Abstract: Disclosed are embodiments for facilitating a system-level optimization route and mode suggestion platform for transportation trips. In some aspects, an embodiment includes receiving identification of an origin (O) location and a destination (D) location of an O/D pair corresponding to a transportation trip request of a user; determining N pickup (PU) locations for the O location and N drop-off (DO) locations for the D location; determining an origin walk duration between each N PU locations and the O location and a destination walk duration between each N DO locations and the D location; routing between the N PU locations and the N DO locations to determine an estimate of in-vehicle time for each route; and selecting a route that minimizes a route score, wherein the route score is based on a sum of the origin walk duration, the in-vehicle time, and the destination walk duration.

Abstract: Assistance can be provided to users of AVs based on user sentiments. A system may receive a request for assistance from a user of an AV (e.g., a passenger of the AV). The system may also receive sensor data that is captured by a sensor suite of the AV from detecting the user, the AV, or another object. The system determines a sentiment of the user based on the sensor data. The system may input the sensor data into a machine learning model and the model outputs information indicating the user's sentiment. The system can determine who, when, or how to service the user's request based on the user's sentiment. The system may assign the user's request to an agent who can provide the assistance. The system can further provide guidance (e.g., suggested content of a conversation with the user) to the agent based on the user's sentiment.

Abstract: A method of providing an onboard assistant for a vehicle, comprising: receiving sensor data from sensors of the vehicle; transforming the sensor data using a trained machine learning model to provide transformed sensor data; inferring from the transformed sensor data that a special condition for the vehicle requires intervention; and contacting an operator of the vehicle to inform the operator of the special condition and receive instructions for handling the special condition.

Abstract: The disclosed technology provides solutions for improving solar carport systems and in particular, for improving a solar carport integrated with a busbar. Aspects of the disclosed technology include an integrated solar carport that includes at least one beam, at least one rail coupled to the at least one beam, and one or more vertical columns configured to support the at least one beam and the at least one rail. Further, the integrated solar carport includes one or more solar modules coupled to the at least one beam or the at least one rail and a busbar coupled to each beam of the at least one beam and one of the vertical columns. Methods of manufacturing the integrated solar carport are also provided.

Abstract: A method of providing an onboard assistant for a vehicle, comprising: receiving sensor data from sensors of the vehicle; transforming the sensor data using a trained machine learning model to provide transformed sensor data; inferring from the transformed sensor data that a special condition for the vehicle requires intervention; and contacting an operator of the vehicle to inform the operator of the special condition and receive instructions for handling the special condition.

Abstract: There is disclosed a method of operating an autonomous vehicle (AV), including: detecting an alert condition within the AV via data from an electronic sensor suite of the AV; based at least in part on detecting the alert condition, automatically initiating a call with another party; and communicatively coupling a passenger of the AV to the conference call, whereby the passenger can communicate with the other party via the conference call.

Abstract: The disclosed technology provides solutions for providing an accurate pick-up location for an autonomous vehicle and a rider during a ride hailing pick-up. A method of the disclosed technology can include steps for determining map information associated with at least one thoroughfare for routing an autonomous vehicle, wherein the map information is based on location data associated with a client device requesting the autonomous vehicle; receiving sensor data from the client device corresponding to the at least one thoroughfare; determining, based on the sensor data and the map information, a first position of the client device relative to the at least one thoroughfare; and routing the autonomous vehicle based on the first position of the client device relative to the at least one thoroughfare. Systems and machine-readable media are also provided.

Abstract: Systems and methods are provided for autonomous vehicle recovery. In particular, systems and methods are provided for vehicle recovery prioritization in a fleet of vehicles when multiple vehicles request recovery. Stranded vehicles in need of recovery assigned a risk profile and prioritized based on the risk profile. The risk profile can be based on a number of factors, such as a risk level for the vehicle due to the vehicle's situation, the presence of passengers in the vehicle, and congestion caused by the vehicle. Recovery response can be based on the recovery prioritization. Vehicle sensors and computing power can be used to inform onboard processors and/or central computers of a risk profile for the vehicle, and dispatch can trigger a response plan according to a recovery response framework.

Abstract: Autonomous vehicles can offer affordable, accessible, and efficient transportation for passengers and cargo. For passengers with different mobility abilities, it can be a challenge to enter and exit an autonomous vehicle. It may also be difficult to bring a wheeled carrier in and out of an autonomous vehicle. A smart ramp can be included with an autonomous vehicle to improve the experience and safety of those with different mobility abilities, and to make it easier for wheeled carriers to go up and go down the ramp. The smart ramp has actuatable tiles that can be selectively actuated based on the position of a wheel of a wheeled carrier and a direction of travel of the wheeled carrier. The tiles may have a rubber-like material on a top side to provide grip and traction for users of the ramp.

Abstract: Autonomous driving computing systems in autonomous vehicles can include semiconductor chips with varying degrees of heat dissipation. The semiconductor chips are mounted on a printed circuit board, which together may be packaged in an enclosure assembly. The enclosure assembly may be mounted in the autonomous vehicle. Having a compact or low-profile enclosure assembly, and the harsh operating environment of the autonomous vehicle may pose a challenge for cooling the semiconductor chips and design of the enclosure assembly. Some cooling mechanisms can be difficult to manufacture, assemble, and/or service. An impeller-based intake subassembly can be combined with an air guidance plate that has a hollow structure that can direct air from the intake subassembly towards the printed circuit board through exhaust slots extending from the hollow structure, and air pathways to direct the air across the printed circuit board from the exhaust slots towards an impeller-based exhaust subassembly.

Abstract: Architectures and techniques for radar interference detection are provided. A radar sensor system in accordance with the present disclosure may receive, via a radio frequency (RF) receiver, radar signals including a radar signal of interest and one or more interfering radar signals. The radar sensor system may calculate a Doppler spectrum for each of the radar signals and perform a chirplet transform on the Doppler spectrum to generate various waveform parameters. A Principal Component Analysis (PCA) may be performed on the waveform parameters to extract frequency features of the radar signals. The radar sensor system may classify the frequency features using a classifier to identify interfering frequency features associated with the interfering radar signals using a classifier. The radar sensor system may further extract interfering waveform information based on the interfering frequency features of the interfering RF signals.

Abstract: Systems and techniques are provided for using a multi-sensor modality target to evaluate autonomous vehicle sensors. An example method can include identifying a sensor target panel based on a first set of Light Detection and Ranging (LiDAR) return signals corresponding to at least one retroreflective panel associated with the sensor target panel. In some aspects, the method can include transmitting a plurality of LiDAR beams directed toward the sensor target panel, wherein the sensor target panel includes a first sensor target region that is associated with a first reflectivity value and a second sensor target region that is associated with a second reflectivity value. In some cases, the method can include determining one or more LiDAR parameters based on a second set of LiDAR return signals corresponding to the sensor target panel.

Abstract: Systems and methods are provided for automated detection and disinfection of microbes in autonomous vehicles, to prevent possible transmission of diseases or illness to subsequent users. Automated detection and disinfection of a vehicle includes autonomously scanning various parts of the autonomous vehicle for microbes, selecting a disinfectant based on detected microbes, and autonomously disinfecting at least a portion of the autonomous vehicle.

Abstract: A computing system that can receive an object search request from a user indicating a request to search for a specific object in an area traversed by one or more autonomous vehicle. The object search request can include a set of physical characteristics of the specific object. The computing system can then transmit a signal to an autonomous vehicle indicating a request for the autonomous vehicle to search for the specific object. The signal can cause the autonomous vehicle to transmit an image, selected based on a physical characteristic of the object, to the computing system. The computing system can then generate a score indicative of a difference between one or more physical characteristic of the object in the image and the specific object. The computing system can then selectively transmit the image to a mobile device operated by the user based on the score.

Abstract: There is disclosed a method of providing rider service for an autonomous vehicle (AV) system, including operating an AV to provide a trip to a passenger; associating the passenger with a unique passenger identifier (UPID); receiving passenger metadata for the passenger according to the UPID; and responding to a rider service instance, comprising customizing the response according to the UPID and the passenger metadata.

Abstract: A methodology is described for determining a time for responding to an initial encounter by a vehicle with a map error in a map segment, wherein the initial encounter is detected by a detector. A method includes identifying an error type associated with the map error, wherein the error type is one of a first error type and a second error type; determining at least one additional factor associated with the initial encounter; determining a response time for the map error based on the error type and the at least one additional factor; and initiating a mitigating action in response to the initial encounter within the response time, wherein the response time comprises an amount of time from the initial encounter with the map error to a time at which a mitigating action should be taken.

Abstract: Systems and methods for preventing loss of audio during calls to and from a vehicle. In particular, systems and methods are provided for preventing the loss of audio for calls during an audio bus failure. Vehicles include interior microphones and speakers, which are connected via an audio bus. In some examples, the audio bus also includes other components such as a mixer, a transceiver, one or more cellular modems, an audio input module, and a digital signal processor. Using the audio bus, microphone input is beamformed and mixed and transmitted over a cellular network to a call recipient. Sound received back from the call recipient is received at the audio bus and transmitted to the vehicle via one or more speakers coupled to the audio bus. In some instances, the audio bus can fail, and alternative call procedures can be used to contact a remote advisor or other call recipient.

Abstract: The subject disclosure relates to features that improve safety for autonomous vehicle (AV) maneuvers and in particular, that improve safety for parallel parking. A process of the disclosed technology includes steps for initiating a parking maneuver, navigating the AV into a parking location, and detecting a roadway grade with respect to a direction of the AV. In some aspects, the process can further include steps for automatically adjusting a wheel angle of the AV based on the roadway grade with respect to the direction of the AV. Systems and machine-readable media are also provided.

Abstract: The subject disclosure relates to techniques for integrating synthetic plants into a virtual scene. A process of the disclosed technology can include receiving a digital asset comprising synthetic foliage, processing the digital asset to modify at least one parameter associated with the synthetic foliage to generate a modified digital asset, acquiring synthetic sensor data corresponding with the modified digital asset, and calculating a classification score for the modified digital asset based on the synthetic sensor data.

Abstract: Aspects of the disclosed technology provide solutions for measuring divergence between recorded real-world scene data, and a simulated environment. A process of the disclosed technology can include steps for generating, based on real-world autonomous vehicle (AV) scene data, a computer-generated simulation of a real-world scenario, determining, an occlusion region in which at least one surrounding object obstructs a field of view of the AV, and determining, based on the occlusion region, a portion of the object of interest that is visible to the AV. In some aspects, the process can further include steps for determining a divergence value indicating a difference between the portion of the object of interest that is visible to the AV within the simulation of the real-world scenario to an actual portion of the object of interest that is visible to the AV within the real-world scenario. Systems and machine-readable media are also provided.