Efficient Parallelized Simulation of Cyber-Physical Systems

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F24%3A00376366" target="_blank" >RIV/68407700:21730/24:00376366 - isvavai.cz</a>

Výsledek na webu

<a href="https://openreview.net/pdf?id=VzKXbCzNoU" target="_blank" >https://openreview.net/pdf?id=VzKXbCzNoU</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Efficient Parallelized Simulation of Cyber-Physical Systems

Popis výsledku v původním jazyce

Advancements in accelerated physics simulations have greatly reduced training times for reinforcement learning policies, yet the conventional step-by-step agent-simulator interac tion undermines simulation accuracy. In the real world, interactions are asynchronous, with sensing, acting and processing happening simultaneously. Failing to capture this widens the sim2real gap and results in suboptimal real-world performance. In this paper, we address the challenges of simulating realistic asynchronicity and delays within parallelized simula tions, crucial to bridging the sim2real gap in complex cyber-physical systems. Our approach efficiently parallelizes cyber-physical system simulations on accelerator hardware, including physics, sensors, actuators, processing components and their asynchronous interactions. We extend existing accelerated physics simulations with latency simulation capabilities by con structing a `supergraph’ that encodes all data dependencies across parallelized simulation steps, ensuring accurate simulation. By finding the smallest supergraph, we minimize re dundant computation. We validate our approach on two real-world systems and perform an extensive ablation, demonstrating superior performance compared to baseline methods.

Název v anglickém jazyce

Efficient Parallelized Simulation of Cyber-Physical Systems

Popis výsledku anglicky

Advancements in accelerated physics simulations have greatly reduced training times for reinforcement learning policies, yet the conventional step-by-step agent-simulator interac tion undermines simulation accuracy. In the real world, interactions are asynchronous, with sensing, acting and processing happening simultaneously. Failing to capture this widens the sim2real gap and results in suboptimal real-world performance. In this paper, we address the challenges of simulating realistic asynchronicity and delays within parallelized simula tions, crucial to bridging the sim2real gap in complex cyber-physical systems. Our approach efficiently parallelizes cyber-physical system simulations on accelerator hardware, including physics, sensors, actuators, processing components and their asynchronous interactions. We extend existing accelerated physics simulations with latency simulation capabilities by con structing a `supergraph’ that encodes all data dependencies across parallelized simulation steps, ensuring accurate simulation. By finding the smallest supergraph, we minimize re dundant computation. We validate our approach on two real-world systems and perform an extensive ablation, demonstrating superior performance compared to baseline methods.

Druh

J_ost - Ostatní články v recenzovaných periodicích

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Transactions on Machine Learning Research

ISSN

2835-8856

e-ISSN

2835-8856

Svazek periodika

2024

Číslo periodika v rámci svazku

May

Stát vydavatele periodika

DE - Spolková republika Německo

Počet stran výsledku

18

Strana od-do

—

Kód UT WoS článku

—

EID výsledku v databázi Scopus

2-s2.0-85219527413