Abstract: Systems and techniques are provided for synchronizing sensor operations. An example method includes determining a frequency of each scan cycle of a sensor configured to scan different regions of space; based on the frequency, a field-of-view (FOV) of the sensor, and a FOV of an additional sensor, determining an amount of time between a state of a first scan cycle of the sensor in which a point within the FOV of the sensor is aligned with a point within the FOV of the additional sensor and a state of a second scan cycle in which the point within the FOV of the sensor is aligned with the point within the FOV of the additional sensor; determining a time offset based on the amount of time; and sending, to the additional sensor, a signal configured to trigger the additional sensor to capture data at/after time intervals defined by the time offset.

Abstract: The handling of external calls from one or more services to one or more subservices is described. Upon detecting that a service has made an external call to a subservice and prior to allowing the external call to be sent to the subservice, a system evaluates the external call against one or more pre-call thresholds to determine whether or not the one or more pre-call thresholds are met. If the determination is that a pre-call threshold of the one or more pre-call thresholds is not met, the external call is failed without sending the external call to the subservice. This failing might include communicating to the service that placed the external call that the external call has failed. Otherwise, the system sends the external call to the subservice. By applying these thresholds, the service is kept from using too many resources.

Abstract: System and method are disclosed for training a generative adversarial network pipeline that can produce realistic artificial depth images useful as training data for deep learning networks used for robotic tasks. A generator network receives a random noise vector and a computer aided design (CAD) generated depth image and generates an artificial depth image. A discriminator network receives either the artificial depth image or a real depth image in alternation, and outputs a predicted label indicating a discriminator decision as to whether the input is the real depth image or the artificial depth image. Training of the generator network is performed in tandem with the discriminator network as a generative adversarial network. A generator network cost function minimizes correctly predicted labels, and a discriminator cost function maximizes correctly predicted labels.

Abstract: An offline authentication of batteries includes communicating an encrypted authentication request to secondary batteries and a vehicle controller by a primary battery of an electric vehicle. The encrypted authentication request is decrypted to obtain a first random number and a fleet flag. An encrypted authentication response, including a first random number, a second random number, and a vehicle identifier, is communicated to each battery. Each battery verifies the first random number and the vehicle identifier. An encrypted battery status, including the first and second random numbers and an authentication status, is communicated to the primary battery that verifies the first and second random number and the authentication status. The primary battery communicates an encrypted authentication message to the secondary batteries and the vehicle controller. The secondary batteries and the vehicle controller verify the first and second random numbers and the authentication status for authenticating each battery.

Abstract: Generation of an autonomy map for assisting an autonomous vehicle includes extracting the historical autonomy information associated one or more route segments of one or more routes. An autonomy level for each route segment is determined based on the extracted historical autonomy information. A digital autonomy map is generated including each route segment of at least one route such that each route segment is tagged with the determined autonomy level. The autonomy level of each route segment is dynamically updated in real-time for providing real-time driving assistance to the autonomous vehicle.

Abstract: A universal asynchronous receiver/transmitter includes a transmission register to include information to be transmitted, a receive register to include information received, a frame error checking circuit to evaluate contents of the receive register for a frame error, and control logic. The control logic is to route the contents of the transmission register to the receive register. The control logic is to, during transmission of the contents of the transmission register through the reprogrammable pin to the receive register, modify a bit inversion register to yield modified contents to be provided to the receive register. The modified contents are to cause a frame error. The control logic is to determine whether the frame error checking circuit detected the frame error.

Abstract: Methods, apparatuses, and systems for controlling regenerative braking of a vehicle are disclosed. A user interface facilitates a user to provide an input to select an operating mode for the vehicle, the operating mode selected from one of selectable modes comprising: (i) manually controlled regenerative braking mode and (ii) automatically controlled regenerative braking mode. When the (i) mode is selected, the controller applies a scaling factor to the regenerative torque capability curve of the vehicle based on additional user input. When the (ii) mode is selected, the controller automatically applies the scaling factor based on one or more traction control events and environmental factors.

Abstract: An autonomous system can detect out-of-distribution (OOD) data in robotic grasping systems, based on evaluating image inputs of the robotic grasping systems. Furthermore, the system makes various decisions based on detecting the OOD data, so as to avoid inefficient or hazardous situations or other negative consequences (e.g., damage to products). For example, the system can determine whether a suction-based gripper is optimal for grasping objects in a given scene, based at least in part on determining whether an image defines OOD data.

Abstract: Fully flexible kitting processes can be automated by generating pick and place motions for multi-robot, multi-gripper, robotic systems.

Abstract: In some cases, grasp point algorithms can be implemented so as to compute grasp points on an object that enable a stable grasp. It is recognized herein, however, that in practice a robot in motion can drop the object or otherwise have grasp issues when the object is grasped at the computed stable grasp points. Path constraints that can differ based on a given object are generated while generating the trajectory for a robot, so as to ensure that a grasp remains stable throughout the motion of the robot.

Abstract: A charge system and corresponding method for maintaining an available state-of-charge above a predetermined threshold during an extended charging session and/or restarting a charging session if said charging session terminates and the resulting available state-of-charge remains below the predetermined threshold. Additionally, a charge system and corresponding method for tracking metrics of a charge session to allow for accessibility in reviewing and/or troubleshooting charging session-related events.

Abstract: A covariate shift generally refers to the change of the distribution of the input data (e.g., noise distribution) between the training and inference regimes. Such covariate shifts can degrade the performance grasping neural networks, and thus robotic grasping operations. As described herein, an output of a grasp neural network can be transformed, so as to determine appropriate locations on a given object for a robot or autonomous machine to grasp.

Abstract: A control system for controlling a powertrain of an electric or hybrid electric vehicle is disclosed. The powertrain comprises a battery and a traction motor and is operable in a regenerative braking mode. The control system is configured to generate a deceleration target for the vehicle in the regenerative braking mode, and to generate a torque command for the traction motor based on the deceleration target. By generating a deceleration target for the vehicle during regenerative braking and using the deceleration target to control the torque of the traction motor, more consistent regenerative braking may be provided, particularly when the vehicle is used to carry different loads.

Abstract: Robots might interact with planar objects (e.g., garments) for process automation, quality control, to perform sewing operations, or the like. It is recognized herein that robots interacting with such planar objects can pose particular problems, for instance problems related to detecting the planar object and estimating the pose of the detected planar object. A system can be configured to detect or segment planar objects, such as garments. The system can include a three-dimensional (3D) sensor positioned to detect a planar object along a transverse direction. The system can further include a first surface that supports the planar object. The first surface can be positioned such that the planar object is disposed between the first surface and the 3D sensor along the transverse direction. In various examples, the 3D sensor is configured to detect the planar object without detecting the first surface.

Abstract: The handling of external calls from one or more services to one or more subservices is described. Upon detecting that a service has made an external call to a subservice and prior to allowing the external call to be sent to the subservice, a system evaluates the external call against one or more pre-call thresholds to determine whether or not the one or more pre-call thresholds are met. If the determination is that a pre-call threshold of the one or more pre-call thresholds is not met, the external call is failed without sending the external call to the subservice. This failing might include communicating to the service that placed the external call that the external call has failed. Otherwise, the system sends the external call to the subservice. By applying these thresholds, the service is kept from using too many resources.

Abstract: A universal asynchronous receiver/transmitter includes a transmission register to include information to be transmitted, a receive register to include information received, a frame error checking circuit to evaluate contents of the receive register for a frame error, and control logic. The control logic is to route the contents of the transmission register to the receive register. The control logic is to, during transmission of the contents of the transmission register through the reprogrammable pin to the receive register, modify a bit inversion register to yield modified contents to be provided to the receive register. The modified contents are to cause a frame error. The control logic is to determine whether the frame error checking circuit detected the frame error.

Abstract: Systems and methods are provided for receiving data indicating a spatial distribution and 802.11ax capabilities of access point radios and of client devices in a network, assigning the access point radios as either first access point radios or second access point radios, the first access point radios conducting data transmission using an 802.11ax wireless standard and the second access point radios conducting data transmission using legacy wireless standards, based on the data, determining whether any of the client devices are to be steered to a different access point radio based on the 802.11ax capabilities of the client devices, and in response to determining that a client device is to be steered to a different access point radio, steering the client device to a first access point radio or a second access point radio.

Abstract: An architecture for training the weights of artificial neural networks provides a global constrainer modifying the neuron weights in each iteration not only by the back-propagated error but also by a global constraint constraining these weights based on the value of all weights at that iteration. The ability to accommodate a global constraint is made practical by using a constrained gradient descent which approximates the error gradient deduced in the training as a plane, offsetting the increased complexity of the global constraint.

Abstract: A method for automatically generating a bill of process in a manufacturing system comprising: receiving design information representative of a product to be produced; iteratively performing simulations of the manufacturing system; identifying manufacturing actions based on the simulations; optimizing the identified manufacturing actions to efficiently produce the product to be produced; generating, by the manufacturing system, a bill of process for producing the product. Simulations may be performed using a digital twin of the product being produced and a digital twin of the environment. System actions are optimized using a reinforcement learning technique to automatically produce a bill of process based on the design information of the product and task specifications.

Abstract: Systems and methods are provided for receiving data indicating a spatial distribution and 802.11ax capabilities of access point radios and of client devices in a network, assigning the access point radios as either first access point radios or second access point radios, the first access point radios conducting data transmission using an 802.11ax wireless standard and the second access point radios conducting data transmission using legacy wireless standards, based on the data, determining whether any of the client devices are to be steered to a different access point radio based on the 802.11ax capabilities of the client devices, and in response to determining that a client device is to be steered to a different access point radio, steering the client device to a first access point radio or a second access point radio.