Abstract: The technology relates to using on-board sensor data, off-board information and a deep learning model to classify road wetness and/or to perform a regression analysis on road wetness based on a set of input information. Such information includes on-board and/or off-board signals obtained from one or more sources including on-board perception sensors, other on-board modules, external weather measurement, external weather services, etc. The ground truth includes measurements of water film thickness and/or ice coverage on road surfaces. The ground truth, on-board and off-board signals are used to build the model. The constructed model can be deployed in autonomous vehicles for classifying/regressing the road wetness with on-board and/or off-board signals as the input, without referring to the ground truth.

Abstract: The technology relates to using on-board sensor data, off-board information and a deep learning model to classify road wetness and/or to perform a regression analysis on road wetness based on a set of input information. Such information includes on-board and/or off-board signals obtained from one or more sources including on-board perception sensors, other on-board modules, external weather measurement, external weather services, etc. The ground truth includes measurements of water film thickness and/or ice coverage on road surfaces. The ground truth, on-board and off-board signals are used to build the model. The constructed model can be deployed in autonomous vehicles for classifying/regressing the road wetness with on-board and/or off-board signals as the input, without referring to the ground truth.

Abstract: The technology relates to using on-board sensor data, off-board information and a deep learning model to classify road wemess and/or to perform a regression analysis on road wetness based on a set of input information. Such information includes on-board and/or off-board signals obtained from one or more sources including on-board perception sensors, other on-board modules. external weather measurement, external weather services, etc. The ground truth includes measurements of water film thickness and/or ice coverage on road surfaces. The ground truth, on-board and off-board signals are used to build the model. The constructed model can be deployed in autonomous vehicles for classifying/regressing the road wetness with on-board and/or off-board signals as the input, without referring to the ground truth.

Abstract: The technology relates to using on-board sensor data, off-board information and a deep learning model to classify road wetness and/or to perform a regression analysis on road wetness based on a set of input information. Such information includes on-board and/or off-board signals obtained from one or more sources including on-board perception sensors, other on-board modules, external weather measurement, external weather services, etc. The ground truth includes measurements of water film thickness and/or ice coverage on road surfaces. The ground truth, on-board and off-board signals are used to build the model. The constructed model can be deployed in autonomous vehicles for classifying/regressing the road wetness with on-board and/or off-board signals as the input, without referring to the ground truth.

Abstract: The technology relates to using on-board sensor data, off-board information and a deep learning model to classify road wetness and/or to perform a regression analysis on road wetness based on a set of input information. Such information includes on-board and/or off-board signals obtained from one or more sources including on-board perception sensors, other on-board modules, external weather measurement, external weather services, etc. The ground truth includes measurements of water film thickness and/or ice coverage on road surfaces. The ground truth, on-board and off-board signals are used to build the model. The constructed model can be deployed in autonomous vehicles for classifying/regressing the road wetness with on-board and/or off-board signals as the input, without referring to the ground truth.

Abstract: The technology relates to using on-board sensor data, off-board information and a deep learning model to classify road wetness and/or to perform a regression analysis on road wetness based on a set of input information. Such information includes on-board and/or off-board signals obtained from one or more sources including on-board perception sensors, other on-board modules, external weather measurement, external weather services, etc. The ground truth includes measurements of water film thickness and/or ice coverage on road surfaces. The ground truth, on-board and off-board signals are used to build the model. The constructed model can be deployed in autonomous vehicles for classifying/regressing the road wetness with on-board and/or off-board signals as the input, without referring to the ground truth.

Abstract: Aspects of the disclosure relate to detecting spurious objects. For instance, a model may be trained using raining data including a plurality of LIDAR data points generated by a LIDAR sensor of a vehicle. Each given LIDAR data point includes location information and intensity information, and is associated with waveform data for that given LIDAR data point. At least one of the plurality of LIDAR data points is further associated with a label identifying spurious objects through which the vehicle is able to drive. The model and/or a plurality of heuristics may then be provided to a vehicle in order to allow the vehicle to determine LIDAR data points that correspond to spurious objects. These LIDAR data points may then be filtered from sensor data, and the filtered sensor data may be used to control the vehicle in an autonomous driving mode.

Abstract: Aspects of the disclosure relate to detecting spurious objects. For instance, a model may be trained using raining data including a plurality of LIDAR data points generated by a LIDAR sensor of a vehicle. Each given LIDAR data point includes location information and intensity information, and is associated with waveform data for that given LIDAR data point. At least one of the plurality of LIDAR data points is further associated with a label identifying spurious objects through which the vehicle is able to drive. The model and/or a plurality of heuristics may then be provided to a vehicle in order to allow the vehicle to determine LIDAR data points that correspond to spurious objects. These LIDAR data points may then be filtered from sensor data, and the filtered sensor data may be used to control the vehicle in an autonomous driving mode.

Abstract: The technology relates to using on-board sensor data, off-board information and a deep learning model to classify road wetness and/or to perform a regression analysis on road wetness based on a set of input information. Such information includes on-board and/or off-board signals obtained from one or more sources including on-board perception sensors, other on-board modules, external weather measurement, external weather services, etc. The ground truth includes measurements of water film thickness and/or ice coverage on road surfaces. The ground truth, on-board and off-board signals are used to build the model. The constructed model can be deployed in autonomous vehicles for classifying/regressing the road wetness with on-board and/or off-board signals as the input, without referring to the ground truth.

Abstract: Aspects of the disclosure provide methods for controlling a first vehicle having an autonomous driving mode. In one instance, sensor data generated by one or more sensors of the first vehicle may be received. A splash and characteristics of the splash may be detected from the sensor data using a classifier. A severity of a puddle may be determined based on the characteristics of the splash and a speed of a second vehicle that caused the splash. The first vehicle may be controlled based on the severity. In another instance, a location of a puddle relative to a tire of a second vehicle is estimated using sensor data generated by one or more sensors of the first vehicle. A severity of the puddle may be determined based on the estimated location. The first vehicle may be controlled based on the severity.

Abstract: The technology relates detecting standing water. In one example, a system comprising one or more processors may be configured to receive sensor data generated by a perception system of a vehicle, wherein the sensor data corresponds to an area surrounding a vehicle. The one or more processors may identify a location in the area where the sensor data is not present and receive map information corresponding to the area, wherein the map information includes road surface locations. The one or more processors may determine that the location corresponds to one or more of the road surface locations in the map information; and output, based upon the determination that the location corresponds to one or more of the road surface locations in the map information, an indication that standing water is at the location.

Abstract: Aspects of the disclosure relate to detecting spurious objects. For instance, a model may be trained using raining data including a plurality of LIDAR data points generated by a LIDAR sensor of a vehicle. Each given LIDAR data point includes location information and intensity information, and is associated with waveform data for that given LIDAR data point. At least one of the plurality of LIDAR data points is further associated with a label identifying spurious objects through which the vehicle is able to drive. The model and/or a plurality of heuristics may then be provided to a vehicle in order to allow the vehicle to determine LIDAR data points that correspond to spurious objects. These LIDAR data points may then be filtered from sensor data, and the filtered sensor data may be used to control the vehicle in an autonomous driving mode.