Autonomous vehicles on the edge: A survey on autonomous vehicle racing

J Betz, H Zheng, A Liniger, U Rosolia… - IEEE Open Journal …, 2022 - ieeexplore.ieee.org
The rising popularity of self-driving cars has led to the emergence of a new research field in
recent years: Autonomous racing. Researchers are develo** software and hardware for …

Cautious nmpc with gaussian process dynamics for autonomous miniature race cars

L Hewing, A Liniger… - 2018 European Control …, 2018 - ieeexplore.ieee.org
This paper presents an adaptive high performance control method for autonomous miniature
race cars. Racing dynamics are notoriously hard to model from first principles, which is …

Barrier-certified adaptive reinforcement learning with applications to brushbot navigation

M Ohnishi, L Wang, G Notomista… - IEEE Transactions on …, 2019 - ieeexplore.ieee.org
This paper presents a safe learning framework that employs an adaptive model learning
algorithm together with barrier certificates for systems with possibly nonstationary agent …

Scalable deep kernel Gaussian process for vehicle dynamics in autonomous racing

J Ning, M Behl - Conference on Robot Learning, 2023 - proceedings.mlr.press
Autonomous racing presents a challenging environment for testing the limits of autonomous
vehicle technology. Accurately modeling the vehicle dynamics (with all forces and tires) is …

[PDF][PDF] Safe policy search using Gaussian process models

K Polymenakos, A Abate… - Proceedings of the 18th …, 2019 - oxford-man.ox.ac.uk
We propose a method to optimise the parameters of a policy which will be used to safely
perform a given task in a data-efficient manner. We train a Gaussian process model to …

Safe exploration by solving early terminated mdp

H Sun, Z Xu, M Fang, Z Peng, J Guo, B Dai… - ar** to reduce the impact of model error in receding horizon control
CD McKinnon, AP Schoellig - 2020 IEEE International …, 2020 - ieeexplore.ieee.org
This paper presents a method to enable a robot using stochastic Model Predictive Control
(MPC) to achieve high performance on a repetitive path-following task. In particular, we …