Abstract: Provided are methods for track segment cleaning of tracked objects using neural networks, which can include detecting a first track segment and a second track segment. The method includes applying a machine learning model trained to determine if the first track segment and second track segment capture real objects and if the first track segment and the second track segment are representative of an identical object exterior to a vehicle. The method further includes combining the first track segment and the second track segment to form a single track segment having a single trajectory in response to the first track segment and the second track segment being determined to be representative of the identical object. Systems and computer program products are also provided.

Abstract: This disclosure describes the use of optical sensors to detect and characterize the state of traffic lights to assist with the navigation of autonomous vehicles. In particular, a specific optical configuration is shown that includes both a fixed-exposure sensor and an auto-exposure sensor. Imagery from the two sensor types can be combined to more accurately characterize the state of traffic signals at any particular intersection. Systems and methods for analyzing only select regions of the imagery captured by the traffic light detection system are also described.

Abstract: Provided are methods for object detection using radar and lidar fusion, which can include generating clusters combining clusters of point clouds for radar and lidar, respectively, from which fused features are determined using a deep learning model. Systems and computer program products are also provided.

Abstract: Provided are methods for object detection using radar and lidar fusion, which can include generating clusters combining clusters of point clouds for radar and lidar, respectively, from which fused features are determined using a deep learning model. Systems and computer program products are also provided.

Abstract: This disclosure describes the use of optical sensors to detect and characterize the state of traffic lights to assist with the navigation of autonomous vehicles. In particular, a specific optical configuration is shown that includes both a fixed-exposure sensor and an auto-exposure sensor. Imagery from the two sensor types can be combined to more accurately characterize the state of traffic signals at any particular intersection. Systems and methods for analyzing only select regions of the imagery captured by the traffic light detection system are also described.

Abstract: Among other things, techniques are described for determining precedence order at a multiway stop. In embodiments, identifications are assigned to tracks, and young tracks are compared to stale tracks. A young track matches a stale track based on one or more factors. An identification of the young track is reassigned to an identification of the stale track, wherein the young track is determined to match the stale track based on the one or more factors. An earliest time of appearance of agents is determined based on identifications and in view of perception obscured areas. A precedence order for navigating through the intersection is determined based on local rules, the identifications, and the earliest time of appearance of agents, and the vehicle proceeds through the multiway stop intersection in accordance with the precedence order.

Abstract: Provided are methods for a track refinement network. In examples, center boxes are obtained from a record of driving data, wherein a center box is a center of a sequence of boxes along a track, and the track is associated with a tracked object detected within the sequence of boxes, each respective box comprising a center, a size, and an orientation. Track windows are generated around respective center boxes, wherein a track window corresponds to a respective center box along the track. Track windows are cropped and normalized with respect to center boxes to enable single refinement model for multiple object classes. Point cloud features and trajectory features are extracted from the cropped and normalized track windows. The point cloud features and trajectory features are input into a track refinement network, wherein the track refinement network uses features from the entire track to output a refined center, a refined size, and a refined orientation of each respective center box.

Abstract: Provided are methods for track segment cleaning of tracked objects using neural networks, which can include detecting a first track segment and a second track segment. The method includes applying a machine learning model trained to determine if the first track segment and second track segment capture real objects and if the first track segment and the second track segment are representative of an identical object exterior to a vehicle. The method further includes combining the first track segment and the second track segment to form a single track segment having a single trajectory in response to the first track segment and the second track segment being determined to be representative of the identical object. Systems and computer program products are also provided.

Abstract: Provided are systems and methods for a deep learning based beam control. Sensor data associated with the environment and the corresponding detected objects from a perception system are obtained. Object features and image features are extracted. The extracted object features and image features are fused into fused features. A beam control status is predicted according to the fused features, wherein the beam control status indicates a high beam illumination intensity or a low beam illumination intensity of a light emitting device.

Abstract: Among other things, techniques are described for determining precedence order at a multiway stop. In embodiments, identifications are assigned to tracks, and young tracks are compared to stale tracks. A young track matches a stale track based on one or more factors. An identification of the young track is reassigned to an identification of the stale track, wherein the young track is determined to match the stale track based on the one or more factors. An earliest time of appearance of agents is determined based on identifications and in view of perception obscured areas. A precedence order for navigating through the intersection is determined based on local rules, the identifications, and the earliest time of appearance of agents, and the vehicle proceeds through the multiway stop intersection in accordance with the precedence order.

Abstract: Provided are systems and methods for a deep learning based beam control. Sensor data associated with the environment and the corresponding detected objects from a perception system are obtained. Object features and image features are extracted. The extracted object features and image features are fused into fused features. A beam control status is predicted according to the fused features, wherein the beam control status indicates a high beam illumination intensity or a low beam illumination intensity of a light emitting device.

Abstract: Provided are methods for object detection using radar and lidar fusion, which can include generating clusters combining clusters of point clouds for radar and lidar, respectively, from which fused features are determined using a deep learning model. Systems and computer program products are also provided.

Abstract: Provided are methods for track segment cleaning of tracked objects using neural networks, which can include detecting a first track segment and a second track segment. The method includes applying a machine learning model trained to determine if the first track segment and second track segment capture real objects and if the first track segment and the second track segment are representative of an identical object exterior to a vehicle. The method further includes combining the first track segment and the second track segment to form a single track segment having a single trajectory in response to the first track segment and the second track segment being determined to be representative of the identical object. Systems and computer program products are also provided.

Abstract: In an example method, a perception system receives first data representing a point cloud having a plurality of points, and clusters the points into a plurality of clusters. The clusters include a first cluster representing a first portion of an object and a second cluster representing a second portion of the object. Further, the perception system generates a first bounding box enclosing at least the first cluster and the second cluster, and generates a second bounding box enclosing at least the first cluster and the second cluster. The perception system selects either the first bounding box or the second bounding box, and outputs second data representing the object. The second data includes an indication of the selected bounding box and an indication of the object.

Abstract: This disclosure describes the use of optical sensors to detect and characterize the state of traffic lights to assist with the navigation of autonomous vehicles. In particular, a specific optical configuration is shown that includes both a fixed-exposure sensor and an auto-exposure sensor. Imagery from the two sensor types can be combined to more accurately characterize the state of traffic signals at any particular intersection. Systems and methods for analyzing only select regions of the imagery captured by the traffic light detection system are also described.

Abstract: There is provided a method of signal light detection, and a corresponding signal light detection device. The method includes obtaining a dark frame of an environment, the dark frame comprising a plurality of light blobs captured corresponding to lights captured in the environment, obtaining a bright frame of the environment, the bright frame comprising a plurality of light blobs corresponding to lights captured in the environment, identifying a plurality of candidate light blobs from the plurality of light blobs in the dark frame, identifying a plurality of candidate regions in the bright frame based on the plurality of candidate light blobs identified from the dark frame, classifying each of the plurality of candidate light blobs based on the corresponding candidate region from the bright frame, and evaluating whether one or more of the plurality of classified candidate light blobs is a signal light from a particular type of signaling device.

Abstract: This invention features the identification of novel target genes for peroxisome proliferator-activated receptors alpha (PPAR?) in human, and their use in treating or monitoring the treatment of metabolic abnormalities, as well as in identifying compounds useful for treating metabolic abnormalities.

Abstract: A transgenic mouse with alterations in the H2-Ma gene is prepared by introduction of an altered H2-Ma gene into a host mouse. The resulting transgenic mice do not produce functional H2-M molecules.

Abstract: A transgenic animal with alterations in an thrombin receptor gene is prepared by introduction of an altered thrombin receptor gene into a host animal. The resulting transgenic animals do not produce functional thrombin receptor molecules.