Digital Supercluster Project Announced
Mon Oct 28 202415 viewsWe are extremely pleased to annouce the formation of the Road Ahead Simulation Consortium (TRASC) in initial partnership with Canada's DIGITAL Supercluster and the Embodied AI Foundation (the foundation behind the CARLA simulation framework).
Large-scale simulation is the backbone of autonomous vehicle (AV) and advanced driver assistance system (ADAS) development, where it’s used to train and validate AI vehicle systems prior to real-world testing. The realism of these simulations is critical, as differences between the simulated driving environment and the real world can introduce unacceptable performance and safety errors, requiring far longer and more expensive development cycles. This “sim-to-real gap” is a major hurdle for AV development, particularly for interactions between the AI vehicle and other simulated agents, such as other drivers, pedestrians, and bikes. Human behavior represents a staggering amount of variation, and the inability to adequately represent these nuances in simulation prevents autonomous or semi-autonomous vehicles from handling diverse situations on the road.
In response to the pressing need to narrow the sim-to-real gap, The project aims to establish a consortium to accelerate the technological and commercial development and adoption of behavioral simulation for AV/ADAS simulation and related fields. The project is led by Inverted AI, a Vancouver-based technology company that develops advanced human behavioral models, with collaboration from Embodied AI Foundation (CARLA), the developer of one of the most widely used open-source AV simulator platforms in the world. This consortium intends to unite innovators from across the sector to develop a comprehensive product and partner ecosystem, enhancing the accessibility, interoperability, and realism of simulation technology, while creating and capturing new value in the global market.
Read the full DIGITAL announcement here.
And stay tuned as we grow the consortium. Organizations interested in joining our consortium are invited to contact info@inverted.ai.