Abstract: A system subscribes to one or more inference topics to which inferences are published on behalf of trainable software models executing in a vehicle computing environment. The system receives inferences from the topics as the inferences are published to the topics and associates the inferences with one or more trainable software models to be monitored. Also, the system identifies instances of unexpected output based on comparison of received inferences, associated with a given model to be monitored, to expected inference values identified in a configuration file, stored in a vehicle memory and associated with the given model, and, responsive to identifying the unexpected output, devises a modification strategy for the model based on characteristics of the unexpected output.

Abstract: A vehicle system receives indication of a newly trained machine learning model designated for validation. The system load a copy of the model into shadow execution hardware, capable of background execution of the model and subscribes to one or more data topics to which input data for the model, gathered by a vehicle data gathering process, is published. The system executes the model in the background as the vehicle travels, using data published to the data topics and benchmarks output from the model to determine whether the model outperforms a prior version of the model, that represents the model prior to the model being newly trained, based on relative performance of both models compared to performance expectations defined in a configuration file stored by the vehicle. Also, the system, responsive to the model outperforming the prior version of the model based on the performance expectations defined by the configuration file, validates the model as suitable for deployment.

Abstract: A system receives identification of a machine learning model, stored by a vehicle, that is ready for training. The system determines, based on a configuration file associated with the model, whether batch-based or live training is to be used to train the model and collects data for training, defined by a configuration file associated with the model. The system calls a learning as a service vehicle process to load a kernel and configures the kernel based on configuration data defined in the configuration file. The system receives notification from the learning as a service process that the training is complete. Additionally, the system validates a model, responsive to the notification including indication that training was successful, using a vehicle model validation process to test the model with live data before deployment by background execution of the model and saves a copy of the model for deployment responsive to successful validation.

Abstract: A system receives a plurality of data sets relating to differently trained versions of a global machine learning model, from a plurality of vehicles, the data sets including at least a present local loss value experienced by a current version of the global model executing on a given vehicle for which a data set of the plurality of data sets was received. The system determines a loss reduction for each received data set, representing a loss reduction since a previous local loss value included in a previous received data set corresponding to the given vehicle. The system determines whether the loss reduction for each received data set of the plurality of data sets exceeds a predefined threshold cutoff value and trains the global model using federated learning and based on the data sets of the plurality of data sets for which the loss reduction exceeds the predefined cutoff value.

Abstract: A LiDAR point cloud that includes two candidate clusters for merging is received. At a first phase, a distance between the two clusters is determined. If the distance is greater than a threshold, the candidate clusters are not merged. Otherwise, an additional point cloud is received for each cluster at different times. A motion characteristic is determined for each cluster. If the motion characteristic for each cluster is close (indicating that the objects are moving at the same speed), then the clusters are merged. Otherwise the clusters are not merged. The motion characteristic for a cluster can be determined by performing an alignment operation using the point cloud received for the cluster, and using the error associated with the alignment operation as the motion characteristic for the cluster. The decision to merge clusters is based on raw point cloud data, which can take place early in the tracking cycle.

Abstract: In one embodiment, example systems and methods related to determining when to merge clusters are provided. A LiDAR point cloud that includes two candidate clusters for merging is received. At a first phase, a distance between the two clusters is determined. If the distance is greater than a threshold, the candidate clusters are not merged. Otherwise, an additional point cloud is received for each cluster at different times. A motion characteristic is determined for each cluster based on the point cloud received for each cluster. If the motion characteristic for each cluster is close (indicating that the objects represented by the clusters are moving at the same speed), then the clusters are merged. Otherwise the clusters are not merged. The motion characteristic for a cluster can be determined by performing an alignment operation using the point cloud received for the cluster, and using the error associated with the alignment operation as the motion characteristic for the cluster.

Abstract: The present disclosure provides a dimension estimating system for a host vehicle. The dimension estimating system includes an image sensor and a dimension estimator. The image sensor obtains image data of at least one side of a target vehicle around the host vehicle. The dimension estimator estimates, through a machine learning algorithm, a dimension of the target vehicle based on the image data of the one side of the target vehicle obtained by the image sensor.

Abstract: The present disclosure provides an auto-braking system which includes a braking device, a receiver, and a controller. The controller includes a determining portion, a verifying portion and an executing portion. The determining portion determines whether a vehicle will violate a red signal of the traffic light based on the traffic light state information. The verifying portion verifies the traffic light state information is valid by comparing the traffic light state information with the image of the traffic light captured by the sensor. The executing portion executes a first braking control to slow the vehicle at a first deceleration rate when the determining portion determines that the vehicle will violate a red signal. The executing portion executes a second braking control to slow the vehicle at a second deceleration rate to stop at a specified position when the verifying portion verifies that the traffic light state information is valid.

Abstract: The present disclosure provides an auto-braking system which includes a braking device, a receiver, and a controller. The controller includes a determining portion, a verifying portion and an executing portion. The determining portion determines whether a vehicle will violate a red signal of the traffic light based on the traffic light state information. The verifying portion verifies the traffic light state information is valid by comparing the traffic light state information with the image of the traffic light captured by the sensor. The executing portion executes a first braking control to slow the vehicle at a first deceleration rate when the determining portion determines that the vehicle will violate a red signal. The executing portion executes a second braking control to slow the vehicle at a second deceleration rate to stop at a specified position when the verifying portion verifies that the traffic light state information is valid.