Abstract: A system may schedule a vehicle for accommodating preferences of occupants within the vehicle. In some instances, an identity of the occupant may be determined and using the identity, the preference of the occupant may be determined. The vehicle may be schedule for the occupant in instances where the vehicle is able to accommodate the preference. The vehicle may be adjusted or setting(s) of the vehicle may be adjusted based on the preference. The vehicle may travel along a route according to the preferences.

Abstract: An occupant protection system for a vehicle may include an expandable curtain and/or an expandable bladder configured to be expanded from a stowed state to a deployed state. The system may also include a transverse ceiling trim panel and one or more side ceiling trim panels configured to be coupled to a ceiling of the vehicle, with the transverse ceiling trim panel extending substantially transversely with respect to the one or more side ceiling trim panels. Portions of the ceiling trim panels may be configured to deflect and allow expansion of the expandable curtain and/or the expandable bladder to the deployed state. The system may also include a deployment controller and one or more inflators configured to cause deployment of the expandable curtain at a first time and deployment of the expandable bladder at a second time after the first time.

Abstract: The present disclosure is directed to systems and techniques for controlling an autonomous vehicle. While the autonomous vehicle is travelling to a destination, the autonomous vehicle may encounter a situation preventing the autonomous vehicle from travelling to the destination. A control center may receive information from the autonomous device and use a graphical user interface to provide instructions with limited controls for the autonomous vehicle to navigate to an intermediate position. In such an intermediate position, the vehicle may make way for an emergency vehicle, obtain additional sensor data for continued autonomous planning, signal intent to other objects in the environment, and the like.

Abstract: A domain specific language for use in constructing simulations within real environments is described. In an example, a computing device associated with a vehicle can receive, from one or more sensors associated with the vehicle, sensor data associated with an environment within which the vehicle is positioned. In an example, the vehicle can be an autonomous vehicle. The computing device associated with the vehicle can receive simulated data associated with one or more primitives that are to be instantiated as a scenario in the environment. The computing device can merge the sensor data and the simulated data to generate aggregated data and determine a trajectory along which the vehicle is to drive based at least in part on the aggregated data. The computing device can determine instructions for executing the trajectory and can assess the performance of the vehicle based on how the vehicle responds to the scenario.

Abstract: A reward determined as part of a machine learning technique, such as reinforcement learning, may be used to control an adversarial agent in a simulation such that a component for controlling motion of the adversarial agent is trained to reduce the reward. Training the adversarial agent component may be subject to one or more constraints and/or may be balanced against one or more additional goals. Additionally or alternatively, the reward may be used to alter scenario data so that the scenario data reduces the reward, allowing the discovery of difficult scenarios and/or prospective events.

Abstract: Techniques for identifying a constraint to apply to an operation of a vehicle are described herein. A vehicle computing system receives diagnostics and constraints associated with components of the vehicle. The vehicle computing system identifies constraints to apply to vehicular operation based on the received diagnostics and constraints. The vehicle computing system may determine whether a received constraint is valid, based on associated diagnostics. Based on a determination that the constraint is valid, the vehicle computing system may include the constraint in vehicle control considerations. Based on a determination that the constraint is invalid, the vehicle computing system may withhold the constraint from vehicle control considerations.

Abstract: Techniques for determining whether to limit an operation of a vehicle while operating in a manually assisted mode of operation are described herein. A vehicle computing system can monitor components of the vehicle and identify a fault associated with a component. The vehicle computing system can determine whether the fault is associated with a manual operation of the vehicle. Based on a determination that the fault is not associated with the manual operation of the vehicle (e.g., fault associated with an autonomous control component), the vehicle computing system can override the fault and enable continued operation of the vehicle in the manually assisted mode of operation. Based on a determination that the fault is associated with the manual operation of the vehicle, the vehicle computing system can cause the vehicle to cease operating.

Abstract: A machine-learning (ML) architecture for determining three or more outputs, such as a two and/or three-dimensional region of interest, semantic segmentation, direction logits, depth data, and/or instance segmentation associated with an object in an image. The ML architecture may output these outputs at a rate of 30 or more frames per second on consumer grade hardware.

Abstract: Techniques for interacting with authorized and unauthorized users by a door interface component are discussed herein. A vehicle computing device can implement the door interface component and/or an authentication component to control operation of a door of the vehicle or initiate a communication for assistance. For instance, the door interface component can include a button, that provides different visual indicators and functionality based on whether the user is authorized to enter the autonomous vehicle (e.g., open a door or provide visual indicators for the user to select to cause the door to open) or to request to move the vehicle, initiate hiring the vehicle, or call for help when the user is unauthorized to enter the autonomous vehicle.

Abstract: Techniques for increasing performance of machine-learned models while conserving computational resources generally required by ensemble machine-learning methods are described herein. The techniques may include determining multiple views of a scene that is to be input into a machine-learned model. In some examples, a scene data input may be rotated by 90, 180, and 270 degrees to generate four scene inputs (e.g., 0-, 90-, 180-, and 270-degree rotated inputs) that can be passed through the machine-learned model and the results per scene can be aggregated to determine a final prediction/decision. Similarly, scene inputs may be shifted, reflected, translated, and/or the like before being input into the machine-learned model. The predictions may be associated with one or more objects in the environment that are represented in the scenes.

Abstract: A vehicle seat comprises a controllable deformable material and control apparatus is provided for controlling the state of a controllable deformable material. The control apparatus is configured to generate a signal to cause a control element in proximity to the controllable deformable material to change the characteristic of the controllable deformable material and thereby change the state of the controllable deformable material. The controllable deformable material is controllable to change state from a first state to at least a second state and is controllable to change state from at least the second state to the first state, the controllable deformable material being more deformable per unit force in the second state than in the first state.

Abstract: Techniques for capturing and recording processor events and scheduler data in a production system on a per processing resource basis are discussed herein. In some examples, a process metric collection component may be associated with the scheduler and the processing resource such that the process metric collection component can capture real time data associated with the processes or threads both executed by the processing resource and waiting to execute on the processing resource. The captured data may be used by the system to monitor operations.

Abstract: Techniques for updating data operations in a perception system are discussed herein. A vehicle may use a perception system to capture data about an environment proximate to the vehicle. The perception system may receive image data, lidar data, and/or radar data to determine information about an object in the environment. As different sensors may be associated with different time periods for capturing and/or processing operations, the techniques include updating object data with data from sensors associated with a shorter time period to generate intermediate object data.

Abstract: Drive envelope determination is described. In an example, a vehicle can capture sensor data while traversing an environment and can provide the sensor data to computing system(s). The sensor data can indicate agent(s) in the environment and the computing system(s) can determine, based on the sensor data, a planned path through the environment relative to the agent(s). The computing system(s) can also determine lateral distance(s) to the agent(s) from the planned path. In an example, the computing system(s) can determine modified distance(s) based at least in part on the lateral distance(s) and information about the agents. The computing system can determine a drive envelope based on the modified distance(s) and can determine a trajectory in the drive envelope.

Abstract: An occupant protection system may comprise an airtight, deformable container having a pressure sensor configured to generate a vehicle collision signal. A side airbag may be configured to expand between a stowed state and a deployed state. A deployment control system may be configured to receive the vehicle collision signal from the pressure sensor, and based upon the vehicle collision signal, cause an inflator to provide a gas to the airbag to thereby cause the side airbag to expand from the stowed state to the deployed state.

Abstract: An autonomous vehicle guidance system that generates a path for controlling an autonomous vehicle based at least in part on a data structure generated based at least in part on sensor data that may indicate occupied space in an environment surrounding an autonomous vehicle. The guidance system may receive a grid and generate a grid associated with the grid and the data structure. The guidance system may additionally or alternatively sub-sample the grid (latterly and/or longitudinally) dynamically based at least in part on characteristics determined from the data structure. The guidance system may identify a path based at least in part on a set of precomputed motion primitives, costs associated therewith, and/or a heuristic cost plot that indicates a cheapest cost to move from one pose to another.

Abstract: Techniques for using a set of variables to estimate a vehicle velocity of a vehicle are discussed herein. A system may determine an estimated velocity of the vehicle using a minimization based on an initial estimated velocity, steering angle data and wheel speed data. The system may then control an operation of the vehicle based at least in part on the estimated velocity.

Abstract: There is provided a method and system for vehicle security protection. The method comprises: determining, at a detector, a first sensor signal from a flex sensor in an exterior panel of a vehicle, wherein the flex sensor and detector are powered by a power supply of the vehicle, and wherein a magnitude of the first sensor signal is based on an amount of bending of the flex sensor; determining, at the detector, based on the first sensor signal, that the exterior panel of the vehicle is deformed; and outputting, from the detector, a first alert signal, wherein a first controller of the vehicle is configured to transition from a low-power state to a high-power state based at least in part on the first sensor signal.

Abstract: There is provided a network comprising a network switch comprising a pre-configured routing table and a first physical port coupled to an endpoint sensor device initiated with an initial network address. One or more processors are coupled to a third physical port of the network switch and are configured to: transmit configuration data for the endpoint sensor device to the third physical port via a first virtual area network. The first virtual area network is associated by the pre-configured routing table with the first physical port and a second virtual area network is associated with a second physical port of the network switch. A command to the endpoint sensor to use a different network address is transmitted by the network switch via the first physical port based at least in part on receiving the configuration data.

Abstract: A vehicle computing system may implement techniques to determine whether two objects in an environment are related as an articulated object. The techniques may include applying heuristics and algorithms to object representations (e.g., bounding boxes) to determine whether two objects are related as a single object with two portions that articulate relative to each other. The techniques may include predicting future states of the articulated object in the environment. One or more model(s) may be used to determine presence of the articulated object and/or predict motion of the articulated object in the future. Based on the presence and/or motion of the articulated object, the vehicle computing system may control operation of the vehicle.