Abstract: An onboard communication network of a vehicle is monitored to detect a plurality of available messages that include respective cipher-based message authentication codes (CMAC) and that were identified as eligible messages based on having an information entropy greater than a specified threshold. A first message is selected from the plurality of available messages. The CMAC of the selected message is input into a random number generator that outputs a random number seeded by the CMAC of the selected message. Then the random number is provided.

Abstract: A vehicle communication network is monitored to detect a plurality of electronic control units (ECUs). Upon identifying a new ECU in the plurality of ECUs, a highest ECU trip counter is determined from the plurality of ECUs. A global trip counter stored in the memory is updated based on the highest ECU trip counter. The updated trip global trip counter is greater than the highest ECU trip counter. Then a replacement synchronization message is provided to the plurality of ECUs on the vehicle communication network. The replacement synchronization message includes the updated global trip counter.

Abstract: A system for a vehicle includes a computer, a first electronic control module, and a wired vehicle communications network coupling the computer and the first electronic control module. The computer is programmed to transmit authentication keys to the first electronic control module and a plurality of second electronic control modules via the wired vehicle communications network, encrypt a table of the authentication keys using a first key, store the encrypted table, transmit the encrypted table to the first electronic control module via the wired vehicle communications network, and transmit the encrypted table and the first key to a remote server spaced from the wired vehicle communications network.

Abstract: A system includes a control module and a local server. The server is programmed to transmit a command to perform an operation to a plurality of vehicles including a vehicle including the control module. The command including a digital signature that is common across the vehicles. The control module is programmed to receive a temporary value; receive the command; decrypt the digital signature in the command with the temporary value; upon verifying the decrypted digital signature, perform the operation; and upon a metric incrementing to a threshold value, prevent decryption of the digital signature with the temporary value.

Abstract: A computer includes a processor and a memory storing instructions executable by the processor to, upon receiving an authorization message, transmit a plurality of new authentication keys to a respective plurality of control modules, the memory including an expiration time for the authorization message; update a listing of the control modules with respective statuses of the transmissions of the respective new authentication keys to the respective control modules, wherein each status is one of successful or unsuccessful; upon at least one status being unsuccessful, prevent the authorization message from expiring at the expiration time; after preventing the authorization message from expiring, retransmit the respective new authentication keys to each control module for which the respective status is unsuccessful; and then expire the authorization message.

Abstract: Various implementations described herein generate training instances that each include corresponding training instance input that is based on corresponding sensor data of a corresponding autonomous vehicle, and that include corresponding training instance output that is based on corresponding sensor data of a corresponding additional vehicle, where the corresponding additional vehicle is captured at least in part by the corresponding sensor data of the corresponding autonomous vehicle. Various implementations train a machine learning model based on such training instances. Once trained, the machine learning model can enable processing, using the machine learning model, of sensor data from a given autonomous vehicle to predict one or more properties of a given additional vehicle that is captured at least in part by the sensor data.

Abstract: Techniques for using a trip flag to detect desynchronization of trip counter values in a vehicle system. Techniques include a first electronic control unit (ECU) receiving a synchronization message including a trip counter and receiving a message from a second ECU including a trip flag. The trip flag includes a single bit of data generated by the second ECU. The first ECU compares the trip flag to a last bit of the trip counter stored at the first electronic control unit and processes the message in response to the trip flag matching the trip counter. The first ECU compares the trip counter to a previous trip counter based on the trip flag differing from the trip counter. The first ECU processes the message using the previous trip counter or increments the trip counter to process the message based on the comparison with the previous trip counter.

Abstract: A fumarate salt, in particular the hemi-fumarate salt, of 5-((5-methyl-2-((3,4,5-trimethylphenyl)amino)pyrimidin-4-yl)amino)-benzo[d]oxazol-2(3H)-one (Compound (I), compositions comprising such a salt, and processes for the manufacture of such a salt, in particular Compound (I) hemi-fumarate salt are described. The salt is useful for the treatment of conditions such as asthma and COPD, involving modulation of the JAK pathway or inhibition of JAK kinases particularly JAK1.

Abstract: A temperature sensor and temperature sensing system for sensing changes in temperature up to a predetermined temperature is disclosed. The temperature sensor includes a microstructured optical fiber where the microstructured optical fiber includes a plurality of longitudinal channels extending along the microstructured optical fiber. The sensor also includes a fiber Bragg grating formed in the microstructured optical, fiber by generating a periodic modulation in the refractive index along a core region of the microstructured optical fiber. The fiber Bragg grating is operable to produce band reflection at a reflection wavelength that varies in accordance with changes in temperature at the core region of the optical fiber.

Abstract: Determining yaw parameter(s) (e.g., at least one yaw rate) of an additional vehicle that is in addition to a vehicle being autonomously controlled, and adapting autonomous control of the vehicle based on the determined yaw parameter(s) of the additional vehicle. For example, autonomous steering, acceleration, and/or deceleration of the vehicle can be adapted based on a determined yaw rate of the additional vehicle. In many implementations, the yaw parameter(s) of the additional vehicle are determined based on data from a phase coherent Light Detection and Ranging (LIDAR) component of the vehicle, such as a phase coherent LIDAR monopulse component and/or a frequency-modulated continuous wave (FMCW) LIDAR component.

Abstract: A method includes obtaining a first track associated with a first time. A first track associated with a first time is obtained. First predicted state data associated with a second time that is later than the first time, are generated based on the first track. Radar measurement data associated with the second time are obtained from one or more radar sensors. Track data are generated by a machine learning model based on the first predicted state data and the radar measurement data. Second predicted state data associated with the second time are generated based on the first track. A second track associated with the second time is generated based on the track data and the second predicted state data. The second track associated with the second time is provided to an autonomous vehicle control system for autonomous control of a vehicle.

Abstract: Determining yaw parameter(s) (e.g., at least one yaw rate) of an additional vehicle that is in addition to a vehicle being autonomously controlled, and adapting autonomous control of the vehicle based on the determined yaw parameter(s) of the additional vehicle. For example, autonomous steering, acceleration, and/or deceleration of the vehicle can be adapted based on a determined yaw rate of the additional vehicle. In many implementations, the yaw parameter(s) of the additional vehicle are determined based on data from a phase coherent Light Detection and Ranging (LIDAR) component of the vehicle, such as a phase coherent LIDAR monopulse component and/or a frequency-modulated continuous wave (FMCW) LIDAR component.

Abstract: Various implementations described herein generate training instances that each include corresponding training instance input that is based on corresponding sensor data of a corresponding autonomous vehicle, and that include corresponding training instance output that is based on corresponding sensor data of a corresponding additional vehicle, where the corresponding additional vehicle is captured at least in part by the corresponding sensor data of the corresponding autonomous vehicle. Various implementations train a machine learning model based on such training instances. Once trained, the machine learning model can enable processing, using the machine learning model, of sensor data from a given autonomous vehicle to predict one or more properties of a given additional vehicle that is captured at least in part by the sensor data.

Abstract: A portable device for cleaning golf balls and golf clubs is provided. The device may include a hollow, impermeable housing and an impermeable lid. Situated on the lid beneath the lid inner surface is a plunger with a saddle in which to rest a golf ball. The device also contains a plurality of cleaning mechanisms disposed within an inner cavity of the housing and arranged to form a channel, so that when a user submerges and reciprocates the plunger, the golf balls are cleaned. The device may further include a spray nozzle to dispense cleaning solution onto golf clubs. A tee holder, divot fixer holder, and towel holder may also be coupled to the exterior of the housing. The device is preferably sized and shaped to be disposed within or coupled to a golf bag or golf cart.

Abstract: A method includes obtaining a first track associated with a first time. A first track associated with a first time is obtained. First predicted state data associated with a second time that is later than the first time, are generated based on the first track. Radar measurement data associated with the second time are obtained from one or more radar sensors. Track data are generated by a machine learning model based on the first predicted state data and the radar measurement data. Second predicted state data associated with the second time are generated based on the first track. A second track associated with the second time is generated based on the track data and the second predicted state data. The second track associated with the second time is provided to an autonomous vehicle control system for autonomous control of a vehicle.

Abstract: Various implementations described herein generate training instances that each include corresponding training instance input that is based on corresponding sensor data of a corresponding autonomous vehicle, and that include corresponding training instance output that is based on corresponding sensor data of a corresponding additional vehicle, where the corresponding additional vehicle is captured at least in part by the corresponding sensor data of the corresponding autonomous vehicle. Various implementations train a machine learning model based on such training instances. Once trained, the machine learning model can enable processing, using the machine learning model, of sensor data from a given autonomous vehicle to predict one or more properties of a given additional vehicle that is captured at least in part by the sensor data.

Abstract: A vehicle control system includes a set of radars, with each radar of the set including a depth setting which controls a corresponding range of the radar. The corresponding range of at least one radar may be adjusted based on contextual information, as determined by the vehicle when the vehicle is in use.

Abstract: Determining classification(s) for object(s) in an environment of autonomous vehicle, and controlling the vehicle based on the determined classification(s). For example, autonomous steering, acceleration, and/or deceleration of the vehicle can be controlled based on determined pose(s) and/or classification(s) for objects in the environment. The control can be based on the pose(s) and/or classification(s) directly, and/or based on movement parameter(s), for the object(s), determined based on the pose(s) and/or classification(s). In many implementations, pose(s) and/or classification(s) of environmental object(s) are determined based on data from a phase coherent Light Detection and Ranging (LIDAR) component of the vehicle, such as a phase coherent LIDAR monopulse component and/or a frequency-modulated continuous wave (FMCW) LIDAR component.

Abstract: Determining yaw parameter(s) (e.g., at least one yaw rate) of an additional vehicle that is in addition to a vehicle being autonomously controlled, and adapting autonomous control of the vehicle based on the determined yaw parameter(s) of the additional vehicle. For example, autonomous steering, acceleration, and/or deceleration of the vehicle can be adapted based on a determined yaw rate of the additional vehicle. In many implementations, the yaw parameter(s) of the additional vehicle are determined based on data from a phase coherent Light Detection and Ranging (LIDAR) component of the vehicle, such as a phase coherent LIDAR monopulse component and/or a frequency-modulated continuous wave (FMCW) LIDAR component.

Abstract: Various implementations described herein generate training instances that each include corresponding training instance input that is based on corresponding sensor data of a corresponding autonomous vehicle, and that include corresponding training instance output that is based on corresponding sensor data of a corresponding additional vehicle, where the corresponding additional vehicle is captured at least in part by the corresponding sensor data of the corresponding autonomous vehicle. Various implementations train a machine learning model based on such training instances. Once trained, the machine learning model can enable processing, using the machine learning model, of sensor data from a given autonomous vehicle to predict one or more properties of a given additional vehicle that is captured at least in part by the sensor data.