Abstract: The subject disclosure relates to techniques for managing the configuration of vehicles. A process of the disclosed technology can include steps of receiving a first vehicle identifier for a first vehicle, wherein the first vehicle is associated with a first vehicle platform, identifying a first configuration for the first vehicle platform based on the first vehicle identifier, receiving a second vehicle identifier for a second vehicle, wherein the second vehicle is associated with a second vehicle platform, and wherein the first vehicle platform is different from the second vehicle platform, and identifying a second configuration for the second vehicle platform based on the second vehicle identifier, wherein the first vehicle and the second vehicle run on an identical software stack. Systems and machine-readable media are also provided.

Abstract: The subject disclosure relates to ways to identify self-hit data collected by autonomous vehicle (AV) sensors. In some aspects, a method of the disclosed technology includes steps for generating a geometric model of an autonomous vehicle (AV), wherein the geometric model specifies physical boundaries of the AV in three-dimensional (3D) space, collecting sensor data for an environment around the AV, and identifying one or more data points, from among the collected sensor data, that correspond with a surface of the AV. Systems and machine-readable media are also provided.

Abstract: The subject disclosure relates to ways to identify self-hit data collected by autonomous vehicle (AV) sensors. In some aspects, a method of the disclosed technology includes steps for generating a geometric model of an autonomous vehicle (AV), wherein the geometric model specifies physical boundaries of the AV in three-dimensional (3D) space, collecting sensor data for an environment around the AV, and identifying one or more data points, from among the collected sensor data, that correspond with a surface of the AV. Systems and machine-readable media are also provided.

Abstract: The subject disclosure relates to techniques for maintaining an optimized mix of samples selected from a smaller data set and a larger data set for use in training a machine learning algorithm. A process of the disclosed technology can include creating a plurality of chunks of samples, wherein each chunk contains a predetermined proportion of samples from the smaller data set and the larger data set, while also including substantially all samples in the larger dataset are distributed across the plurality of chunks of samples, loading a first chunk of samples of the plurality of chunks of samples into a memory, randomizing the order of samples in the first chunk of samples, and providing the samples in the first chunk of samples in the randomized order into the machine learning algorithm.

Abstract: The subject disclosure relates to techniques for managing the configuration of vehicles. A process of the disclosed technology can include steps of receiving a first vehicle identifier for a first vehicle, wherein the first vehicle is associated with a first vehicle platform, identifying a first configuration for the first vehicle platform based on the first vehicle identifier, receiving a second vehicle identifier for a second vehicle, wherein the second vehicle is associated with a second vehicle platform, and wherein the first vehicle platform is different from the second vehicle platform, and identifying a second configuration for the second vehicle platform based on the second vehicle identifier, wherein the first vehicle and the second vehicle run on an identical software stack. Systems and machine-readable media are also provided.

Abstract: The subject disclosure relates to techniques for improving performance of a machine learning algorithm that at least receives data descriptive of a 3-D object and provides an output, where the 3-D object occurs infrequently in a training dataset. A process of the disclosed technology can include determining that the machine learning algorithm performed below a threshold performance score when receiving data descriptive of the 3-D object in a real-world scene, wherein the 3-D object is classified as a first type of object, creating at least one 3-D representation of the first type of object for use in a simulation, modifying a plurality of simulated scenes to include the at least one 3-D representation of the first type of object, and training the machine learning algorithm with the modified simulated scenes, whereby the machine learning algorithm has greater exposure to the first type of object.

Abstract: The subject disclosure relates to techniques for tracking keypoints on an object represented in a Light Detection and Ranging (LiDAR) point cloud. A process of the disclosed technology can include receiving, for each of a plurality of frames in a series, an identification of at least one keypoint on the object represented in LiDAR point clouds and a confidence score for the respective keypoint, wherein each of the plurality of frames includes LiDAR point clouds including the object at different times represented in the series, and determining kinematics for the object from a determined movement of the keypoint across the plurality of frames.

Abstract: The subject disclosure relates to techniques for identifying keypoints associated with an object based on LiDAR point cloud data. A process of the disclosed technology can include inputting the LiDAR point cloud data representing an object as perceived by a LiDAR sensor into an algorithm trained to identify the keypoints associated with the object, and identifying, by the algorithm, at least one keypoint associated with the object and a respective confidence score for the at least one keypoint.

Abstract: The present technology is directed to identifying and labeling a vehicle appendage. More specifically, the present technology is generally related to receiving one or more lidar points associated with a vehicle having an appendage and outputting a label to classify the vehicle and the appendage. In some examples, a first portion of the one or more lidar points associated with the vehicle having the appendage represents the vehicle and a second portion of the one or more lidar points associated with the vehicle having the appendage represents the appendage The present disclosure can further train a perception model to output the label to classify the vehicle and the appendage.

Abstract: The subject disclosure relates to ways to identify self-hit data collected by autonomous vehicle (AV) sensors. In some aspects, a method of the disclosed technology includes steps for generating a geometric model of an autonomous vehicle (AV), wherein the geometric model specifies physical boundaries of the AV in three-dimensional (3D) space, collecting sensor data for an environment around the AV, and identifying one or more data points, from among the collected sensor data, that correspond with a surface of the AV. Systems and machine-readable media are also provided.