Header

UZH-Logo

Maintenance Infos

RPGD: A Small-Batch Parallel Gradient Descent Optimizer with Explorative Resampling for Nonlinear Model Predictive Control


Heetmeyer, Frederik; Paluch, Marcin; Bolliger, Diego; Bolli, Florian; Deng, Xiang; Filicicchia, Ennio; Delbruck, Tobi (2023). RPGD: A Small-Batch Parallel Gradient Descent Optimizer with Explorative Resampling for Nonlinear Model Predictive Control. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), London, United Kingdom, 29 May 2023 - 2 June 2023, Institute of Electrical and Electronics Engineers.

Abstract

Nonlinear model predictive control often involves nonconvex optimization for which real-time control systems require fast and numerically stable solutions. This work proposes RPGD, a Resampling Parallel Gradient Descent optimizer designed to exploit small-batch parallelism of modern hardware like neural accelerators or multithreaded microcontrollers. After initialization, it continuously maintains a small population of good control trajectory solution candidates and improves them using gradient information, followed by selection of elite candidates and resampling of the others. In simulation on a cartpole, the OpenAI Gym mountain car, a Dubins car with obstacles, and a high input dimensional 2D arm, it produces similar or lower MPC costs than benchmark cross-entropy and path integral methods. On a physical cartpole, it performs swing-up and cart target following of the pole, using either a differential equation or multilayer perceptron as dynamics model. RPGD drives an F1TENTH simulated race car at near-optimal lap times and a real F1TENTH car in laps around a cluttered room. We study alterations of RPGD's building blocks to justify its composition. RPGD compute time in Python with TensorFlow optimization running on CPU is 2 to 4 times slower than the FORCESPRO commercial embedded solver.

Abstract

Nonlinear model predictive control often involves nonconvex optimization for which real-time control systems require fast and numerically stable solutions. This work proposes RPGD, a Resampling Parallel Gradient Descent optimizer designed to exploit small-batch parallelism of modern hardware like neural accelerators or multithreaded microcontrollers. After initialization, it continuously maintains a small population of good control trajectory solution candidates and improves them using gradient information, followed by selection of elite candidates and resampling of the others. In simulation on a cartpole, the OpenAI Gym mountain car, a Dubins car with obstacles, and a high input dimensional 2D arm, it produces similar or lower MPC costs than benchmark cross-entropy and path integral methods. On a physical cartpole, it performs swing-up and cart target following of the pole, using either a differential equation or multilayer perceptron as dynamics model. RPGD drives an F1TENTH simulated race car at near-optimal lap times and a real F1TENTH car in laps around a cluttered room. We study alterations of RPGD's building blocks to justify its composition. RPGD compute time in Python with TensorFlow optimization running on CPU is 2 to 4 times slower than the FORCESPRO commercial embedded solver.

Statistics

Citations

Dimensions.ai Metrics

Altmetrics

Downloads

9 downloads since deposited on 31 Jan 2024
9 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Paper), refereed, original work
Communities & Collections:07 Faculty of Science > Institute of Neuroinformatics
Dewey Decimal Classification:570 Life sciences; biology
Scopus Subject Areas:Physical Sciences > Software
Physical Sciences > Control and Systems Engineering
Physical Sciences > Electrical and Electronic Engineering
Physical Sciences > Artificial Intelligence
Language:English
Event End Date:2 June 2023
Deposited On:31 Jan 2024 12:46
Last Modified:01 Feb 2024 22:07
Publisher:Institute of Electrical and Electronics Engineers
Series Name:IEEE International Conference on Robotics and Automation. Proceedings
ISSN:1050-4729
OA Status:Green
Publisher DOI:https://doi.org/10.1109/icra48891.2023.10161233
  • Content: Submitted Version
  • Language: English