Autonomous Drifting Control in 3D Car Racing Simulator

Igor, Zubov; Afanasyev, Ilya; Gabdullin, Aidar; Mustafin, Ruslan; Shimchik, Ilya

doi:10.1109/is.2018.8710588

Cited by 11 publications

(8 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To improve the convergence ability and avoid the high sample complexity, one of the leading state-of-the-art methods called soft actor-critic (SAC) [17] [2] to understand and control high sideslip drift maneuvers of road vehicles. Zubov et al [1] apply a more-refined three-state single-track model with tire parameters to realize a controller stabilizing the all-wheel drive (AWD) car around an equilibrium state in the Speed Dreams Simulator.…”

Section: A Reinforcement Learning Algorithmsmentioning

confidence: 99%

“…1(a). In order to make a quick turn through sharp corners, skilled drivers execute drifts by deliberately inducing deep saturation of the rear tires by oversteering [1] or using the throttle [2], thereby destabilising the vehicle. They then stabilise the vehicle as it begins to spin by controlling it under a high sideslip configuration (up to 40 degrees [3]).…”

Section: Introductionmentioning

confidence: 99%

“…Therefore, by studying drift behaviors, we can design controllers which fully exploit vehicle *The first two authors contributed equally to this work. 1 P. Cai, X. Mei, Y. Sun and M. Liu are with The Hong Kong University of Science and Technology (email: pcaiaa, xmeiab, eeyxsun, eelium@ust.hk).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

High-Speed Autonomous Drifting With Deep Reinforcement Learning

Cai

Mei

Tai

et al. 2020

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

Drifting is a complicated task for autonomous vehicle control. Most traditional methods in this area are based on motion equations derived by the understanding of vehicle dynamics, which is difficult to be modeled precisely. We propose a robust drift controller without explicit motion equations, which is based on the latest model-free deep reinforcement learning algorithm soft actor-critic. The drift control problem is formulated as a trajectory following task, where the errorbased state and reward are designed. After being trained on tracks with different levels of difficulty, our controller is capable of making the vehicle drift through various sharp corners quickly and stably in the unseen map. The proposed controller is further shown to have excellent generalization ability, which can directly handle unseen vehicle types with different physical properties, such as mass, tire friction, etc.Index Terms-Deep reinforcement learning, deep learning in robotics and automation, racing car, motion control, field robots.• We design a closed-loop controller based on model-free deep RL to control front-wheel drive (FWD) vehicles to drive at high speed (80-128 km/h), and to drift through sharp corners quickly and stably following a reference trajectory, as shown in Fig. 2.

show abstract

Section: A Reinforcement Learning Algorithmsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

High-Speed Autonomous Drifting With Deep Reinforcement Learning

Cai

Mei

Tai

et al. 2020

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

show abstract

“…Other works found in the literature address the issue of drifting too, however, they tend to limit the scope of their research to simulation environments [ 16 , 17 ] or require additional parameters that cannot easily be estimated with an IMU [ 18 ]. Conversely, the drift recognition in this work is designed to operate by performing consistency checks between two estimated state variables: the lateral acceleration and the sideslip angle.…”

Section: Introductionmentioning

confidence: 99%

High Precision Outdoor and Indoor Reference State Estimation for Testing Autonomous Vehicles

Morales

Dauth

Huber³

et al. 2021

Sensors

View full text Add to dashboard Cite

A current trend in automotive research is autonomous driving. For the proper testing and validation of automated driving functions a reference vehicle state is required. Global Navigation Satellite Systems (GNSS) are useful in the automation of the vehicles because of their practicality and accuracy. However, there are situations where the satellite signal is absent or unusable. This research work presents a methodology that addresses those situations, thus largely reducing the dependency of Inertial Navigation Systems (INSs) on the SatNav. The proposed methodology includes (1) a standstill recognition based on machine learning, (2) a detailed mathematical description of the horizontation of inertial measurements, (3) sensor fusion by means of statistical filtering, (4) an outlier detection for correction data, (5) a drift detector, and (6) a novel LiDAR-based Positioning Method (LbPM) for indoor navigation. The robustness and accuracy of the methodology are validated with a state-of-the-art INS with Real-Time Kinematic (RTK) correction data. The results obtained show a great improvement in the accuracy of vehicle state estimation under adverse driving conditions, such as when the correction data is corrupted, when there are extended periods with no correction data and in the case of drifting. The proposed LbPM method achieves an accuracy closely resembling that of a system with RTK.

show abstract

“…If we also consider recent advances in the field of Artificial Intelligence (AI) we have all the instruments to potentially reduce human error in transportation systems by building self-driving vehicles. They are capable of autonomously steering, navigating, vehicle agile ma-neuvering, making decisions, foreseeing potential accidents and acting better than human drivers in some critical situations [14,31]. Having such machines at our disposal could result in numerous benefits, including, but not limited to, fewer accidents, reduced traffic congestions, and enablement for so-called Mobility-as-a-Service (MaaS) [16].…”

Section: Introductionmentioning

confidence: 99%

An Architecture for Distributed Ledger-Based M2M Auditing for Electric Autonomous Vehicles

Strugar

Hussain

Mazzara

et al. 2019

Advances in Intelligent Systems and Computing

Self Cite

View full text Add to dashboard Cite

Electric Autonomous Vehicles (EAVs) promise to be an effective way to solve transportation issues such as accidents, emissions and congestion, and aim at establishing the foundation of Machine-to-Machine (M2M) economy. For this to be possible, the market should be able to offer appropriate charging services without involving humans. The state-of-the-art mechanisms of charging and billing do not meet this requirement, and often impose service fees for value transactions that may also endanger users and their location privacy. This paper aims at filling this gap and envisions a new charging architecture and a billing framework for EAV which would enable M2M transactions via the use of Distributed Ledger Technology (DLT).

show abstract

Autonomous Drifting Control in 3D Car Racing Simulator

Cited by 11 publications

References 20 publications

High-Speed Autonomous Drifting With Deep Reinforcement Learning

High-Speed Autonomous Drifting With Deep Reinforcement Learning

High Precision Outdoor and Indoor Reference State Estimation for Testing Autonomous Vehicles

An Architecture for Distributed Ledger-Based M2M Auditing for Electric Autonomous Vehicles

Contact Info

Product

Resources

About