Abstract: An interchangeable electro-mechanical lock core for use with a lock device having a locked state and an unlocked state is disclosed. The interchangeable electromechanical lock core may include a moveable plug having a first position relative to a lock core body which corresponds to the lock device being in the locked state and a second position relative to a lock core body which corresponds to the lock device being in the unlocked state.

Abstract: The invention relates generally to antibodies, activatable antibodies, multispecific antibodies, and multispecific activatable antibodies that specifically bind to at least CD3, as well as to methods of making and using these antibodies, activatable antibodies, multispecific antibodies, and/or multispecific activatable antibodies in a variety of therapeutic, diagnostic and prophylactic indications.

Abstract: A method for a serial protocol-based event trigger includes detecting a condition of a Device Under Test (DUT) with a first text pattern, wherein the condition indicates an enabled function of the DUT. A command is transmitted to the DUT to perform a first action with the enabled function in response to detecting the condition of the DUT. A second text pattern received from the DUT is detected in response to the first action. The second text pattern indicates a successful completion of an event by the enabled function. A second action is performed in response to detecting the second text pattern.

Abstract: A method of installing a sensor pod on a vehicle includes aligning a sensor pod arm with a bracket attached to the vehicle, lowering the sensor pod arm onto the bracket, supporting the weight of the sensor pod on a support axle between the bracket and the sensor pod arm before rigidly coupling the sensor pod arm to the bracket, rotating the sensor pod arm into alignment with the bracket, and securing the sensor pod arm to the bracket. A method of uninstalling the sensor pod on a vehicle.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a simulation of an environment that is being interacted with by a plurality of agents over a plurality of time steps, wherein the simulation comprises a respective simulation state for each time step that specifies a respective state of each agent at the time step. In one aspect, a method comprises, for each time step: obtaining a current simulation state for the current time step; generating a plurality of candidate next simulation states for a next time step; determining, for each candidate next simulation state, a discriminative score characterizing a likelihood that the candidate next simulation state is a realistic simulation state; and selecting a candidate next simulation state as the simulation state for the next time step based on the discriminative scores for the candidate next simulation states.

Abstract: A universal bracket for connecting a sensor pod and a vehicle. The universal bracket includes a first end having a surface for connecting to the vehicle, a second end for connecting to the sensor pod, three fixation points extending perpendicular to and through the surface for preventing lateral movement, vertical movement, and forward movement of the universal bracket with respect to the vehicle, the three fixation further preventing rotational movement of the universal bracket with respect to the vehicle, and at least one port extending from the first end to the second end, the at least one port configured to allow passage of one or more conduits extending from the vehicle to the sensor pod. A connecting assembly includes the universal bracket.

Abstract: A connecting assembly for connecting sensors in a sensor pod to a vehicle. The connecting assembly has a conduit connector located on a housing of the sensor pod, a conduit configured to connect with the conduit connector and extending from the conduit connector to the vehicle, and a conduit connector point located at a connection between the conduit connector and the conduit. The conduit connector point has a first shear strength when the conduit is in tension and the conduit has a second shear strength when the conduit is in tension. The first shear strength is less than the second shear strength.

Abstract: An apparatus for reducing damage and debris in a sensor pod collision. The apparatus having a bracket configured to couple a sensor pod to a vehicle, the bracket having a post, a sensor pod arm rotatable about the post, a fastener for securing the sensor pod arm to the post, and a frangible fixation point spaced apart from the post, the frangible fixation point configured to break apart at a predetermined force.

Abstract: A quick swap sensor pod for a truck having an arm having a protrusion with a lower surface, a pin receiving opening extending through the protrusion to the lower surface, the pin receiving opening having a depth and aligned vertically, and a conduit connector within the arm for coupling a conduit to the quick swap sensor pod. The arm is configured to rotate about an axis of the pin receiving opening between an initial position and a final position. In both the initial position and the final position, the depth of the pin receiving opening is configured to counteract a moment created by a weight of the quick swap sensor pod and the lower surface is configured to support the weight of the quick swap sensor pod.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a simulation of an environment that is being interacted with by a plurality of agents over a plurality of time steps, wherein the simulation comprises a respective simulation state for each time step that specifies a respective state of each agent at the time step. In one aspect, a method comprises, for each time step: obtaining a current simulation state for the current time step; generating a plurality of candidate next simulation states for a next time step; determining, for each candidate next simulation state, a discriminative score characterizing a likelihood that the candidate next simulation state is a realistic simulation state; and selecting a candidate next simulation state as the simulation state for the next time step based on the discriminative scores for the candidate next simulation states.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating simulated trajectories using parallel beam search.

Abstract: In one embodiment, a computing system may receive an uncompressed image from a camera. The computing system may generate a compressed image by performing a compression process on the uncompressed image, wherein a decompressed image may be generated as a byproduct during the compression process. The computing system may send the decompressed image to a machine-learning model that was trained using decompressed images. The computing system may generate, by the machine-learning model, an output based on the decompressed image. The computing system may provide operational instructions to a vehicle based on the output.

Abstract: Systems and methods for performing low voltage charging of a high voltage, series-connected string of battery modules are disclosed. A battery pack system may include a plurality of battery cells, including one or more groups of battery cells coupled in parallel. A processor may be configured to select a sub-group of battery cells from a group of battery cells for charging separately from other battery cells of the selected group of battery cells. The group of battery cells may be reconfigured to allow charging of the sub-group of battery cells separate from the other battery cells. The sub-group of battery cells may be charged, and then the group of battery cells may be reconfigured to allow operation of the sub-group of battery cells with the other battery cells. During charging, the sub-group of battery cells may be unavailable but other battery cells may continue to discharge.

Abstract: Methods, computer systems, and apparatus, including computer programs encoded on computer storage media, for generating a prediction that characterizes an environment. The system obtains an input including data characterizing observed trajectories one or more agents and data characterizing one or more map features identified in a map of the environment. The system generates, from the input, an encoder input that comprises representations for each of a plurality of points in a top-down representation of the environment. The system processes the encoder input using a point cloud encoder neural network to generate a global feature map of the environment, and processes a prediction input including the global feature map using a predictor neural network to generate a prediction output characterizing the environment.

Abstract: A jetted bag opener separates mixed solid waste from flexible containers such as plastic and paper bags, and includes a housing configured with an ingress and an egress, at least two sets of a plurality of fluid delivery nozzles, where a first set of the nozzles is arranged along a sidewall at a first side of the housing, and a second set of the nozzles is arranged along the sidewall at a second side of the housing opposite the first side, and as fluid is sprayed from the nozzle outlets, the fluid is delivered at a force sufficient to penetrate into the flexible containers passing through the housing to thereby create an opening in the flexible containers for release of the mixed solid waste held therein.

Abstract: In one embodiment, a method includes, by a computing device of a first sensor receiving synchronization information from a controller. The synchronization information being generated based on a clock of the controller. The method also includes determining, based on the synchronization information, a first offset between a first clock of the first sensor and the clock of the controller; storing the first offset; and synchronizing, based on the stored first offset and the first clock of the first sensor, a first data capture by the first sensor with a second data capture by a second sensor. The first data capture and the second data capture being requested by the controller.

Abstract: In one embodiment, a computing system receives sensor data from one or more sensors of a vehicle. The computing system determines a metric associated with the vehicle based on the received sensor data. The computing system determines, based on the metric, a length of a transmission cycle of a communication network of the vehicle. The transmission cycle comprises one or more scheduled time periods dedicated for transmitting data from respective first nodes in the communication network. The computing system configures the communication network of the vehicle based at least in part on the length of the transmission cycle to adjust respective occurrence frequencies of the scheduled time periods over multiple instances of the transmission cycle.

Abstract: In particular embodiments, a computing system may detect a number of objects captured within an overlapping region between a first field of view associated with a first camera and a second field of view associated with a second camera. The system may determine a respective priority ranking for each of the objects. The system may select an object from the objects based on the respective priority ranking for the object. The system may determine, for the first camera, a first lighting condition associated with the first field of view. The system may determine, for the second camera, a second lighting condition associated with the second field of view. The system may determine a shared exposure time for the selected object based on the first lighting condition and the second lighting condition. The system may cause at least one image of the selected object to be captured using the shared exposure time.

Abstract: In one embodiment, a method includes, by a computing device of a first sensor receiving synchronization information from a controller. The synchronization information being generated based on a clock of the controller. The method also includes determining, based on the synchronization information, a first offset between a first clock of the first sensor and the clock of the controller; storing the first offset; and synchronizing, based on the stored first offset and the first clock of the first sensor, a first data capture by the first sensor with a second data capture by a second sensor. The first data capture and the second data capture being requested by the controller.

Abstract: In one embodiment, a method includes receiving data from one or more sensors associated with a vehicle; and receiving a message from a first processor. The message from the first processor includes a first control command for an actuator of the vehicle and a first certificate function. The method also includes receiving a message from the second processor. The message from the second processor includes a second control command for the actuator of the vehicle and a second certificate function. The method also includes computing a first certificate based on the first certificate function and the data; computing a second certificate based on the second certificate function and the data; determining a valid control signal based on an accuracy of the first second control command and second control command relative the first certificate and second certificate; and transmitting the valid control signal to the actuator of the vehicle.