DARPA seeks proposals to advance RACER-Sim project

18 January 2021 (Last Updated January 18th, 2021 16:31)

The Defense Advanced Research Projects Agency (DARPA) in the US has sought proposals that will help in advancing with the Robotic Autonomy in Complex Environments with Resiliency - Simulation (RACER-Sim) project.

The Defense Advanced Research Projects Agency (DARPA) in the US has sought proposals that will help in advancing with the Robotic Autonomy in Complex Environments with Resiliency – Simulation (RACER-Sim) project.

The agency invited proposals for new computer models as it aims to develop simulation technologies for robotic vehicles in militarily-relevant settings.

Particularly, the RACER-Sim project is looking for innovations that will help in bridging the gap from simulation to the real world, as well as trim the cost of off-road autonomy development.

In the last decade, the use of simulation for developing field robotics has surged significantly.

For the military off-road environment, the computers models re-create three-dimensional surfaces, compliant soils and vegetation and hundreds of obstacle classes.

Additionally, the solutions consider lower fidelity or limited mapping data, unique platform-surface interactions and continuous motion planning among others while designing the environment.

The available models are usually unable to meet all the challenges of the real-world.

RACER program manager Dr Stuart Young said: “Because these challenges haven’t been effectively met, the practical use of current virtual models to advance off-road field robotics capabilities is limited and doesn’t yet allow a demonstrable simulation-to-real world capability.

“The large reality gap of current software models and complexities of their use discourage developers and prevent them from leveraging the full benefits of simulation.”

The RACER-Sim project will assess technologies that can be applied to the off-road environment in the areas of algorithm development, simulation element technologies and simulator content generation over a four-year timeline.