Abstract: Arrangements relating to personal storage with shared vehicles are described. A shared vehicle, a user device, a storage compartment, a storage computing system, and/or a storage depot can be communicatively linked. The storage compartment can be configured to store one or more physical items as well as electronic data. The storage compartment can be configured to be selectively loaded within and unloaded from a shared vehicle during a use by a user. The storage compartment can be configured to be communicatively linked to the shared vehicle when in a loaded condition such that a component of the shared vehicle may access the electronic data during the use of the shared vehicle. Systems and methods described herein can be implemented with shared autonomous vehicles.

Abstract: Arrangements relating to the transitioning of a vehicle between operational modes are described. The vehicle can transition between a first operational mode and a second operational mode. The second operational mode has a greater degree of manual involvement than the first operational mode. For instance, the first operational mode can be an unmonitored autonomous operational mode, and the second operational mode can be a monitored autonomous operational mode or a manual operational mode. It can be determined whether an operational mode transition event has occurred while the vehicle is operating in the first operational mode. In response to determining that an operational mode transition event has occurred, a time buffer for continuing in the first operational mode before switching to the second operational mode can be determined. A transition alert can be presented within the vehicle. The transition alert can represent the determined time buffer.

Abstract: Arrangements relate to the interaction between an autonomous vehicle and an external environment of the autonomous vehicle. Such interaction can occur in various ways. For example, a non-verbal human gesture in the external environment can be detected. The non-verbal human gesture can be identified. A future driving maneuver can be determined based on the identified non-verbal human gesture. The autonomous vehicle can be caused to implement the determined future driving maneuver. As another example, the external environment of the autonomous vehicle can be detected to identify a person (e.g. a human pedestrian, a human bicyclist, a human driver or occupant of another vehicle, etc.) therein. The identified person can be located. It can be determined whether the person is potentially related to a future driving maneuver of the autonomous vehicle. The autonomous vehicle can be caused to send a directional message to the person.

Abstract: Arrangements relating to personal storage with shared vehicles are described. A shared vehicle, a user device, a storage computing system, and/or a storage depot can be communicatively linked. A storage request can be sent from one of the computing systems. One or more storage parameters can be determined, and storage instructions can be sent based on the determined storage parameters. The storage instructions can provide routing instructions to a vehicle and loading instructions to a storage depot. Storage depots can automatically transfer storage compartments between storage space and a vehicle through the use of robotics. Systems and methods described herein can be implemented with shared autonomous vehicles.

Abstract: Human driving performance can be assessed using an autonomous vehicle. An autonomous vehicle can have a manual operational mode and one or more autonomous operational modes. While the vehicle is operating in the manual operational mode, driving data relating to a manual driving maneuver can be acquired. The acquired driving data can be evaluated relative to a driving scene model to determine whether the manual driving maneuver is acceptable or unacceptable based on the acquired driving data. Responsive to determining that the manual driving maneuver is unacceptable, feedback can be provided to a user. In some instances, the feedback can be active feedback or passive feedback. In some instance, the user can be the human driver of the vehicle, or some other person related to the driver in some manner.

Abstract: Arrangements relating to personal storage with shared vehicles are described. A shared vehicle, a user device, a storage computing system, and/or a storage depot can be communicatively linked. A storage request can be sent from one of the computing systems. One or more storage parameters can be determined, and storage instructions can be sent based on the determined storage parameters. The storage instructions can provide routing instructions to a vehicle and loading instructions to a storage depot. Storage depots can automatically transfer storage compartments between storage space and a vehicle through the use of robotics. Systems and methods described herein can be implemented with shared autonomous vehicles.

Abstract: Arrangements related to the operation of an autonomous vehicle are described. The autonomous vehicle includes a vehicle seat. It can be determined whether a future planned driving maneuver of the autonomous vehicle includes a change in a current motion of the autonomous vehicle. Responsive to determining that the future planned driving maneuver includes a change in the current motion of the autonomous vehicle, the vehicle seat can be caused to provide a haptic indication of the future planned driving maneuver prior to implementing the future planned driving maneuver. In this way, a vehicle seat occupant can be alerted to the future planned driving maneuver. The haptic indication can include a movement of the vehicle seat. In one or more arrangements, the movement of the vehicle seat can correspond to a sensation that a vehicle seat occupant will experience during at least a portion of the future planned driving maneuver.

Abstract: Arrangements relating to the transitioning of a vehicle between operational modes are described. The vehicle can transition between a first operational mode and a second operational mode. The second operational mode has a greater degree of manual involvement than the first operational mode. For instance, the first operational mode can be an unmonitored autonomous operational mode, and the second operational mode can be a monitored autonomous operational mode or a manual operational mode. It can be determined whether an operational mode transition event has occurred while the vehicle is operating in the first operational mode. In response to determining that an operational mode transition event has occurred, a time buffer for continuing in the first operational mode before switching to the second operational mode can be determined. A transition alert can be presented within the vehicle. The transition alert can represent the determined time buffer.

Abstract: This application describes an automated driving system and methods. The automated driving system includes a perception system disposed on an autonomous vehicle. The automated driving system can detect, using the perception system, information for an environment proximate to the autonomous vehicle. The information for the environment includes current behavior of an object of interest and traffic density information. The automated driving system can also determine a classifier for the environment based on a prediction of future behavior of the object of interest. Based on the classifier, the automated driving system can identify a transition between vehicle states, the vehicle states being associated with a planned action for the autonomous vehicle. The automated driving system can also send a command to one or more vehicle systems to control the autonomous vehicle to execute the planned action according to the transition.

Abstract: Arrangements related to the operation of an autonomous vehicle are described. The autonomous vehicle includes a vehicle seat. It can be determined whether a future planned driving maneuver of the autonomous vehicle includes a change in a current motion of the autonomous vehicle. Responsive to determining that the future planned driving maneuver includes a change in the current motion of the autonomous vehicle, the vehicle seat can be caused to provide a haptic indication of the future planned driving maneuver prior to implementing the future planned driving maneuver. In this way, a vehicle seat occupant can be alerted to the future planned driving maneuver. The haptic indication can include a movement of the vehicle seat. In one or more arrangements, the movement of the vehicle seat can correspond to a sensation that a vehicle seat occupant will experience during at least a portion of the future planned driving maneuver.

Abstract: A method for generating accurate lane level maps based on course map information and Lidar data captured during the pass of a sensor carrying vehicle along a road. The method generates accurate lane estimates including the center of each lane, the number of lanes, and the presence of any bicycle paths and entrance and exit ramps using a computer-implemented method where the course map data and the Lidar data are subjected to particle filtering.

Abstract: Arrangements relate to the interaction between an autonomous vehicle and an external environment of the autonomous vehicle. Such interaction can occur in various ways. For example, a non-verbal human gesture in the external environment can be detected. The non-verbal human gesture can be identified. A future driving maneuver can be determined based on the identified non-verbal human gesture. The autonomous vehicle can be caused to implement the determined future driving maneuver. As another example, the external environment of the autonomous vehicle can be detected to identify a person (e.g. a human pedestrian, a human bicyclist, a human driver or occupant of another vehicle, etc.) therein. The identified person can be located. It can be determined whether the person is potentially related to a future driving maneuver of the autonomous vehicle. The autonomous vehicle can be caused to send a directional message to the person.

Abstract: A method of modeling an intersection structure of a roadway. The method includes receiving a first data set including road lane information, and receiving a second data set including vehicle trajectory information for an intersection structure of a roadway. The method includes determining lane node locations from at least one of the first and second data sets. A set of potential links between the lane node locations may be compiled. The method may further include assessing, for each link, a probability that the link is a valid link, and assigning each link with a probability value. The links may be filtered based on a predetermined threshold probability value and a set of valid links is generated. A model of the intersection structure is created based on the set of valid links.

Abstract: A vehicle system includes a first sensor and a second sensor, each having, respectively, different first and second modalities. A controller includes a processor configured to: receive a first sensor input from the first sensor and a second sensor input from the second sensor; detect, synchronously, first and second observations from, respectively, the first and second sensor inputs; project the detected first and second observations onto a graph network; associate the first and second observations with a target on the graph network, the target having a trajectory on the graph network; select either the first or the second observation as a best observation based on characteristics of the first and second sensors; and estimate a current position of the target by performing a prediction based on the best observation and a current timestamp.

Abstract: A method for generating accurate lane level maps based on coarse map information and image sensor data captured during the pass of a sensor carrying vehicle along a road. The method generates accurate lane estimates including any of the center of each lane, the number of lanes, and the presence of any bicycle paths, and entrance and exit ramps, merging of two lanes into one lane, or the expansion of one lane into two lanes, using a computer-implemented method where the coarse map data and the image sensor data are subjected to dual reversible jump-Markov chain Monte Carlo filtering.

Abstract: A method of multi-beam Lidar intensity measurement calibration including determining, by a positioning device, position information of a moving platform within a global reference frame, collecting a plurality of data points, each data point including the position information and intensity information from a plurality of beams, segmenting the plurality of data points into a plurality of voxels, based on the position information associated with each data point, finding a subset of voxels in the plurality of voxels that include a point corresponding to a certain beam in the plurality of beams and an intensity value in a predetermined neighborhood of a certain intensity value, estimating a probability density based on the subset of voxels, and generating a calibration map that maps the certain intensity value of the certain beam to a calibrated intensity value for the certain beam, based on the probability density and a prior density.

Abstract: A method for generating accurate lane level maps based on course map information and Lidar data captured during the pass of a sensor carrying vehicle along a road. The method generates accurate lane estimates including the center of each lane, the number of lanes, and the presence of any bicycle paths and entrance and exit ramps using a computer-implemented method where the course map data and the Lidar data are subjected to particle filtering.

Abstract: A method and apparatus for estimating and tracking a 3D object shape and pose estimation is disclosed A plurality of 3D object models of related objects varying in size and shape are obtained, aligned and scaled, and voxelized to create a 2D height map of the 3D models to train a principle component analysis model. At least one sensor mounted on a host vehicle obtains a 3D object image. Using the trained principle component analysis model, the processor executes program instructions to estimate the shape and pose of the detected 3D object until the shape and pose of the detected 3D object matches one principle component analysis model. The output of the shape and pose of the detected 3D object is used in one vehicle control function.

Abstract: A method of multi-beam Lidar intensity measurement calibration including determining, by a positioning device, position information of a moving platform within a global reference frame, collecting a plurality of data points, each data point including the position information and intensity information from a plurality of beams, segmenting the plurality of data points into a plurality of voxels, based on the position information associated with each data point, finding a subset of voxels in the plurality of voxels that include a point corresponding to a certain beam in the plurality of beams and an intensity value in a predetermined neighborhood of a certain intensity value, estimating a probability density based on the subset of voxels, and generating a calibration map that maps the certain intensity value of the certain beam to a calibrated intensity value for the certain beam, based on the probability density and a prior density.

Abstract: Method and system for imaging an object in three-dimensions, binning data of the imaged object into three dimensional bins, determining a density value p of the data in each bin, and creating receptive fields of three dimensional feature maps, including processing elements O, each processing element O of a same feature map having a same adjustable parameter, weight Wc1. The density values p are processed with the processing elements O to determine an output value o for at least each three dimensional location of the imaging of the object having a density value p above a predetermined threshold value. An object is classified by processing the output values o with a committee of classifiers, and the classification of the object is communicated.