New Technique Controls Autonomous Vehicles in Extreme Conditions

Researchers from Georgia Institute of Technology have devised a new way to help keep a driverless vehicle under control as it maneuvers at the edge of its handling limits. The approach could help make future autonomous cars safer under hazardous road conditions. The researchers assessed the new technology by racing, sliding, and jumping one-fifth-scale, fully autonomous auto-rally cars at the equivalent of 90 mph. The technique uses advanced algorithms and onboard computing, combined with installed sensing devices, to increase vehicular stability while maintaining performance. Traditional robotic-vehicle techniques use the same control approach whether a vehicle is driving normally or at the edge of roadway adhesion. The Georgia Tech method – known as model predictive path integral control (MPPI) – was developed specifically to address the non-linear dynamics involved in controlling a vehicle near its friction limits.