Abstract: Tracking a current and/or previous position, velocity, acceleration, and/or heading of an object using sensor data may comprise determining whether to associate a current object detection generated from recently received (e.g., current) sensor data with a previous object detection generated from formerly received sensor data. In other words, a track may identify that an object detected in former sensor data is the same object detected in current sensor data. However, multiple types of sensor data may be used to detect objects and some objects may not be detected by different sensor types or may be detected differently, which may confound attempts to track an object. An ML model may be trained to receive outputs associated with different sensor types and/or a track associated with an object, and determine a data structure comprising a region of interest, object classification, and/or a pose associated with the object.

Abstract: Aspects of the invention relate to a method comprising: determining an output torque at a wheel of a vehicle mounted to a test apparatus comprising an external motor, the output torque being in response to a command; determining a correction factor based on the output torque and at least one coefficient associated with a reaction of a component of the vehicle and/or of the test apparatus to an applied torque at the vehicle; and controlling the external motor to apply the correction factor to the wheel of the vehicle.

Abstract: A thermal management assembly may implement cooling techniques to cool at least a portion of a computer system with one or more cooling systems. The techniques may include using a thermal management assembly in fluid communication with the cooling system(s) to supply fluid from at least one of the cooling systems to at least a portion of the computer system. The techniques may also or instead include using a first thermal coupling to transfer thermal energy between the first cooling system and the computer system and a second thermal coupling to transfer thermal energy between the second cooling system and the computer system. Cooling a computer system using the cooling techniques described herein lowers an operating temperature of the computer system thereby mitigating heat related computer failure.

Abstract: A method for operating a fleet of vehicles may include determining a first set of parameters for operating a first vehicle as it travels to a destination, and determining a second set of parameters for operating a second vehicle. Consumption of the first set of parameters by the first vehicle may cause the first vehicle to accelerate, alter shocks and/or suspensions, and/or move into a free lane. Consumption of the second set of parameters by the second vehicle may cause the second vehicle to remain outside of a drive envelope of the first vehicle, between the first vehicle and the particular destination.

Abstract: This disclosure is directed to calibrating sensors for an autonomous vehicle. First sensor data and second sensor data can be captured by one or more sensors representing an environment. The first sensor data and the second sensor data can be associated with a grid in a plurality of combinations to generate a plurality of projected data. A number of data points of the projected data occupying a cell of the grid can be summed to determine a spatial histogram. An amount of error (such as an entropy value) can be determined for each of the projected data, and the projected data corresponding to the lowest entropy value can be selected as representing a calibrated configuration of the one or more sensors. Calibration data associated with the lowest entropy value can be determined and used to calibrate the one or more sensors, respectively.

Abstract: An electronic braking system with independent antilock braking and stability control. The system can utilize a variety of electro-mechanical actuators to apply clamping force to a mechanical brake caliper. The system can include a caliper electronic control unit (CECU) and a wheel speed sensor at each wheel of the vehicle to enable independent slip control, or antilock braking, at each wheel. A separate executive management unit (EMU) can receive data from each electronic caliper, vehicle accelerometers, and other sensors to provide electronic stability control (ESC) independent of antilock braking (ABS) functions. The removal of a conventional master cylinder, brake pedal, ABS pump, brake lines, and other components can reduce weight and complexity. The elimination of hydraulic lines running to a central ABS module and master cylinder can enable modular drive units to be swapped out more quickly and efficiently.

Abstract: Techniques associated with generating and maintaining sparse geographic and map data. In some cases, the system may maintain a factor graph comprising a plurality of nodes. In some cases, the nodes may comprise pose data and sensor data associated with an autonomous vehicle at the geographic position represented by the node. The nodes may be linked based on shared trajectories and shared sensor data.

Abstract: Techniques and methods for performing collision monitoring using system data. For instance, a vehicle may generate sensor data using one or more sensors. The vehicle may then analyze the sensor data using systems in order to determine parameters associated with the vehicle and parameters associated with another object. Additionally, the vehicle may determine uncertainties associated with the parameters and then process the parameters using the uncertainties. Based at least in part on the processing, the vehicle may determine a distribution of estimated locations associated with the vehicle and a distribution of estimated locations associated with the object. Using the distributions of estimated locations, the vehicle may determine the probability of collision between the vehicle and the object.

Abstract: A seat for a vehicle includes an occupant protection system. The occupant protection system includes an airbag or other barrier that at least partially occludes an opening to a volume under a vehicle seat. The occupant protection system may reduce or prevent lower leg injury and/or retain cargo in the volume during a collision event.

Abstract: Techniques for predicting safety metrics associated with near-miss conditions for a vehicle, such as an autonomous vehicle, are discussed herein. For instance, a training system identifies an object in an environment and determines a trajectory for the object. The training system may receive a trajectory for a vehicle and associate the trajectory for the object and the trajectory for the vehicle with an event involving the object and the vehicle. In examples, the training system determines a parameter associated with motion of the vehicle as indicated by the trajectory of the vehicle relative to the trajectory of the object, and the event. Then, the training system may determine a safety metric associated with the event that indicates whether the vehicle came within a threshold of a collision with the object during a time period associated with the event.

Abstract: The described techniques relate to modifying a trajectory of a vehicle, such as an autonomous vehicle, based on an overlap area associated with an object in the environment. In examples, map data may be used, in part, to generate an initial trajectory for an autonomous vehicle to follow through an environment. In some cases, a yield trajectory may be generated based on detection of the object, and the autonomous vehicle may evaluate a cost function to determine whether to execute the yield or follow the initial trajectory. In a similar manner, the autonomous vehicle may determine a merge location of two lanes of a junction, and use the merge location to update extents of an overlap area to prevent the autonomous vehicle from blocking the junction and/or provide sufficient space to yield to the oncoming vehicle while merging.

Abstract: Techniques for detecting an object in an environment, determining a probability that the object is a region of particulate matter, and controlling a vehicle based on the probability. The region particulate matter may include steam (e.g., emitted from a man-hole cover, a dryer exhaust port, etc.), exhaust from a vehicle (e.g., car, truck, motorcycle, etc.), dust, environmental gases (e.g., resulting from sublimation, fog, evaporation, etc.), or the like. Based on the associated probability that the object is a region of particulate matter, a vehicle computing system may substantially maintain a vehicle trajectory, modify a trajectory of the vehicle to ensure the vehicle does not impact the object, stop the vehicle, or otherwise control the vehicle to ensure that the vehicle continues to progress in a safe manner. The vehicle controller may continually adjust the trajectory based on additionally acquired sensor data and associated region probabilities.

Abstract: Techniques for detecting an object in an environment and determining a probability that the object is a cloud of particulate matter. The cloud of particulate matter may include steam (e.g., emitted from a man-hole cover, a dryer exhaust port, etc.), exhaust from a vehicle (e.g., car, truck, motorcycle, etc.), environmental gases (e.g., resulting from sublimation, fog, evaporation, etc.), a cloud of dust, water splashing, blowing leaves, or other types of particulate matter that may be located in the environment of the vehicle and may not impact driving behavior (e.g., an autonomous vehicle may safely pass through the particulate matter without impact to the platform). A vehicle computing system may determine the probability that the object is a cloud of particulate matter and may control the vehicle based on the probability.

Abstract: Techniques for segmenting sensor data are discussed herein. Data can be represented in individual levels in a multi-resolution voxel space. A first level can correspond to a first region of an environment and a second level can correspond to a second region of an environment that is a subset of the first region. In some examples, the levels can comprise a same number of voxels, such that the first level covers a large, low-resolution region, while the second level covers a smaller, higher-resolution region, though more levels are contemplated. Operations may include analyzing sensor data represented in the voxel space from a perspective, such as a top-down perspective. From this perspective, techniques may generate masks that represent objects in the voxel space. Additionally, techniques may generate segmentation data to verify and/or generate the masks, or otherwise cluster the sensor data.

Abstract: Techniques associated with generating simulation scenarios for simulating a vehicle controller are discussed herein. Log data may include sensor data captured by sensors of a vehicle. The log data may represent objects in an environment. Objects may be associated with a region of a discretized representation of the environment relative to the vehicle. Specific states of objects (relative position in a region type, velocity, classification, size, etc.) may represent an instance of an occupation. Log data can be aggregated based on similar region type and/or object state. A statistical model over object states can be determined for each region type and can later be sampled to determine simulation parameters. A simulation scenario can be generated based on the simulation parameters, and a vehicle controller can be evaluated based on the simulation scenario.

Abstract: Ground truth data may be too sparse to supervise training of a machine-learned (ML) model enough to achieve an ML model with sufficient accuracy/recall. For example, in some cases, ground truth data may only be available for every third, tenth, or hundredth frame of raw data. Training an ML model to detect a velocity of an object when ground truth data for training is sparse may comprise training the ML model to predict a future position of the object based at least in part on image, radar, and/or lidar data (e.g., for which no ground truth may be available). The ML model may be altered based at least in part on a difference between ground truth data associated with a future time and the future position.

Abstract: Techniques are disclosed for executing a data processing pipeline. The techniques may include receiving a job at a data pipeline queue, setting up one or more distributed processing environments, and allocating the job to one of the distributed processing environments. The techniques may further include receiving the allocated job at a job queue within the distributed processing environment, increasing a priority level of the job, and executing the job within the distributed processing environment. The techniques can further include providing a retry pipeline at the data processing pipeline, and re-executing the job at a stage following a failure of at least one of its components. The techniques may decrement the retry budget as the job is re-executed.

Abstract: Techniques for determining predictions on a top-down representation of an environment based on vehicle action(s) are discussed herein. Sensors of a first vehicle (such as an autonomous vehicle) can capture sensor data of an environment, which may include object(s) separate from the first vehicle (e.g., a vehicle or a pedestrian). A multi-channel image representing a top-down view of the object(s) and the environment can be generated based on the sensor data, map data, and/or action data. Environmental data (object extents, velocities, lane positions, crosswalks, etc.) can be encoded in the image. Action data can represent a target lane, trajectory, etc. of the first vehicle. Multiple images can be generated representing the environment over time and input into a prediction system configured to output prediction probabilities associated with possible locations of the object(s) in the future, which may be based on the actions of the autonomous vehicle.

Abstract: Techniques are disclosed for a combined machine learned (ML) model that may generate a track confidence metric associated with a track and/or a classification of an object. Techniques may include obtaining a track. The track, which may include object detections from one or more sensor data types and/or pipelines, may be input into a machine-learning (ML) model. The model may output a track confidence metric and a classification. In some examples, if the track confidence metric does not satisfy a threshold, the ML model may cause the suppression of the output of the track to a planning component of an autonomous vehicle.