Abstract: In various examples, a hazard detection system fuses outputs from multiple sensors over time to determine a probability that a stationary object or hazard exists at a location. The system may then use sensor data to calculate a detection bounding shape for detected objects and, using the bounding shape, may generate a set of particles, each including a confidence value that an object exists at a corresponding location. The system may then capture additional sensor data by one or more sensors of the ego-machine that are different from those used to capture the first sensor data. To improve the accuracy of the confidences of the particles, the system may determine a correspondence between the first sensor data and the additional sensor data (e.g., depth sensor data), which may be used to filter out a portion of the particles and improve the depth predictions corresponding to the object.

Abstract: In various examples, an obstacle detector is capable of tracking a velocity state of detected objects or obstacles using LiDAR data. For example, using LiDAR data alone, an iterative closest point (ICP) algorithm may be used to determine a current state of detected objects for a current frame and a Kalman filter may be used to maintain a tracked state of the one or more objects detected over time. The obstacle detector may be configured to estimate velocity for one or more detected objects, compare the estimated velocity to one or more previous tracked states for previously detected objects, determine that the detected objects corresponds to a certain previously detected object, and update the tracked state for the previously detected object with the estimated velocity.

Abstract: In various examples, a deep neural network(s) (e.g., a convolutional neural network) may be trained to detect moving and stationary obstacles from RADAR data of a three dimensional (3D) space. In some embodiments, ground truth training data for the neural network(s) may be generated from LIDAR data. More specifically, a scene may be observed with RADAR and LIDAR sensors to collect RADAR data and LIDAR data for a particular time slice. The RADAR data may be used for input training data, and the LIDAR data associated with the same or closest time slice as the RADAR data may be annotated with ground truth labels identifying objects to be detected. The LIDAR labels may be propagated to the RADAR data, and LIDAR labels containing less than some threshold number of RADAR detections may be omitted. The (remaining) LIDAR labels may be used to generate ground truth data.

Abstract: In various examples, systems and methods are described that generate scene flow in 3D space through simplifying the 3D LiDAR data to “2.5D” optical flow space (e.g., x, y, and depth flow). For example, LiDAR range images may be used to generate 2.5D representations of depth flow information between frames of LiDAR data, and two or more range images may be compared to generate depth flow information, and messages may be passed—e.g., using a belief propagation algorithm—to update pixel values in the 2.5D representation. The resulting images may then be used to generate 2.5D motion vectors, and the 2.5D motion vectors may be converted back to 3D space to generate a 3D scene flow representation of an environment around an autonomous machine.

Abstract: A deep neural network(s) (DNN) may be used to detect objects from sensor data of a three dimensional (3D) environment. For example, a multi-view perception DNN may include multiple constituent DNNs or stages chained together that sequentially process different views of the 3D environment. An example DNN may include a first stage that performs class segmentation in a first view (e.g., perspective view) and a second stage that performs class segmentation and/or regresses instance geometry in a second view (e.g., top-down). The DNN outputs may be processed to generate 2D and/or 3D bounding boxes and class labels for detected objects in the 3D environment. As such, the techniques described herein may be used to detect and classify animate objects and/or parts of an environment, and these detections and classifications may be provided to an autonomous vehicle drive stack to enable safe planning and control of the autonomous vehicle.

Abstract: A deep neural network(s) (DNN) may be used to detect objects from sensor data of a three dimensional (3D) environment. For example, a multi-view perception DNN may include multiple constituent DNNs or stages chained together that sequentially process different views of the 3D environment. An example DNN may include a first stage that performs class segmentation in a first view (e.g., perspective view) and a second stage that performs class segmentation and/or regresses instance geometry in a second view (e.g., top-down). The DNN outputs may be processed to generate 2D and/or 3D bounding boxes and class labels for detected objects in the 3D environment. As such, the techniques described herein may be used to detect and classify animate objects and/or parts of an environment, and these detections and classifications may be provided to an autonomous vehicle drive stack to enable safe planning and control of the autonomous vehicle.

Abstract: In various examples, a deep neural network(s) (e.g., a convolutional neural network) may be trained to detect moving and stationary obstacles from RADAR data of a three dimensional (3D) space. In some embodiments, ground truth training data for the neural network(s) may be generated from LIDAR data. More specifically, a scene may be observed with RADAR and LIDAR sensors to collect RADAR data and LIDAR data for a particular time slice. The RADAR data may be used for input training data, and the LIDAR data associated with the same or closest time slice as the RADAR data may be annotated with ground truth labels identifying objects to be detected. The LIDAR labels may be propagated to the RADAR data, and LIDAR labels containing less than some threshold number of RADAR detections may be omitted. The (remaining) LIDAR labels may be used to generate ground truth data.

Abstract: In various examples, systems and methods are disclosed that perform sensor fusion using rule-based and learned processing methods to take advantage of the accuracy of learned approaches and the decomposition benefits of rule-based approaches for satisfying higher levels of safety requirements. For example, in-parallel and/or in-serial combinations of early rule-based sensor fusion, late rule-based sensor fusion, early learned sensor fusion, or late learned sensor fusion may be used to solve various safety goals associated with various required safety levels at a high level of accuracy and precision. In embodiments, learned sensor fusion may be used to make more conservative decisions than the rule-based sensor fusion (as determined using, e.g., severity (S), exposure (E), and controllability (C) (SEC) associated with a current safety goal), but the rule-based sensor fusion may be relied upon where the learned sensor fusion decision may be less conservative than the corresponding rule-based sensor fusion.

Abstract: An annotation pipeline may be used to produce 2D and/or 3D ground truth data for deep neural networks, such as autonomous or semi-autonomous vehicle perception networks. Initially, sensor data may be captured with different types of sensors and synchronized to align frames of sensor data that represent a similar world state. The aligned frames may be sampled and packaged into a sequence of annotation scenes to be annotated. An annotation project may be decomposed into modular tasks and encoded into a labeling tool, which assigns tasks to labelers and arranges the order of inputs using a wizard that steps through the tasks. During the tasks, each type of sensor data in an annotation scene may be simultaneously presented, and information may be projected across sensor modalities to provide useful contextual information. After all annotation tasks have been completed, the resulting ground truth data may be exported in any suitable format.

Abstract: A deep neural network(s) (DNN) may be used to detect objects from sensor data of a three dimensional (3D) environment. For example, a multi-view perception DNN may include multiple constituent DNNs or stages chained together that sequentially process different views of the 3D environment. An example DNN may include a first stage that performs class segmentation in a first view (e.g., perspective view) and a second stage that performs class segmentation and/or regresses instance geometry in a second view (e.g., top-down). The DNN outputs may be processed to generate 2D and/or 3D bounding boxes and class labels for detected objects in the 3D environment. As such, the techniques described herein may be used to detect and classify animate objects and/or parts of an environment, and these detections and classifications may be provided to an autonomous vehicle drive stack to enable safe planning and control of the autonomous vehicle.

Abstract: A deep neural network(s) (DNN) may be used to detect objects from sensor data of a three dimensional (3D) environment. For example, a multi-view perception DNN may include multiple constituent DNNs or stages chained together that sequentially process different views of the 3D environment. An example DNN may include a first stage that performs class segmentation in a first view (e.g., perspective view) and a second stage that performs class segmentation and/or regresses instance geometry in a second view (e.g., top-down). The DNN outputs may be processed to generate 2D and/or 3D bounding boxes and class labels for detected objects in the 3D environment. As such, the techniques described herein may be used to detect and classify animate objects and/or parts of an environment, and these detections and classifications may be provided to an autonomous vehicle drive stack to enable safe planning and control of the autonomous vehicle.

Abstract: In various examples, a deep neural network(s) (e.g., a convolutional neural network) may be trained to detect moving and stationary obstacles from RADAR data of a three dimensional (3D) space, in both highway and urban scenarios. RADAR detections may be accumulated, ego-motion-compensated, orthographically projected, and fed into a neural network(s). The neural network(s) may include a common trunk with a feature extractor and several heads that predict different outputs such as a class confidence head that predicts a confidence map and an instance regression head that predicts object instance data for detected objects. The outputs may be decoded, filtered, and/or clustered to form bounding shapes identifying the location, size, and/or orientation of detected object instances. The detected object instances may be provided to an autonomous vehicle drive stack to enable safe planning and control of the autonomous vehicle.

Abstract: In various examples, a deep neural network(s) (e.g., a convolutional neural network) may be trained to detect moving and stationary obstacles from RADAR data of a three dimensional (3D) space. In some embodiments, ground truth training data for the neural network(s) may be generated from LIDAR data. More specifically, a scene may be observed with RADAR and LIDAR sensors to collect RADAR data and LIDAR data for a particular time slice. The RADAR data may be used for input training data, and the LIDAR data associated with the same or closest time slice as the RADAR data may be annotated with ground truth labels identifying objects to be detected. The LIDAR labels may be propagated to the RADAR data, and LIDAR labels containing less than some threshold number of RADAR detections may be omitted. The (remaining) LIDAR labels may be used to generate ground truth data.

Abstract: A deep neural network(s) (DNN) may be used to detect objects from sensor data of a three dimensional (3D) environment. For example, a multi-view perception DNN may include multiple constituent DNNs or stages chained together that sequentially process different views of the 3D environment. An example DNN may include a first stage that performs class segmentation in a first view (e.g., perspective view) and a second stage that performs class segmentation and/or regresses instance geometry in a second view (e.g., top-down). The DNN outputs may be processed to generate 2D and/or 3D bounding boxes and class labels for detected objects in the 3D environment. As such, the techniques described herein may be used to detect and classify animate objects and/or parts of an environment, and these detections and classifications may be provided to an autonomous vehicle drive stack to enable safe planning and control of the autonomous vehicle.

Abstract: In various examples, a deep neural network (DNN) may be used to detect and classify animate objects and/or parts of an environment. The DNN may be trained using camera-to-LiDAR cross injection to generate reliable ground truth data for LiDAR range images. For example, annotations generated in the image domain may be propagated to the LiDAR domain to increase the accuracy of the ground truth data in the LiDAR domain—e.g., without requiring manual annotation in the LiDAR domain. Once trained, the DNN may output instance segmentation masks, class segmentation masks, and/or bounding shape proposals corresponding to two-dimensional (2D) LiDAR range images, and the outputs may be fused together to project the outputs into three-dimensional (3D) LiDAR point clouds. This 2D and/or 3D information output by the DNN may be provided to an autonomous vehicle drive stack to enable safe planning and control of the autonomous vehicle.

Abstract: A deep neural network(s) (DNN) may be used to perform panoptic segmentation by performing pixel-level class and instance segmentation of a scene using a single pass of the DNN. Generally, one or more images and/or other sensor data may be stitched together, stacked, and/or combined, and fed into a DNN that includes a common trunk and several heads that predict different outputs. The DNN may include a class confidence head that predicts a confidence map representing pixels that belong to particular classes, an instance regression head that predicts object instance data for detected objects, an instance clustering head that predicts a confidence map of pixels that belong to particular instances, and/or a depth head that predicts range values. These outputs may be decoded to identify bounding shapes, class labels, instance labels, and/or range values for detected objects, and used to enable safe path planning and control of an autonomous vehicle.

Abstract: A system and method are disclosed for use in a virtual reality environment including a head mounted display device and a processing unit. In examples, the processing unit adjusts an amount by which left and right displayed images overlap each other at a given distance, such as the focal distance, from the head mounted display device.

Abstract: A system and method are disclosed for use in a virtual reality environment including a head mounted display device and a processing unit. In examples, the processing unit adjusts an amount by which left and right displayed images overlap each other at a given distance, such as the focal distance, from the head mounted display device.

Abstract: Systems and methods are described herein that cause data from asynchronous data sources to be provided with a timestamp that corresponds to a common time base. A trigger board can be used to control synchronized data sources, and can generate timestamps when data is collected by the synchronized data sources. Unsynchronized data sources can generate data independent of the trigger board. System timestamps are generated each time data from the synchronized data source and the unsynchronized data source is received. Values of the system timestamp can be modified, and can be replaced by timestamps that correspond to the time base used by the trigger board.

Abstract: A system described herein includes a receiver component that receives first velocity data that is indicative of a velocity of a vehicle over a period of time, wherein the first velocity data corresponds to a first sensor. The receiver component also receives second velocity data that is indicative of the velocity of the vehicle over the period of time, wherein the second velocity data corresponds to a second sensor. The system also includes a modifier component that determines a difference between the first velocity data and the second velocity data and outputs at least one final velocity value for the vehicle based at least in part upon the first difference data.