2015)

添加到收藏夹

Article Engineering, Mechanical

Optimal control for a Formula One car with variable parameters

Giacomo Perantoni et al.

VEHICLE SYSTEM DYNAMICS (2014)

添加到收藏夹

Article Automation & Control Systems

IMITATION LEARNING OF CAR DRIVING SKILLS WITH DECISION TREES AND RANDOM FORESTS

Pawel Cichosz et al.

INTERNATIONAL JOURNAL OF APPLIED MATHEMATICS AND COMPUTER SCIENCE (2014)

添加到收藏夹

Article Psychology, Applied

The adaptation period to a driving simulator

Adi Ronen et al.

TRANSPORTATION RESEARCH PART F-TRAFFIC PSYCHOLOGY AND BEHAVIOUR (2013)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Race driver model

F. Braghin et al.

COMPUTERS & STRUCTURES (2008)

添加到收藏夹

Article Engineering, Civil

Collision avoidance for vehicle-following systems

Stefan K. Gehrig et al.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2007)

添加到收藏夹

Article Behavioral Sciences

Modeling driver behavior in a cognitive architecture

Dario D. Salvucci

HUMAN FACTORS (2006)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.