Abstract: The pedestrian tracking system implemented in a host vehicle is disclosed. The system estimates trajectories of the host vehicle and the pedestrian based on factors of position and velocity of the host vehicle and parameters of position and velocity of the pedestrian. The trajectories of the host vehicle and the pedestrian are estimated to estimate a point of intersection of the host vehicle and the pedestrian. Further, the system estimates time to collision based on the estimated point of intersection and determines trajectory of the pedestrian in path of the host vehicle. Furthermore, the system assesses collision risk to select the pedestrian as a target and generates a deceleration actuation command to decelerate the host vehicle based on the selected target, which is provided to an automatic emergency braking (AEB) actuation unit.

Abstract: An aspect of the present disclosure relates to a system implemented in a host vehicle, comprising: a radar based detection unit, comprising one or more radar sensors, for detecting one or more targets around the host vehicle; a vision based detection unit, comprising one or more image sensors, for detecting one or more targets in the field of view of the host vehicle; and a processing unit to: receive information corresponding to detected one or more targets from each of the radar based detection unit and the vision based detection unit; match each of the one or more targets detected by the radar based detection unit with one or more targets detected by vision based detection unit to identify a target as a matched target; categorize the matched target as a locked target; and track the locked target using information received from the radar based detection unit.

Abstract: An aspect of the present disclosure relates to a system implemented in a host vehicle, comprising: a radar based detection unit, comprising one or more radar sensors, for detecting one or more targets around the host vehicle; a vision based detection unit, comprising one or more image sensors, for detecting one or more targets in the field of view of the host vehicle; and a processing unit to: receive information corresponding to detected one or more targets from each of the radar based detection unit and the vision based detection unit; match each of the one or more targets detected by the radar based detection unit with one or more targets detected by vision based detection unit to identify a target as a matched target; categorize the matched target as a locked target; and track the locked target using information received from the radar based detection unit.

Abstract: The pedestrian tracking system implemented in a host vehicle is disclosed. The system estimates trajectories of the host vehicle and the pedestrian based on factors of position and velocity of the host vehicle and parameters of position and velocity of the pedestrian. The trajectories of the host vehicle and the pedestrian are estimated to estimate a point of intersection of the host vehicle and the pedestrian. Further, the system estimates time to collision based on the estimated point of intersection and determines trajectory of the pedestrian in path of the host vehicle. Furthermore, the system assesses collision risk to select the pedestrian as a target and generates a deceleration actuation command to decelerate the host vehicle based on the selected target, which is provided to an automatic emergency braking (AEB) actuation unit.

Abstract: Provided are techniques for the efficient distribution of peer zone databases in a FC Fabric. In an example, a switch instantiates a peer zone definition defining a peer zone in which two or more initiator host devices are each permitted to communicate with one or more target storage devices via the switched FC fabric and the two or more initiator host devices are prevented from communicating with each other. The switch stores the peer zone definition in a peer zone database at the FC switch, and distributes the peer zone definition to other FC switches of the switched FC fabric without performing a Fabric lock operation.

Abstract: Provided are techniques for the efficient distribution of peer zone databases in a FC Fabric. In an example, a switch instantiates a peer zone definition defining a peer zone in which two or more initiator host devices are each permitted to communicate with one or more target storage devices via the switched FC fabric and the two or more initiator host devices are prevented from communicating with each other. The switch stores the peer zone definition in a peer zone database at the FC switch, and distributes the peer zone definition to other FC switches of the switched FC fabric without performing a Fabric lock operation.

Abstract: Provided are techniques for the efficient distribution of peer zone databases in a FC Fabric. In an example, a switch instantiates a peer zone definition defining a peer zone in which two or more initiator host devices are each permitted to communicate with one or more target storage devices via the switched FC fabric and the two or more initiator host devices are prevented from communicating with each other. The switch stores the peer zone definition in a peer zone database at the FC switch, and distributes the peer zone definition to other FC switches of the switched FC fabric without performing a Fabric lock operation.

Abstract: Presented herein are priority route based techniques for mitigation of slow drain devices in a Fibre Channel (FC) fabric comprising a plurality of FC switches. In accordance with examples presented herein, a first FC switch in a FC fabric receives an indication that a first computing device attached to the FC fabric has entered a slow drain condition. The first FC switch is configured to prepare and install a priority route for packet flows directed to the first computing device.

Abstract: An embodiment disclosed herein pertains to a system implemented in a host vehicle comprising a processing unit to receive radar data, pertaining to a target vehicle, detected by a radar sensor; map the received radar data in an image received from an image sensor to obtain a radar map point in said image, wherein the radar map point is obtained by compensating an offset error pertaining to height of the target vehicle; detect position of the target vehicle, in the image received from the imaging sensor, by processing said received image; determine an association between the radar map point and detected position of the target vehicle in the image by detecting a search region in the image; and confirm the obtained radar map point as the position of the target vehicle in the image based on computation of a threshold value.

Abstract: In an example, a computerized neural fabric is created by representing each pattern of learned weights of one or more machine learning algorithm-trained models specifying a specific set of products as a column in the computerized neural fabric, each pattern comprising one or more clusters representing combinations of convolutional filters, each cluster learning low level features and sending output via a vertical flow up the corresponding column to a final classification within the corresponding pattern. One or more potential lateral flows between patterns in the computerized neural fabrics is dynamically determined based on resemblance of a new product in a candidate image to the specific sets of products in each of the patterns and identifying possible mutations of the patterns based on the resemblance. Then, one of the one or more potential lateral flows is selected as a new model.

Abstract: In an example, a first machine learning algorithm is used to train a smart contour model to identify contours of product shapes in input images and to identify backgrounds in the input images. A second machine learning algorithm is used to train a plurality of shape-specific classification models to output identifications of products in input images. A candidate image of one or more products is obtained. The candidate image is passed to the smart contour model, obtaining output of one or more tags identifying product contours in the candidate image. The candidate image and the one or more tags are passed to an ultra-large scale multi-hierarchy classification system to identify one or more classification models for one or more individual product shapes in the candidate image. The one or more classification models are used to distinguish between one or more products and one or more unknown products in the image.

Abstract: In an example, a computerized neural fabric is created by representing each pattern of learned weights of one or more machine learning algorithm-trained models specifying a specific set of products as a column in the computerized neural fabric, each pattern comprising one or more clusters representing combinations of convolutional filters, each cluster learning low level features and sending output via a vertical flow up the corresponding column to a final classification within the corresponding pattern. One or more potential lateral flows between patterns in the computerized neural fabrics is dynamically determined based on resemblance of a new product in a candidate image to the specific sets of products in each of the patterns and identifying possible mutations of the patterns based on the resemblance. Then, one of the one or more potential lateral flows is selected as a new model.

Abstract: In an example, a first machine learning algorithm is used to train a smart contour model to identify contours of product shapes in input images and to identify backgrounds in the input images. A second machine learning algorithm is used to train a plurality of shape-specific classification models to output identifications of products in input images. A candidate image of one or more products is obtained. The candidate image is passed to the smart contour model, obtaining output of one or more tags identifying product contours in the candidate image. The candidate image and the one or more tags are passed to an ultra-large scale multi-hierarchy classification system to identify one or more classification models for one or more individual product shapes in the candidate image. The one or more classification models are used to distinguish between one or more products and one or more unknown products in the image.

Abstract: A vehicle drivetrain assembly having a clutch collar actuator mechanism. The clutch collar actuator mechanism may include an air bellow and a fork that may operatively connect an actuator rod to a clutch collar. The clutch collar actuator mechanism may actuate the clutch collar from a first position to a second position when the air bellow is inflated.

Abstract: Provided are techniques for the efficient distribution of peer zone databases in a FC Fabric. In an example, a switch instantiates a peer zone definition defining a peer zone in which two or more initiator host devices are each permitted to communicate with one or more target storage devices via the switched FC fabric and the two or more initiator host devices are prevented from communicating with each other. The switch stores the peer zone definition in a peer zone database at the FC switch, and distributes the peer zone definition to other FC switches of the switched FC fabric without performing a Fabric lock operation.

Abstract: Presented herein are priority route based techniques for mitigation of slow drain devices in a Fibre Channel (FC) fabric comprising a plurality of FC switches. In accordance with examples presented herein, a first FC switch in a FC fabric receives an indication that a first computing device attached to the FC fabric has entered a slow drain condition. The first FC switch is configured to prepare and install a priority route for packet flows directed to the first computing device.

Abstract: In one embodiment, a method for enabling communication between two network fiber channel (FC) switches, includes: receiving at least one protocol frame at a first network FC switch, the at least one protocol frame being received from a second network FC switch connected to the first network FC switch and comprising information related to a manufacturer of the second network FC switch; retrieving a first identifier of the second network FC switch from the at least one protocol frame, the first identifier comprising primary manufacturer information identifying a manufacturer of the second network FC switch; determining that the retrieved first identifier does not match one of a plurality of peer switch manufacturer identifiers stored in a memory of the first network FC switch, each of the plurality of peer switch manufacturer identifiers identifying peer switches for which one or more features may be enabled for communicating with the first network FC switch; retrieving a second identifier of the second network

Abstract: In one example embodiment, a time unconstrained fabric switch software upgrade function is described for an in-switch-software-upgrade/downgrade (ISSU) in a network switch. Prior to an ISSU, Hello protocol data unit (PDU) information is stored for relevant control protocols of associated interfaces of the switch. The Hello PDU information comprises information on messages and data exchanged by the control protocols that may be used to maintain communications links of the switch. During the configuring of the ISSU, and while the control plane of the switch is, at least partially, dysfunctional, Hello PDUs are sent on the interfaces according to the stored PDU information in order to maintain the communication links. The Hello PDU information may include a time interval value for each relevant protocol that determines when Hello PDUs are sent.

Abstract: Presented herein are techniques for collecting and delivering consolidated nameserver information in a merged Fiber (Fiber) Channel (FC) fabric. A principal switch in a merged FC fabric collects information from one or more subordinate switches. The principal switch consolidates the information collected from the subordinate switches to generate consolidated nameserver information. The principal switch then pushes the consolidated nameserver information from the principal switch to each of the subordinate switches.

Abstract: A vehicle drivetrain assembly having a clutch collar actuator mechanism. The clutch collar actuator mechanism may include an air bellow and a fork that may operatively connect an actuator rod to a clutch collar. The clutch collar actuator mechanism may actuate the clutch collar from a first position to a second position when the air bellow is inflated.