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, perception of landmark shapes may be used for localization in autonomous systems and applications. In some embodiments, a deep neural network (DNN) is used to generate (e.g., per-point) classifications of measured 3D points (e.g., classified LiDAR points), and a representation of the shape of one or more detected landmarks is regressed from the classifications. For each of one or more classes, the classification data may be thresholded to generate a binary mask and/or dilated to generate a densified representation, and the resulting (e.g., dilated, binary) mask may be clustered into connected components that are iteratively: fitted a shape (e.g., a polynomial or Bezier spline for lane lines, a circle for top-down representations of poles or traffic lights), weighted, and merged. As such, the resulting connected components and their fitted shapes may be used to represent detected landmarks and used for localization, navigation, and/or other uses.

Abstract: In various examples, one or more DNNs may be used to detect landmarks (e.g., lane lines) and regress a representation of their shape. A DNN may be used to jointly generate classifications of measured 3D points using one output head (e.g., a classification head) and regress a representation of one or more fitted shapes (e.g., polylines, circles) using a second output head (e.g., a regression head). In some embodiments, multiple DNNs (e.g., a chain of multiple DNNs or multiple stages of a DNN) are used to sequentially generate classifications of measured 3D points and a regressed representation of the shape of one or more detected landmarks. As such, classified landmarks and corresponding fitted shapes may be decoded and used for localization, navigation, and/or other uses.

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, 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: 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 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: 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: 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 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 (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: In various examples, a technique for monitoring sensor performance is disclosed that includes aggregating sensor data collected by a sensor into a plurality of statistics for a plurality of sectors corresponding to a two-dimensional (2D) plane representing a sensory field of the sensor. The techniques also include determining a performance of the sensor based on the plurality of statistics and historical sensor data or information associated with the sensor. The techniques further include transmitting, to one or more components, one or more indications of the performance of the sensor to cause the one or more components to perform one or more operations in view of or accounting for the performance of the sensor.

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: 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 surface may be estimated using depth data for autonomous systems and applications. One or more software components or modules may use the depth data (e.g., 3D LiDAR point cloud data) in addition to ego-motion data (e.g., data representative of location, heading, speed, and/or pose of the ego-machine) to generate a non-parametric model of the ground or driving surface. In some embodiments, an iterative process may be used to generate and iteratively refine estimated surface values by minimizing (or approximating minimization of) a cost function that penalizes deviation between measured values and estimated values and/or deviations among adjacent measured values. The systems and applications described herein may include robust real-time or near real-time ground surface estimation relying on generated data, and may further include a large-scale offline ground surface estimation approach that is non-causal and uses (e.g., all) available data at once.

Abstract: In various examples, a hazard detection system plots hazard indicators from multiple detection sensors to grid cells of an occupancy grid corresponding to a driving environment. For example, as the ego-machine travels along a roadway, one or more sensors of the ego-machine may capture sensor data representing the driving environment. A system of the ego-machine may then analyze the sensor data to determine the existence and/or location of the one or more hazards within an occupancy grid—and thus within the environment. When a hazard is detected using a respective sensor, the system may plot an indicator of the hazard to one or more grid cells that correspond to the detected location of the hazard. Based, at least in part, on a fused or combined confidence of the hazard indicators for each grid cell, the system may predict whether the corresponding grid cell is occupied by a hazard.

Abstract: In various examples, systems and methods of the present disclosure detect and/or track objects in an environment using projection images generated from LiDAR. For example, a machine learning model—such as a deep neural network (DNN)—may be used to compute a motion mask indicative of motion corresponding to points representing objects in an environment. Various input channels may be provided as input to the machine learning model to compute a motion mask. One or more comparison images may be generated based on comparing depth values projected from a current range image to a coordinate space of a previous range image to depth values of the previous range image. The machine learning model may use the one or more projection images, the one or more comparison images, and/or the one or more range images to compute a motion mask and/or a motion vector output representation.