2019 · 26 citations · 8 references
ComputingAutomotive EngineeringAutonomous SystemsArtificial IntelligenceAutonomous VehiclesMachine LearningVehicle ControlVehicle Control SystemsAutonomous Vehicle ControlSimulated Environments
Autonomous driving is one of the newly emerging feats in artificial intelligence (AI). The challenge in developing autonomous cars is to design controllers that can steer a vehicle in the right direction with enough speed. A good controller activates a set of multiple actuators simultaneously. The output of the controller is a function of the sensory inputs. Nowadays, controllers are mostly developed by connecting a car simulator with a machine learning (ML) algorithm. The simulator provides a pragmatic environment for simulated cars. The ML algorithm, on the other hand, does the job of an expert human controller designer; it designs the controllers on behalf of the latter. In our case, we use a famous car racing simulator called TORCS (The Open Racing Car Simulator). This paper proposes a new controller for TORCS that helps cars win races with grace. We also propose a novel strategy to design smart controllers using ML algorithms. Our controller is called FUSCD (Future Smart Car Driver).
8
TORCS, The Open Racing Car Simulator
Eric Espié, Christophe Guionneau, Bernhard Wymann et al. · Infoscience (Ecole Polytechnique Fédérale de Lausanne) · 2005 · 295 citations · Full text