November 30, 2022
Duality Robotics, working with Amazon Web Services (AWS), unveiled an exciting new visualization of high-fidelity, city-scale simulation. Showcased at AWS re:Invent 2022, the “Rush Hour Emergency and Response Simulation in Smart Cities” demo illustrates what Falcon, Duality’s digital twin simulator, can achieve when integrated with AWS SimSpace Weaver, AWS’s newly debuted fully managed compute service that helps customers build, operate, and oversee large-scale spatial simulations.
AWS SimSpace Weaver allows customers to run a simulation that has more than a million entities interacting in real time, and create sophisticated environments, while significantly reducing the time-to-simulation deployment. There are no upfront commitments or fees to use AWS SimSpace Weaver, and customers “only pay for the amount of compute used.”
In a demo, a semi-autonomous, teleoperated Emergency Medical Services (EMS) unit navigates a metropolis with over one million simulated vehicle and pedestrian agents, while coordinating its path with traffic information and assisting ground units. Conventionally, this type of resource-intensive simulation would be subject to the limitations of available local hardware. But with AWS SimScape Weaver integration, Falcon’s full capabilities can run at an increasingly larger scale while the available computational resources scale up with the spatial simulation’s needs on AWS infrastructure, AWS said.
AWS said SimSpace Weaver handles provisioning Amazon Elastic Compute Cloud (Amazon EC2) instances as well as managing the network and compute infrastructure. By integrating Falcon’s simulation features with AWS SimSpace Weaver and by leveraging Epic Games’ Unreal Engine 5 City Sample project, Duality’s team created a sprawling city-scale simulation in just three months. The simulation runs via a multitude of concurrent Falcon instances while AWS SimSpace Weaver tracks and manages the state information of each simulated entity so the spatial simulation functions as a unified, seamless whole.
“Our demo offers a successful proof of concept of how such a simulation can be implemented,” said Apurva Shah, CEO of Duality Robotics. “The EMS use case demonstrates high fidelity physics, photoreal rendering, virtual sensors, and real-time performance with over a million concurrent agents.” Because Falcon employs Epic Games’ Unreal Engine to power realistic 3D environments and visualize data with a high level of accuracy, it also leverages vast collections of Unreal assets – a benefit for efficient simulation deployment. “Falcon with AWS SimSpace Weaver can now take digital twins of environments and systems developed for the Unreal ecosystem and make them instantly available for massive scale simulation,” said Shah.
To learn more about the sim, visit the Duality website here.