A system includes a performance optimization module of an autonomous vehicle configured to: (1) receive a first and second set of real-time parameter values of the autonomous vehicle; (2) identify instability of the autonomous vehicle in response to detecting one or more errors between a control command given by a controller unit to the autonomous vehicle and an execution of the control command by the autonomous vehicle based on the first set of real-time parameter values and the second set of real-time parameter values; (3) generate additional information associated with the autonomous vehicle and an environment in which the autonomous vehicle is driving based on the one or more errors; generate a corrective course of action for reducing a duration needed to drive a given route by the autonomous vehicle; and feed back the additional information and the corrective course of action to the controller unit for execution.

An racing coach device can comprise an infrared (IR) sensor, a processing element, and a display. The IR sensor can be configured to measure a tire temperature of a vehicle. The processing element wirelessly coupled to the IR sensor can be configured to generate racing metrics based on the tire temperature. The display coupled to the processing element can be configured to convey the racing metrics to a user of the vehicle.

In general, the subject matter described in this disclosure can be embodied in methods, systems, and program products for performing vehicle control. A computing system determines a difference between a recent rate of change and a historical rate of change of a rotating vehicle shaft of a vehicle during a vehicle race. The computing system determines that the difference between the recent rate of change of the rotating vehicle shaft and the historical rate of change of the rotating vehicle shaft satisfies a criteria for limiting vehicle power, wherein the computing system changes the criteria for limiting vehicle power during the vehicle race. The computing system sends a signal for receipt by a vehicle component of the vehicle, to cause the vehicle component to limit rotation of the rotating vehicle shaft.

Systems and methods are provided for determining vehicle configurations. The system can receive simulation data or actual driving data of a driving track corresponding to a driver and associate the simulation data or actual driving data with one or more driving parameters. A driver style can be determined based on the one or more driving parameters. A vehicle configuration can be determined for a vehicle of the driver based on the determined driver style. The system can display one or more vehicle settings associated with the vehicle configuration on a user interface.

An racing coach device can comprise an infrared (IR) sensor, a processing element, and a display. The IR sensor can be configured to measure a tire temperature of a vehicle. The processing element wirelessly coupled to the IR sensor can be configured to generate racing metrics based on the tire temperature. The display coupled to the processing element can be configured to convey the racing metrics to a user of the vehicle.

A method for an online, task-aware opponent modeling in autonomous racing is described. The method includes concurrently training an opponent-aware policy and an opponent-aware encoder using reinforcement learning. The method also includes calculating, by the opponent-aware encoder, opponent encoding information according to prior opponent positions. The method further includes updating learning parameters of the opponent-aware policy using the opponent encoding information from the opponent-aware encoder to predict actions. The method also includes updating a posterior network according to an auxiliary mutual information loss between the actions predicted by the opponent-aware policy and the opponent encoding information from the opponent-aware encoder.

Systems and methods for determining a maximum phase recovery envelope are disclosed herein. In one example, a system includes a processor and a memory having a vehicle control module. The vehicle control module includes instructions that, when executed by the processor, cause the processor to determine a critical point on a phase plane indicating a maximum defined recovery point a vehicle can recover from, perform forward and reverse simulations from the critical point to define outermost contours of a maximum phase recovery envelope using parameters and state of the vehicle, and cause the vehicle to operate within the maximum phase recovery envelope.