City-Scale Simulation Becomes Reality
At AWS re:Invent, Amazon announced the release of SimSpace Weaver, its exciting new computing service that can power real-time spatial simulations on a city scale. The service will allow developers to simulate real-world events at scale in real time to help planners better prepare for scenarios that would have been too rare, dangerous or expensive to create.
SimSpace Weaver removes the need to balance between scale and fidelity. In the past, to run a larger scale, simulation engineers would need to provision more resources. Obviously, this came at a cost and a trade-off between how dynamic the simulation could be and the scale of the simulation had to be made. Now, engineers can run simulations on a city scale with high fidelity without those overheads.
The digital twin simulator Falcon of Duality Robotics has already collaborated with AWS to create some incredible capability demonstrations. Falcon have said:
We’re thrilled by the result of our collaboration with AWS and the potential of AWS SimSpace Weaver to enable Falcon’s capabilities at an increasingly larger scale. When paired with high-quality digital twins, the Falcon-Unreal-AWS SimSpace Weaver integration opens a new level of possibility in leveraging the enterprise metaverse for solving complex real-world problems within realistic budgets and schedules for our customers. At Duality, our singular focus is on helping our customers leverage digital twins to solve high impact problems, and this collaboration represents a significant step in that direction.
Rush Hour Emergency Response in Smart Cities Simulation
For the demo, Falcon based the City Sample environment on The Matrix Awakens: An Unreal Engine 5 Experience. The environment is an interactive open world with tens of thousands of buildings, MassAI vehicles, and MetaHuman characters that mimic realistic behaviors.
Duality’s team designed and implemented some significant modifications in order to adapt the City Sample to the demo. The modifications include implementing traffic-aware route optimization, creating controls and driving rules for the semi-autonomous ambulance, creating a traffic officer for rerouting vehicles, adding sensors for external data analysis, designing a new traffic light dynamic, and modifying visual assets.
Marcia Villalba gave more details as to how the system works on the AWS blog. She explained that SimSpace Weaver works by using a data replication system that handles memory and network management for partitions that can be in different EC2 instances.
She says that another important element of SimSpace Weaver is its scheduler. It can keep all distributed partitions synchronized as if it was one machine. This allows SimSpace Weaver to weave instances together across multiple instances to create a city scale simulation.
Villalba stresses that SimSpace Weaver is not a simulator, it only provides the infrastructure to create them. Users can build their own simulations by using the AWS SimSpace Weaver C++ SDK together with out-of-the-box plugins that can integrate with Unreal Engine 5 or Unity.