DARPA is soliciting proposals for promising new technologies to be investigated for its Robotic Autonomy in Complex Environments with Resiliency – Simulation (RACER-Sim) project, which seeks to develop innovative ways to reduce the cost of autonomy development for offroad UGVs (unmanned ground vehicles) by bridging the gap from simulation to the real world.
Developing simulations for military off-road robotics is especially difficult, as computers need to recreate a challenging three-dimensional environment that includes complex surfaces, compliant soils and vegetation, and hundreds of obstacle classes. Simulation software must take into account lower fidelity or limited mapping data, unique vehicle-surface interactions, continuous motion planning, and no defined road networks or driving rules. The modelling of high speed off-road performance of sensors and modalities, sensor-to-terrain representations, autonomous platforms, and autonomous control represents a significant software and processing challenge.
Over a four-year time period, RACER-Sim will investigate technologies that are applicable to the off-road environment, including algorithm development, simulation element technologies, and simulator content generation.
Dr. Stuart Young, RACER program manager, commented: “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.”
