Abstract: A radar sensor system receives or generates radar data indicative of radar returns received at an antenna array. An encoder neural network encodes the radar data into first embeddings defined in a first latent space. A transformer neural network receives the first embeddings and transforms the first embeddings to second embeddings defined in a second latent space. A decoder neural network receives the second embeddings and decodes the second embeddings to generate beamformed radar data.

Abstract: A method and apparatus for implementing a method are disclosed. The method includes providing point cloud data to a machine learning algorithm, the point cloud data detected in the vicinity of an autonomous vehicle. The method further includes differentiating, via the machine learning algorithm, in the point cloud, data directly representing a location of a first object and data indirectly representing a location of a second object. The method includes transforming the data indirectly representing the location of the second object into data directly representing the location of the second object and generating corrected point cloud data based on the data directly representing the location of the first object and the data directly representing the location of the second object. The method includes outputting the corrected point cloud data to the autonomous vehicle.

Abstract: A method of calibrating a radar sensor includes receiving radar returns from a plurality of objects based on a radar signal sent from the radar sensor, each of the radar returns having a magnitude, at least a subset of the objects are known static objects, identifying a location and orientation of the radar sensor when the signal was sent, identifying expected reflectance values for each of the plurality of known static objects, calculating a conversion function configured to adjust the magnitudes of each of the radar returns for the known static objects to an estimated reflectance value based on the expected reflectance values for each of the known static objects, and adjusting an output of the radar sensor based on the conversion function.

Abstract: The technologies described herein relate to a radar system that is configured to generate point clouds based upon radar tensors generated by the radar system. More specifically, the radar system is configured to generate heatmaps based upon radar tensors, wherein a neural network receives the radar tensors as input and constructs the heatmaps as output. Point clouds are generated based upon the heatmaps. A computing system detects objects in an environment of an autonomous vehicle (AV) based upon the point clouds, and the computing system further causes the AV to perform a driving maneuver based upon the detected objects.

Abstract: A system includes a first sensor system of a first modality and a second sensor system of a second modality. The system further includes a computing system that is configured to detect and identify objects represented in sensor signals output by the first and second sensor systems. The computing system employs a hierarchical arrangement of transformers to fuse features of first sensor data output by the first sensor system and second sensor data output by the second sensor system.

Abstract: Technologies described herein relate to learning parameter values of a preprocessing algorithm that is executed in a radar system. The preprocessing algorithm is configured to receive raw radar data as input and is further configured to generate three-dimensional point clouds as output, where the preprocessing algorithm generates the three-dimensional point clouds based upon the raw radar data and the parameter values that are assigned to the preprocessing algorithm. To learn the parameter values, the preprocessing algorithm is converted to auto-differentiated form and is added as an input network layer to a deep neural network (DNN) that is configured to identify objects represented in three-dimensional point clouds. The parameter values are learned jointly with weight matrices of the DNN.

Abstract: The technologies described herein relate to a radar system that is configured to generate point clouds based upon radar tensors generated by the radar system. More specifically, the radar system is configured to identify bins in radar tensors that correspond to objects in an environment of the radar system, and to use energy values in other bins to construct a point cloud. A computing system detects objects in an environment of the radar system based upon the point clouds.

Abstract: The technologies described herein relate to a computing architecture in an autonomous vehicle (AV). The AV includes a radar system that includes a local data processing device. The AV also includes a centralized data processing device. The local data processing device is configured to perform processing on raw sensor data generated by the radar system to form a feature vector. The local data processing device transmits the feature vector to the centralized data processing device, which performs further processing to identify an object in an environment of the AV.

Abstract: Various technologies relating to a system that uses a computer-implemented model to determine optimal radar parameter settings based on the situational and environmental context of an autonomous vehicle (AV) to improve driving outcomes of the AV. Simulated sensor data corresponding to different radar parameter settings can be generated in simulation, and the computer-implemented model can be trained based on the respective sets of simulated sensor data. A radar system of an AV can be modified to operate using a radar parameter setting identified by the computer-implemented model, where the radar parameter setting is outputted by the computer-implemented model responsive to a state identified from sensor data being inputted to the computer-implemented model. The AV can use the output of the computer-implemented model to select the optimal radar parameter settings to implement.

Abstract: A radar sensor system receives or generates radar data indicative of radar returns received at an antenna array. An encoder neural network encodes the radar data into first embeddings defined in a first latent space. A transformer neural network receives the first embeddings and transforms the first embeddings to second embeddings defined in a second latent space. A decoder neural network receives the second embeddings and decodes the second embeddings to generate beamformed radar data.

Abstract: The technologies described herein relate to a domain adaptation system for sensor data. A computer-implemented model is trained using a set of training sensor data to facilitate classification of objects that are in the vicinity of an autonomous vehicle (AV). The set of training data corresponds to a first domain, such as firmware version of a sensor system, model of a sensor system, position of the sensor system on a vehicle, an environmental condition, etc. The set of training data is generated based upon pre-existing training data that corresponds to a second domain that is different from the first domain. Put differently, the pre-existing training data is transformed to correspond to the domain of a sensor system as it will be used on the AV.

Abstract: The technologies described herein relate to a computing architecture in an autonomous vehicle (AV). The AV includes a radar system that includes a local data processing device. The AV also includes a centralized data processing device. The local data processing device is configured to perform processing on raw sensor data generated by the radar system to form a feature vector. The local data processing device transmits the feature vector to the centralized data processing device, which performs further processing to identify an object in an environment of the AV.