Autonomous systems, including self-driving cars, unmanned aircraft, and humanoid robots, learn from modelling and simulation. However, the training process can take months to years, and have trouble account for all the uncertainty found in the real world. In the world of robotics, this is known as the simulation-to-real gap.
To improve this gap, the Defense Advanced Research Projects Agency (DARPA) has implemented a programme to develop rapid autonomy transfer techniques. Called Transfer Learning from Imprecise and Abstract Models to Autonomous Technologies, or TIAMAT, it aims to enable “same-day autonomy”, so that it can adapt to the quick changes in dynamic environments.
DARPA has selected Indy Autonomous Challenge (IAC) as an official test and evaluation platform for the TIAMAT programme.
“We were inspired to create the Indy Autonomous Challenge by the successes of the DARPA Grand Challenges which were held 20 years ago and gave rise to the modern autonomous vehicle industry,” said Paul Mitchell, CEO of IAC,
“It is an honour to partner with DARPA to accelerate the development and training of Physical AI using our first-of-its-kind robotics platform of the world’s fastest autonomous racecars.”
All agree that AI will revolutionise autonomy in the physical world, but testing this in the real world is expensive and can be risky.
Over the next 3 years, IAC will work with DARPA to build a SIM-to-SIM and SIM-to-REAL test and evaluation platform that will dramatically improve the speed and efficiency of AI driver training.
The platform will allow rapid iterative testing of novel AI models and piece together those that work best in various high-speed and edge-case environments.
Other TIAMAT performers, as well as current IAC university teams, will be able to test various AI models in low and high-fidelity simulation, and those proven to work will graduate to real testing on a racetrack in IAC AV-24 racecars. This AI training platform will not only benefit high-speed ground vehicles but could be applied across other autonomy domains such as air, sea, and space.
IAC is a non-profit corporation based in Indianapolis, USA, that organises racing competitions among university-affiliated teams from around the world. Teams programme AI drivers to pilot fully autonomous racecars and compete in a series of h events at iconic tracks.