Abstract: Original sensor data is received from one or more sensors of a vehicle. Free space around the vehicle is identified according to the sensor data, such as by identifying regions where data points have a height below a threshold. A location for an object model is selected from the free space. A plane is fitted to sensor data around the location and the object model is oriented according to an orientation of the plane. Sensing of the object model by a sensor of the vehicle is simulated to obtain simulated data, which is then added to the original sensor data. Sensor data corresponding to objects that would have been obscured by the object model is removed from the original sensor data. Augmented sensor data may be used to validate a control algorithm or train a machine learning model.

Abstract: A computer includes a processor and a memory storing instructions executable by the processor to actuate a steering system of a vehicle to perform a lane-keeping operation, cease the lane-keeping operation upon receiving a takeover request, determine that the takeover request has occurred upon detecting that a torque applied to a steering wheel exceeds a torque threshold, determine that the vehicle is traveling over a road disturbance or will travel over a road disturbance within a time threshold based on receiving map data indicating a location of the road disturbance, and increase the torque threshold upon determining that the vehicle is traveling over the road disturbance or will travel over the road disturbance within the time threshold. The lane-keeping operation includes steering the vehicle without operator input.

Abstract: Original sensor data is received from one or more sensors of a vehicle. Free space around the vehicle is identified according to the sensor data, such as by identifying regions where data points have a height below a threshold. A location for an object model is selected from the free space. A plane is fitted to sensor data around the location and the object model is oriented according to an orientation of the plane. Sensing of the object model by a sensor of the vehicle is simulated to obtain simulated data, which is then added to the original sensor data. Sensor data corresponding to objects that would have been obscured by the object model is removed from the original sensor data. Augmented sensor data may be used to validate a control algorithm or train a machine learning model.

Abstract: From detecting a marker detected in an image, a physical object on which the marker is provided can be identified. Based on a determining a location of the marker in the physical world, a location and an orientation of the physical object can be determined.

Abstract: From detecting a marker detected in an image, a physical object on which the marker is provided can be identified. Based on a determining a location of the marker in the physical world, a location and an orientation of the physical object can be determined.

Abstract: Example lane detection systems and methods are described. In one implementation, a method received an image from-facing vehicle camera and applies a geometric transformation to the image to create a birds-eye view of the image. The method analyzes the birds-eye view of the image using a neural network, which was previously trained using side-facing vehicl camera images, to determine a lane position associated with the birds-eye view of the image.

Abstract: Original sensor data is received from one or more sensors of a vehicle. Free space around the vehicle is identified according to the sensor data, such as by identifying regions where data points have a height below a threshold. A location for an object model is selected from the free space. A plane is fitted to sensor data around the location and the object model is oriented according to an orientation of the plane. Sensing of the object model by a sensor of the vehicle is simulated to obtain simulated data, which is then added to the original sensor data. Sensor data corresponding to objects that would have been obscured by the object model is removed from the original sensor data. Augmented sensor data may be used to validate a control algorithm or train a machine learning model.

Abstract: Original sensor data is received from one or more sensors of a vehicle. Free space around the vehicle is identified according to the sensor data, such as by identifying regions where data points have a height below a threshold. A location for an object model is selected from the free space. A plane is fitted to sensor data around the location and the object model is oriented according to an orientation of the plane. Sensing of the object model by a sensor of the vehicle is simulated to obtain simulated data, which is then added to the original sensor data. Sensor data corresponding to objects that would have been obscured by the object model is removed from the original sensor data. Augmented sensor data may be used to validate a control algorithm or train a machine learning model.

Abstract: A method for determining a position of a vehicle in a lane includes receiving perception information from a first camera positioned on a first side of a vehicle and a second camera positioned on a second side of the vehicle. The method includes determining, using one or more neural networks, a position of the vehicle with respect to lane markings on the first side and the second side of the vehicle. The method further includes notifying a driver or control system of the position of the vehicle.

Abstract: Example lane detection systems and methods are described. In one implementation, a method receives an image from a front-facing vehicle camera and applies a geometric transformation to the image to create a birds-eye view of the image. The method analyzes the birds-eye view of the image using a neural network, which was previously trained using side-facing vehicle camera images, to determine a lane position associated with the birds-eye view of the image.

Abstract: A method for determining a position of a vehicle in a lane includes receiving perception information from a first camera positioned on a first side of a vehicle and a second camera positioned on a second side of the vehicle. The method includes determining, using one or more neural networks, a position of the vehicle with respect to lane markings on the first side and the second side of the vehicle. The method further includes notifying a driver or control system of the position of the vehicle.