Real-Time Implementation of Randomized Model Predictive Control for Autonomous Driving

Model predictive control (MPC) using randomized optimization is expected to solve different control problems. However, it still faces various challenges for real-world applications. This paper attempts to solve those challenges and demonstrates a successful implementation of randomized MPC on the au...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on intelligent vehicles Vol. 7; no. 1; pp. 11 - 20
Main Authors: Muraleedharan, Arun, Okuda, Hiroyuki, Suzuki, Tatsuya
Format: Journal Article
Language:English
Published: Piscataway IEEE 01.03.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Acceleration
Automobiles
Autonomous vehicles
Collision avoidance
Computational modeling
Frequency-domain analysis
graphics processing unit (GPU)
Graphics processing units
model predictive control
Optimization
Predictive control
Radio control
Real-time systems
sampling based optimization
Smoothness
Steering
Vehicle dynamics
ISSN:2379-8858, 2379-8904
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Model predictive control (MPC) using randomized optimization is expected to solve different control problems. However, it still faces various challenges for real-world applications. This paper attempts to solve those challenges and demonstrates a successful implementation of randomized MPC on the autonomous driving using a radio-controlled (RC) car. First of all, a sample generation technique in the frequency domain is discussed. This prevents undesirable randomness which affect the smoothness of the steering operation. Second, the proposed randomized MPC is implemented on a Graphics Processing Unit (GPU). The expected GPU acceleration in calculation speed at various problem sizes is also presented. The results show the improved control performance and computational speed that was not achievable using CPU based implementation. Besides, the selection of parameters for randomized MPC is discussed. The usefulness of the proposed scheme is demonstrated by both simulation and experiments. In the experiments, a 1/10 model RC car is used for collision avoidance task by autonomous driving.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2379-8858
2379-8904
DOI:10.1109/TIV.2021.3062730