Abstract
Reporters obtained the following quote from the background information supplied by the inventors: “Conventional methods that focus on driver modeling or predict ion by differentiable simulation often use rendered grids (with map and agents) as discrete input or rendered grids with rotated focus area (region of interest) . Such solutions are described, for example, in Scibior et al., “Imagining The R oad Ahead: Multi-Agent Trajectory Prediction via Differentiable Simulation”, arX iv: 2104.11212v1 or in Suo et al., “TrafficSim: Learning to Simulate Realistic M ulti-Agent Behaviors”, CVPR2021, arXiv: 2101.06557v1.