Published on Mon Nov 09 2020

A Learning-Based Tune-Free Control Framework for Large Scale Autonomous Driving System Deployment

Yu Wang, Shu Jiang, Weiman Lin, Yu Cao, Longtao Lin, Jiangtao Hu, Jinghao Miao, Qi Luo

This paper presents the design of a tune-free (human-out-of-the-loop) control framework. The framework consists of three machine-learning-based procedures. The paper shows an improvement in control performance.

0
0
0
Abstract

This paper presents the design of a tune-free (human-out-of-the-loop parameter tuning) control framework, aiming at accelerating large scale autonomous driving system deployed on various vehicles and driving environments. The framework consists of three machine-learning-based procedures, which jointly automate the control parameter tuning for autonomous driving, including: a learning-based dynamic modeling procedure, to enable the control-in-the-loop simulation with highly accurate vehicle dynamics for parameter tuning; a learning-based open-loop mapping procedure, to solve the feedforward control parameters tuning; and more significantly, a Bayesian-optimization-based closed-loop parameter tuning procedure, to automatically tune feedback control (PID, LQR, MRAC, MPC, etc.) parameters in simulation environment. The paper shows an improvement in control performance with a significant increase in parameter tuning efficiency, in both simulation and road tests. This framework has been validated on different vehicles in US and China.

Wed Oct 02 2019
Machine Learning
Longitudinal Motion Planning for Autonomous Vehicles and Its Impact on Congestion: A Survey
This paper reviews machine learning methods for the motion planning of autonomous vehicles (AVs) with exclusive focus on the longitudinal behaviors and their impact on traffic congestion. The emerging technologies adopted by leading AV giants like Waymo and Tesla are highlighted.
0
0
0
Sat May 23 2020
Machine Learning
Learning from Naturalistic Driving Data for Human-like Autonomous Highway Driving
An autonomous vehicle should be smart and predictable traffic participant. To achieve this goal, parameters of the motion planning module should be carefully tuned. A method of learning cost parameters of a motion planner from naturalistic driving data is proposed.
0
0
0
Wed Jun 23 2021
Machine Learning
Uncertainty-Aware Model-Based Reinforcement Learning with Application to Autonomous Driving
In this paper we propose a novel uncertainty-aware model-based RL (UA-MBRL) framework. We then implement and validate it in autonomous driving under various task scenarios. The developed algorithms are then implemented in end-to-end autonomous vehicle control tasks.
0
0
0
Thu Aug 13 2020
Machine Learning
Meta Learning MPC using Finite-Dimensional Gaussian Process Approximations
Meta-learning is a powerful tool that enables efficient learning across a finite set of related tasks, easing adaptation to new unseen tasks. The dynamics is modeled via Gaussian process regression and can be approximately reformulated as a linear combination of kernel eigenfunctions.
0
0
0
Sun Jul 09 2017
Artificial Intelligence
A Fast Integrated Planning and Control Framework for Autonomous Driving via Imitation Learning
For safe and efficient planning and control in autonomous driving, we need a policy which can achieve desirable driving quality in long-term horizon. Optimization-based approaches, such as MPC, can provide such optimal policies, but their complexity is generally unacceptable for real-time implementation. We propose
0
0
0
Thu Mar 21 2019
Machine Learning
End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Tasks
Reinforcement Learning (RL) algorithms have found limited success beyondsimulated applications. Real world systems would realistically fail or break before an optimal controller can be learned. Our novel controller synthesis algorithm, RL-CBF, guarantees safety with high probability during the learning process.
0
0
0