Abstract: The disclosed computer-implemented method may include using location data from multiple devices improve the accuracy of location estimates for a rideable vehicle and/or provide calibration for location information. In some examples, at the end of a ride the system may record the location of the rider's device to augment the location data from the rideable vehicle. In another example, when a batch of rideable vehicles are delivered to a location, the system may use the location of the operator's device and/or the locations of other rideable vehicles in the batch to increase the accuracy of data for the location of any given rideable vehicle. In some embodiments, the system may detect the number of functioning location sensors to determine the confidence in the location of the vehicle. This confidence information can then be used in network decisions such as matching. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: A method for facilitating the collection of sensor data and vehicle data captured by one or more sensors of a vehicle is provided. The method includes storing sensor data and vehicle data to a portable memory device coupled to a port of a compute system of a vehicle and determining a storage capacity level of the portable memory device. In response to determining that the storage capacity level of the portable memory device has been reached, the method further includes generating one or more notifications indicating that the portable memory device that the storage capacity level of the portable memory device has been reached. The method thus includes transmitting the one or more notifications to a remote central computing system.

Abstract: Systems, methods, and non-transitory computer-readable media can receive a query specifying at least one example scenario. At least one image representation of the at least one example scenario can be encoded based on the query to produce at least one encoded representation. An embedding of the at least one representation of the at least one example scenario can be generated based on the at least one encoded representation. At least one scenario that is similar to the at least one example scenario can be identified based at least in part on the embedding of the at least one representation of the at least one example scenario and an embedding representing the at least one scenario. Information describing the at least one identified scenario can be provided in response to the query.

Abstract: The disclosed computer-implemented method may include monitoring, during a ride provided by an autonomous vehicle (AV), passenger communications between a passenger and a remote agent using an in-vehicle electronic device. The method may further include identifying passenger ride preferences based on a passenger request, and in association with a first occurrence of a ride event. The method may also include providing confirmation, via the in-vehicle electronic device, that the request is being fulfilled, the fulfillment of which causes a change in the passenger's AV experience based upon changes to features of the AV. The method may further include generating, based upon the request, a prediction of passenger ride preferences for the passenger and then, during a subsequent AV ride carrying the passenger, applying the predicted passenger ride preferences to an AV during a second occurrence of the ride event. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: The disclosed computer-implemented method may determine one or more characteristics of an autonomous vehicle, determine one or more characteristics of one or more road segments of a geographic area, determine at least one geographic zone for the autonomous vehicle within the geographic area based at least on the characteristics of the autonomous vehicle and the characteristics of the one or more road segments of the at least one geographic area, and match a request with the autonomous vehicle within the at least one geographic zone based at least in part on a request location and a destination location of the request being associated with the at least one geographic zone. Other methods, systems, and computer-readable media are disclosed.

Abstract: Examples disclosed herein involve a computing system configured to (i) receive image data captured by an image-capture device; (ii) based on the received image data, generate a set of map update tasks that each define a respective activity for evaluating whether to update a map; (iii) use a multi-factor prioritization scheme to prioritize the set of map update tasks; (iv) assign at least a subset of map update tasks from the set of map update tasks to one or more curators in accordance with the prioritization of the set of map update tasks; (v) receive, from a client station associated with a given curator via a network-based communication path, data defining feedback from the given curator regarding a given map update task; and (vi) update the map based on the received feedback.

Abstract: A computer-implemented method is disclosed for managing personal mobility vehicles (PMVs) across a geographic region. One or more sensor-equipped vehicles traverse the region and collect sensor data, which is used by a computing system to determine the respective state and location of PMVs. Based on these determinations, the system generates a utilization value for the PMVs and compares it to a predefined utilization metric reflecting desired deployment levels. The system then provides instructions to reposition PMVs within the region to satisfy the utilization metric, enabling automated, demand-responsive fleet balancing and reduced reliance on manual monitoring.

Abstract: In one embodiment, a method includes one or more computing systems determining a fleet-level objective for a vehicle. The fleet-level objective is associated with instructing the vehicle to travel a route according to route criteria based on the fleet-level objective. The one or more computing systems may determine one or more of an urgency score indicative of an urgency to fulfill the fleet-level objective or a risk factor score indicative of an overall condition of the vehicle. Based on one or more of the urgency score or the risk factor score, the one or more computing systems may select a particular operating mode from a plurality of operating modes for the vehicle to operate. The one or more computing system may instruct the vehicle to operate in the particular operating mode so as to fulfill the fleet-level objective.

Abstract: In particular embodiments, a computing system may collect, for each ride of a plurality of rides, first ride data associated with a user riding a personal mobility vehicle during a certain time period. The system may calculate, for each ride, an approximate load on the personal mobility vehicle based on at least the first ride data. The system may calculate a user profile of the user based on the approximate loads. The system may collect, for a subsequent ride, second ride data associated with the user riding a current personal mobility vehicle after the certain time period. The system may calculate, for the subsequent ride, a second approximate load on the current personal mobility vehicle based on at least the second ride data. The system may compare the second approximate load to the user profile and classify the subsequent ride as individual or tandem based on the comparison.

Abstract: The disclosed computer-implemented method may include (i) identifying, by a server computer system, a provider computing device for use in capturing street-level image data, where the provider computing device controls a camera positioned to capture street-level imagery outside the vehicle, (ii) determining, by the server computer system, a configuration that controls use of the provider computing device to provide street-level image data captured by the camera to the server computer system, (iii) sending, by the server computer system, the configuration to the computing device, and (iv) receiving, from the computing device, street-level image data captured by the computing device using the camera responsive to the configuration. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for intelligently determining to assess (or not assess) a cancellation penalty and notifying a requestor device of such a penalty in response to either a requestor's selection to cancel a single transportation request for a requestor or a requestor's selection to cancel a shared-transportation request associated with multiple requestors. For example, the disclosed systems can generate conversion probabilities for a requestor reflecting if a cancellation penalty is assessed—and if the cancellation penalty is not assessed—for a cancellation of a transportation request for transport of a lone requestor. Based on the conversion probabilities, the disclosed systems customize a cancellation notice for a requestor device to either include or exclude the cancellation penalty.

Abstract: This disclosure describes a request distribution system that can intelligently distribute transportation requests to provider devices to improve transportation system network coverage and efficiency. For example, the disclosed systems can identify a transportation request corresponding to a first transportation mode and analyze multiple limited-eligibility provider devices having various modes as potential recipients for the transportation request. In some embodiments, the disclosed systems can further determine an expected change in network coverage time associated with providing the transportation request to a first provider device corresponding to the first transportation mode versus a second provider device corresponding to a second transportation mode. The disclosed systems can provide the transportation request to the second provider device corresponding to the second transportation mode according to the expected change in network coverage time and/or other transportation request metrics.

Abstract: Systems, methods, and non-transitory computer-readable media can detect an occurrence of a condition in an environment based on sensor data captured by a vehicle. A determination is made whether the occurrence of the condition satisfies a threshold associated with a likelihood that a behavior associated with an object in the environment will occur based on an interaction between the condition and the object, wherein the likelihood is based on prior observations of one or more objects. Subsequent to determining that the threshold is satisfied, a vehicle operation that is associated with the likelihood that the behavior associated with the object will occur is performed.

Abstract: Examples disclosed herein may involve a computing system that is operable to (i) receive image data and corresponding secondary sensor data, (ii) generate a reconstruction of a map from the image data, wherein the reconstruction comprises sequential pose information, (iii) determine constraints from the secondary sensor data, and (iv) validate the reconstruction of the map by applying the determined constraints from the secondary sensor data to the determined sequential pose information from the reconstruction of the map and determining whether the sequential pose information fails to satisfy any of the constraints determined from the secondary sensor data.

Abstract: The disclosed computer-implemented method may include displaying vehicle environment awareness. In some embodiments, a visualization system may display an abstract representation of a vehicle's physical environment via a mobile device and/or a device embedded in the vehicle. For example, the visualization may use a voxel grid to represent the environment and may alter characteristics of shapes in the grid to increase their visual prominence when the sensors of the vehicle detect that an object is occupying the space represented by the shapes. In some embodiments, the visualization may gradually increase and reduce the visual prominence of shapes in the grid to create a soothing wave effect. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: Examples disclosed herein may involve a computing system that is operable to (i) use a first approach to produce a first representation of an agent's trajectory from a first set of sensor data, (ii) use a second approach to produce a second representation of the agent's trajectory from a second set of sensor data, wherein the first and second representations of the agent's trajectory are based on different spatial reference frames and different temporal reference frames, (iii) align the spatial reference frames of the first and second representations by applying a spatial transformation to one of the first or second representations, (iv) align the temporal reference frames by applying an origin-time offset to one of the first or second representations, and (v) use the aligned first and second representations as a basis for evaluating an accuracy of the first approach relative to the second approach.

Abstract: A micromobility electric vehicle with a controller that operates the vehicle in a walk-assist mode, expanding the population of users that can comfortably use the vehicle. In walk-assist mode, the speed of the vehicle may be limited to a walking speed, regardless of the position of a throttle. In contrast, in a riding mode, the maximum speed may be higher. The walk-assist mode may be entered or exited based on output of one or more sensors, indicating that the user is or is not riding the vehicle or that a user is or is not pushing the vehicle. Such sensors may be positioned in a seat, in a floorboard or on the handlebars of the vehicle. Alternatively or additionally, the sensor may be associated with a control, such as a tab configured to be pressed by a user's thumb when the user is pushing the vehicle.

Abstract: The disclosed computer-implemented method may include a magnetic insertable lock component with a magnet-sensing lock housing. By using a magnet within a pin and a magnetic field sensor within the lock housing, the apparatus may accurately detect the state of the lock. In some embodiments, the apparatus may determine the pin is inserted fully into the lock, the pin is inserted partially into the lock, the pin is not inserted in the lock, and/or that a foreign object that is not the pin is inserted into the lock. By using a magnet within the pin to track the state of the lock, the apparatus may improve both the user experience and the security of the lock. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: Systems and methods associated with a battery for a micromobility transit vehicle are provided. A micromobility transit vehicle may include a frame and a battery disposed at least partially in the frame. The battery may include a housing and a ventilation assembly. The ventilation assembly may include a vent cap releasably coupled to the housing, and a breather plug connected to the vent cap and including a membrane configured to pass air between the housing and an external environment, such as to equalize a pressure within the housing with an external environment. The vent cap may be configured to mechanically release from the housing to vent internal gases out of the battery in response to a pressure within the housing, such as in response to a pressure exceeding a threshold.