Abstract: Methods and system for disinfecting an autonomous vehicle includes one or more LEDs coupled to the autonomous vehicle to emit UVC light into a passenger compartment of the autonomous vehicle. The autonomous vehicle can include sensors to confirm that the passenger compartment is empty and can be configured to prevent ingress of passengers into the passenger compartment while the UVC light is being emitted. Moreover, visible light indicators in the vehicle can be controlled to provide different visual indicators during the disinfecting cycle and when the vehicle is available to a passenger. In examples, the disinfecting cycle can be performed while the autonomous vehicle is in use, e.g., while the autonomous vehicle is traversing to a location to retrieve a passenger. The methods and systems can provide improved cleaning and disinfection of autonomous vehicles without the need to take the vehicles out of operation.

Abstract: Techniques for determining an error model based on vehicle data and ground truth data are discussed herein. To determine whether a complex system (which may be not capable of being inspected) is able to operate safely, various operating regimes (scenarios) can be identified based on operating data. To provide safe operation of such a system, an error model can be determined that can provide a probability associated with perception data and a vehicle can determine a trajectory based on the probability of an error associated with the perception data.

Abstract: An object model for a real-world object is constructed using a parameter-based object generator, where the parameters for the object model are determined using sensor data such as photographic images, radar images, or LIDAR images obtained from the real-world object. Conversion of the sensor data to appropriate object parameters is accomplished using a machine learning system. The machine learning system is calibrated by generating a plurality of object parameters, generating a corresponding plurality of learning objects from the plurality of object parameters, generating a plurality of simulated sensor return data for the learning objects, and then providing the simulated sensor return data and object parameters to the machine learning system.

Abstract: A vehicle may include a primary system and a secondary system to validate operation of the primary system and to control the vehicle to avoid collisions. For example, the secondary system may receive multiple trajectories from the primary system, such as a primary trajectory and a secondary, contingent, trajectory associated with a deceleration or other maneuver. The secondary system may determine if a trajectory is associated with a potential collision, if the trajectory is consistent with a current or previous pose, if the trajectory is compatible with a capability of the vehicle, etc. The secondary system may select the primary trajectory if valid, the secondary trajectory if the primary trajectory is invalid, or another trajectory generated by the secondary system if the primary trajectory and the secondary trajectory are invalid. If no valid trajectory is determined, the vehicle may decelerate at a maximum rate.

Abstract: A vehicle may include an authority tracker to grant and/or limit authority to provide guidance to the vehicle. The authority tracker may store a state in a memory identifying an actor that currently has the authority. An actor requesting to have authority to provide guidance to the vehicle may transmit a control message to the authority tracker which may, in turn, authorize or deny the request based on a policy. The authority tracker may periodically, and/or in response to a request, broadcast a state message identifying the actor that currently has authority, as recorded in the memory.

Abstract: A collision avoidance system may validate, reject, or replace a trajectory generated to control a vehicle. The collision avoidance system may comprise a secondary perception component that may comprise one or more machine learned models, each of which may be trained to output one or more occupancy maps based at least in part on sensor data of different types. The occupancy maps may include a prediction of whether at least a portion of an environment is occupied at a future time by any one of multiple object types. Occupancy maps associated with a same time may be aggregated into a data structure that may be used to validate, reject, or replace the trajectory.

Abstract: Sensors, including time-of-flight sensors, may be used to detect objects in an environment. In an example, a vehicle may include a time-of-flight sensor that images objects around the vehicle, e.g., so the vehicle can navigate relative to the objects. Sensor data generated by the time-of-flight sensor can return pixels subject to over-exposure or saturation, which may be from stray light. In some examples, multiple exposures captured at different exposure times can be used to determine a saturation value for sensor data. The saturation value may be used to determine a threshold intensity against which intensity values of a primary exposure are compared. A filtered data set can be obtained based on the comparison.

Abstract: Systems, methods, and apparatuses described herein are directed to performing segmentation on voxels representing three-dimensional data to identify static and dynamic objects. LIDAR data may be captured by a perception system for an autonomous vehicle and represented in a voxel space. Operations may include determining a drivable surface by parsing individual voxels to determine an orientation of a surface normal of a planar approximation of the voxelized data relative to a reference direction. Clustering techniques can be used to grow a ground plane including a plurality of locally flat voxels. Ground plane data can be set aside from the voxel space, and the remaining voxels can be clustered to determine objects. Voxel data can be analyzed over time to determine dynamic objects. Segmentation information associated with ground voxels, static object, and dynamic objects can be provided to a tracker and/or planner in conjunction with operating the autonomous vehicle.

Abstract: A sensor simulation system may generate sensor data for use in simulations by rendering two-dimensional views of a three-dimensional simulated environment. In various examples, the sensor simulation system uses sensor dependency data to determine specific views to be re-rendered at different times during the simulation. The sensor simulation system also may generate unified views with multi-sensor data at each region (e.g., pixel) of the two-dimensional view for consumption by different sensor types. A hybrid technique may be used in some implementations in which rasterization is used to generate a view, after which ray tracing is used to align the view with a particular sensor. Spatial and temporal upsampling techniques also may be used, including depth-aware and velocity-aware analyses for simulated objects, to improve view resolution and reduce the frequency of re-rendering views.

Abstract: Techniques for a perception system of a vehicle that can detect and track objects in an environment are described herein. The perception system may include a machine-learned model that includes one or more different portions, such as different components, subprocesses, or the like. In some instances, the techniques may include training the machine-learned model end-to-end such that outputs of a first portion of the machine-learned model are tailored for use as inputs to another portion of the machine-learned model. Additionally, or alternatively, the perception system described herein may utilize temporal data to track objects in the environment of the vehicle and associate tracking data with specific objects in the environment detected by the machine-learned model. That is, the architecture of the machine-learned model may include both a detection portion and a tracking portion in the same loop.

Abstract: Techniques for detecting attributes and/or gestures associated with pedestrians in an environment are described herein. The techniques may include receiving sensor data associated with a pedestrian in an environment of a vehicle and inputting the sensor data into a machine-learned model that is configured to determine a gesture and/or an attribute of the pedestrian. Based on the input data, an output may be received from the machine-learned model that indicates the gesture and/or the attribute of the pedestrian and the vehicle may be controlled based at least in part on the gesture and/or the attribute of the pedestrian. The techniques may also include training the machine-learned model to detect the attribute and/or the gesture of the pedestrian.

Abstract: Techniques to predict object behavior in an environment are discussed herein. For example, such techniques may include determining a trajectory of the object, determining an intent of the trajectory, and sending the trajectory and the intent to a vehicle computing system to control an autonomous vehicle. The vehicle computing system may implement a machine learned model to process data such as sensor data and map data. The machine learned model can associate different intentions of an object in an environment with different trajectories. A vehicle, such as an autonomous vehicle, can be controlled to traverse an environment based on object's intentions and trajectories.

Abstract: A vehicle mounted sensor assembly includes a frame and a cover connected to the base. When assembled, the frame and the cover define a volume that is divided between a first cavity and a second cavity. A sensor is disposed in the first cavity and one or more antennas are disposed in the second cavity.

Abstract: Techniques for determining a probability of a false negative associated with a location of an environment are discussed herein. Data from a sensor, such as a radar sensor, can be received that includes point cloud data, which includes first and second data points. The first data point has a first attribute and the second data point has a second attribute. A difference between the first and second attributes is determined such that a frequency distribution may be determined. The frequency distribution may then be used to determine a distribution function, which allows for the determination of a resolution function that is associated with the sensor. The resolution function may then be used to determine a probability of a false negative at a location in an environment. The probability can be used to control a vehicle in a safe and reliable manner.

Abstract: A machine-learning architecture may be trained to determine point cloud data associated with different types of sensors with an object detected in an image and/or generate a three-dimensional region of interest (ROI) associated with the object. In some examples, the point cloud data may be associated with sensors such as, for example, a lidar device, radar device, etc.

Abstract: Techniques for selectively offloading data that is computed by a first processing unit during training of an artificial neural network onto memory associated with a second processing unit and transferring the data back to the first processing unit when the data is needed for further processing are described herein. For example, the first processing unit may compute activations for operations associated with forward propagation. During the forward propagation, one or more of the activations may be transferred to a second processing unit for storage. Then, during backpropagation for the artificial neural network, the activations may be transferred back to the first processing unit as needed to compute gradients.

Abstract: The described techniques relate to modifying a trajectory of a vehicle, such as an autonomous vehicle, based on a latency associated with one or more systems of the vehicle. In examples, a planning system of the vehicle may predict a future latency (e.g., based on an interval between receipt of sensor data and/or object predictions), and use the future latency to determine a time at which to predict object behavior. Additionally, in some cases, the described techniques may include associating a predetermined acceleration with a predicted future location of the object to create a safety distance around the object, where the predetermined acceleration may be based on a maximum expected acceleration of the object. The safety distance may account for the object potentially accelerating in one or more directions at the future time.

Abstract: An autonomous vehicle safety system may activate to prevent collisions by detecting that a planned trajectory may result in a collision. If the safety system is overly sensitive, it may cause false positive activations, and if the system isn't sensitive enough the collision avoidance system may not activate and prevent a collision, which is unacceptable. It may be impossible or prohibitively difficult to detect false positive activations of a safety system and it is unacceptable to risk a false negative, so tuning the safety system is notoriously difficult. Tuning the safety system may include detecting near-miss events using surrogate metrics, and tuning the safety system to increase or decrease a rate of near-miss events as a stand-in for false positives.