Abstract: The methods and systems herein enable relative movement-based seatbelt use detection. Image data of an occupant of a vehicle is received over time. The image data is then input into a machine-learned model or other module that determines whether relative movement between one or more portions of the occupant and corresponding portions of a seatbelt are less than a threshold amount. If the relative movement is less than the threshold amount, an indication of seatbelt misuse (e.g., a fake seatbelt) is output to a vehicle component. By basing the indication of seatbelt misuse on relative movement between the occupant and the seatbelt, seatbelt use detection may be improved.

Abstract: A vehicle restart control apparatus includes a processor configured to generate an override torque according to the environment information of the host vehicle when the vehicle is restarted after stopping; and a storage configured to store data and algorithms driven by the processor.

Abstract: Operating a gaseous fuel engine includes spark-igniting gaseous hydrogen fuel and air, and propagating combustion gases of the spark-ignited mixture outwardly from a spark gap. The propagating combustion gases are impinged upon a cone surface of a piston so as to limit a flame area of the propagating combustion gases. Additional gaseous hydrogen fuel and air is ignited in the combustion cylinder by way of the propagating combustion gases to urge a piston toward a bottom-dead-center position.

Abstract: Systems, methods, and apparatus are provided for providing multi-trailer reverse assistance. In a multi-trailer reverse assistance system in an articulated transport system comprising a lead vehicle, an intermediate trailer, and a final trailer, the reverse assist system includes a controller. The controller is configured to: receive a view of an environment behind the final trailer; cause the view to be displayed in a display screen of a user interface device; receive, via a secondary steering device of the user interface device, a user intended direction of travel of the articulated transport system in reverse to direct the final trailer in a desired direction; continuously calculate controllable steering angles for directing the articulated transport system to direct the final trailer in the desired direction; and control the articulated transport system to direct the final trailer in the desired direction using the calculated controllable steering angles.

Abstract: A system for grading filling of a suspension system includes: a pump control module configured to, during first and second periods, operate an electric pump of the suspension system in first and second directions and decreasing and increasing hydraulic fluid pressure within the suspension system, respectively; a monitoring module configured to: store a first pressure of hydraulic fluid within the suspension system measured using a pressure sensor when the first pressure is less than or equal a first predetermined pressure while the pump is operated in the first direction; and store a second pressure measured using the pressure sensor when the second pressure is greater than or equal a second predetermined pressure while the pump is operated in the second direction; and a grade module configured to determine a grade value for the filling of the suspension system based on the first and second pressures.

Abstract: An internal combustion engine includes multiple fuel injections external to a pre-chamber. A further aspect provides an engine pre-chamber ignition apparatus which employs a pre-assembled and/or removable cartridge including an ignitor and a fresh air inlet but not a fuel inlet injector directly mounted thereto. Another aspect of a vehicular engine apparatus includes a fuel injector positioned externally to a pre-chamber which delivers an initial greater quantity of fuel for combustion and then a later and smaller quantity of fuel for pre-chamber ignition.

Abstract: A fuel vapor recirculation system includes a filler neck adapted to receive a refueling nozzle that dispenses fuel into the filler neck. A fuel tank receives fuel from the filler neck through an inlet check valve. The check valve is disposed in the fuel inlet opening and is normally closed. The check valve opens when fuel is dispensed into the fuel tank. The check valve defines a vent hole that is always open. The fuel tank also includes a fuel limiting vent valve and a grade limit vent valve. A fuel vapor cannister collects fuel vapor and selectively supplies fuel vapor to an intake manifold of a vehicle. The fuel vapor recirculation manifold receives fuel vapor only from the fuel limiting vent valve and the grade limit vent valve in the fuel tank and does not receive fuel vapor directly from the filler neck.

Abstract: A method is provided that may include receiving a global navigation satellite system (GNSS) signal for a moving vehicle and obtaining a position estimation of the vehicle by inputting values of observable characteristics into an artificial intelligence (AI)-based model and receiving the position estimation as an output from the AI-based model. The AI-based model applies different coefficients to the values of the observable characteristics to output the position estimation. The method may also include calculating an error between a location derived from the GNSS signal that may be received and the position estimation obtained from the AI-based model, and changing one or more of the coefficients applied to the observable characteristics in the AI-based model based on the error that is calculated.

Abstract: A diagnostic device is configured to execute a first acquisition process of acquiring a remaining amount of evaporated fuel in a fuel tank when an ignition switch turns off, as an end remaining amount, a determination process of, after the first acquisition process, determining whether there is a blockage of a vapor passage by reducing a pressure in a vapor passage with a pressure reducing pump when the end remaining amount is smaller than a prescribed value while the ignition switch is off, a second acquisition process of, after the determination process, acquiring a remaining amount of liquid fuel in the fuel tank when the ignition switch turns on, as a start remaining amount, and an invalidation process of invalidating a determination result that a blockage is present in the vapor passage in the determination process when the start remaining amount is larger than or equal to a set value.

Abstract: A system for predicting a negative pressure of a brake booster of a vehicle includes: a driving information detector configured to detect driving information according to driving of the vehicle; and a controller configured to calculate a negative pressure of an intake manifold based on a pressure of the intake manifold and an atmospheric pressure that is the driving information and including a booster negative pressure predictor configured to predict the negative pressure of the brake booster by integrating over time a change rate according to a charging rate and a discharging rate of the negative pressure calculated using a previous negative pressure of the brake booster calculated in a previous cycle according to a logic for predicting the negative pressure of the brake booster and the negative pressure of the intake manifold and a brake pedal force of a current cycle.

Abstract: An electric suspension control, in a vehicle including an electric suspension apparatus driven with a motor, short-circuits the motor and limits a vehicle speed to a predetermined speed or less, in a case where an abnormality occurs in the electric suspension apparatus.

Abstract: A system for preventing an engine included in a work machine from restarting, after the work machine is tipped over. A sensor included in the work machine is configured to detect a tipping incident. If a tipping incident is detected, the sensor sends out a signal configured to shut down the engine and a tilt signal configured to prevent the engine from restarting. The engine is only restarted if certain steps are undertaken by an operator and a reset switch is activated.

Abstract: A fuel supply device includes a main body, fuel chamber, fuel supply pipe and a fuel valve. The main body has a main bore with an inlet for air and an outlet through which a fuel and air mixture flows. The fuel chamber retains a supply of fuel. The fuel supply pipe has a passage communicating with the main bore and through which fuel from the fuel chamber flows to the main bore. And the fuel valve has a valve seat, a valve element movable relative to the valve seat between an open position and a closed position, an inlet upstream of the valve seat and is in communication with the fuel chamber, and an outlet downstream of the valve seat. The outlet is coaxially aligned with the passage of the fuel supply pipe and the fuel valve is electrically operated to move the valve element.

Abstract: An example operation includes one or more of determining, by sensors on a transport, a slope of a road and a surface condition of the road and engaging one or more wheels of the transport, based on the slope, the surface condition, and a characteristic of the one or more wheels. Engaging includes braking to the one or more wheels at a different rate as the transport is moving on the road.

Abstract: Neural networks, in many cases, include convolution layers that are configured to perform many convolution operations that require multiplication and addition operations. Compared with performing multiplication on integer, fixed-point, or floating-point format values, performing multiplication on logarithmic format values is straightforward and energy efficient as the exponents are simply added. However, performing addition on logarithmic format values is more complex. Conventionally, addition is performed by converting the logarithmic format values to integers, computing the sum, and then converting the sum back into the logarithmic format. Instead, logarithmic format values may be added by decomposing the exponents into separate quotient and remainder components, sorting the quotient components based on the remainder components, summing the sorted quotient components to produce partial sums, and multiplying the partial sums by the remainder components to produce a sum.

Abstract: A method for controlling a passenger restraint system aboard a motor vehicle includes receiving, via a controller, biometric vulnerability classifier signal(s) indicative of vulnerability characteristics of a passenger seated in an interior of the motor vehicle. In response to the biometric vulnerability classifier signal(s) and a detected vehicle event requiring an actuation of the passenger restraint system, the method includes automatically adjusting an actual capacity setting of the passenger restraint system via the controller. A motor vehicle includes a vehicle body defining a vehicle interior, a passenger restraint system positioned in the vehicle interior; and a controller operable for controlling the actual capacity setting of the passenger restraint system in accordance with the method. The passenger restraint system may include a seatbelt, a seat, and one or more airbag systems.

Abstract: A vapor canister for a vehicle evaporative emissions control system comprises a canister housing defining an internal volume for receiving therein one or more volumes of adsorbent; a fuel vapor inlet port for connecting the canister to a fuel tank; a vent port for intake of fresh air into the canister; a purge port for withdrawing fuel vapors from the canister; and a pump integrated with the canister housing. The integrated pump is actuated to provide an overpressure or underpressure in the canister. The integrated pump can be used for various operating modes, such as e.g. canister purging, leak detection diagnostic, refueling or engine shut down.

Abstract: An internal combustion engine with controlled ignition comprises a cylinder, a relative piston, and a head between which a combustion chamber is operationally defined. The cylinder and the piston define a first prismatic coupling. The engine also comprises a pre-chamber made directly inside the combustion chamber, and a male element stably connected to an upper surface of the piston to penetrate the pre-chamber at least in one portion of the relative motion of the piston in the cylinder. A spark plug is arranged to look out into the pre-chamber.

Abstract: Some embodiments provide a compiler for optimizing the implementation of a machine-trained network (e.g., a neural network) on an integrated circuit (IC). The compiler of some embodiments receives a specification of a machine-trained network including multiple layers of computation nodes and generates a graph representing options for implementing the machine-trained network in the IC. In some embodiments, the graph includes nodes representing options for implementing each layer of the machine-trained network and edges between nodes for different layers representing different implementations that are compatible. The graph is used, in some embodiments, to select an optimum set of cores for implementing the received machine-trained network. The compiler, in some embodiments, optimizes memory storage such that input and output layers of a single layer are not stored in a same memory unit.

Abstract: A vehicle control device includes: a shift-position-switching acceptance unit that accepts switching operation of the shift position of the transmission but does not accept switching operation from a shift position other than the first forward position and the second forward position to the second forward position without via the first forward position; and an automatic-parking control unit that, in a case of moving the vehicle forward during execution of automatic parking control in a state in which the shift position of the transmission is set at a shift position other than the first forward position and the second forward position, sets the shift position of the transmission to the first forward position to move the vehicle forward.