Adaptive loading element

Abstract

A current location and a destination location of a vehicle are identified. A loading parameter is predicted based on the current location and the destination location. A vehicle component is actuated based on the loading parameter.

Description

TECHNICAL FIELD

[0001] The present invention relates to identifying a current location and a destination location of a vehicle. A loading parameter is predicted based on the current location and the destination location. A vehicle component is actuated based on the loading parameter. BACKGROUND

[0002] A vehicle can transport a user and cargo to a destination. Upon arrival at the vehicle, the user can possess an object that needs to be stored in the vehicle during transport, such as luggage. However, the vehicle can not have space to accommodate the object and / or an actual location to load the object. Problems with current object loading and transport technology include a lack of ability to predict object loading needs and / or adapt loading to various objects to be transported in the vehicle. SUMMARY

[0003] A method includes identifying a current location and a destination location of a vehicle, predicting a loading parameter based on the current location and the destination location, and actuating a vehicle component based on the loading parameter.

[0004] The vehicle component can be one of a suspension, a seat, and a loading element.

[0005] The method can include predicting the loading parameter based on a characteristic of the object and one or both of the current location and the destination location in the vehicle.

[0006] The method can include predicting one loading parameter for each object of a plurality of objects.

[0007] The method can include receiving a message from a user device and predicting the loading parameter based on the message from the user device.

[0008] The method can include predicting the loading parameter based on a vehicle activity log.

[0009] The method can include predicting the loading parameter based on user input.

[0010] The method can include predicting the loading parameter based on a message from each sensor of a set of seat sensors.

[0011] The method can include predicting the loading parameter by applying a rule derived from machine learning.

[0012] A system includes a computer programmed to identify a current location and a destination location of a vehicle, predict a loading parameter based on the current location and the destination location, and actuate a vehicle component based on the loading parameter.

[0013] The vehicle component can be one of a suspension, a shelf, a hook, a storage bin, and a seat.

[0014] The computer can be programmed to predict the loading parameter based on a characteristic of the object and one or both of a current location and a destination location in the vehicle.

[0015] The computer can be programmed to predict one loading parameter for each object of the plurality of objects.

[0016] The computer can be programmed to receive a message from a user device and predict the loading parameter based on the message from the user device.

[0017] The computer can be programmed to predict the loading parameter based on a vehicle activity log.

[0018] The computer can be programmed to predict the loading parameter based on user input.

[0019] The computer can be programmed to predict the loading parameter based on a message from each sensor of a set of seat sensors.

[0020] The computer can be programmed to predict the loading parameter by applying a rule derived from machine learning.

[0021] A system includes a loading element including an actuator arranged to move at least a portion of the loading element, and a computer programmed to identify a current location and a destination location of a vehicle, predict a loading parameter based on the current location and the destination location, and actuate a vehicle component based on the loading parameter.

[0022] The computer can be programmed to predict the loading parameter based on a characteristic of the object and one or both of a current location and a destination location in the vehicle. BRIEF DESCRIPTION OF DRAWINGS

[0023] Figure 1 is a block diagram of an example system for predicting a loading parameter in a vehicle.

[0024] Figure 2 is a perspective view of an example loading element in an example vehicle.

[0025] Figure 3 is a perspective view of another example loading element in an example vehicle.

[0026] Figure 4 is an example process for predicting a loading parameter in a vehicle. DETAILED DESCRIPTION

[0027] A system includes a computer programmed to identify a current location and a destination of a vehicle, predict a loading parameter based on the current location and the destination location, and actuate a vehicle component based on the loading parameter.

[0028] The vehicle component can be one of a suspension, a shelf, a hook, a storage bin, and a seat.

[0029] The computer can also be programmed to predict the loading parameter based on a characteristic of the object and one or both of the current location and the destination location in the vehicle. The computer can also be programmed to predict one loading parameter for each of a plurality of objects.

[0030] The computer can also be programmed to receive a message from a user device and predict the loading parameter based on the message from the user device. The computer can also be programmed to predict the loading parameter based on a vehicle activity log. The computer can also be programmed to predict the loading parameter based on a message from each sensor in a set of seat sensors. The computer can also be programmed to predict the loading parameter by applying a rule derived from machine learning.

[0031] A system includes a vehicle loading element having an actuator arranged to move at least a portion of the loading element, and a computer programmed to identify a current location and a destination location of the vehicle, predict a loading parameter based on the current location and the destination location, and actuate a vehicle component based on the loading parameter.

[0032] The computer can also be programmed to predict the loading parameter based on a characteristic of the object and one or both of the current location and the destination location in the vehicle.

[0033] A method includes identifying a current location and a destination location of a vehicle, predicting a loading parameter based on the current location and the destination location, and actuating a vehicle component based on the loading parameter.

[0034] The vehicle component can be one of a suspension, a shelf, a hook, a storage bin, and a seat.

[0035] The method can also include predicting the loading parameter based on a characteristic of the object and one or both of the current location and the destination location in the vehicle. The method can also include predicting one loading parameter for each of a plurality of objects.

[0036] The method can also include receiving a message from a user device and predicting the loading parameter based on the message from the user device. The method can also include predicting the loading parameter based on a vehicle activity log. The method can also include predicting the loading parameter based on a message from each sensor in a set of seat sensors. The method can also include predicting the loading parameter by applying a rule derived from machine learning.

[0037] A computing device programmed to perform any of the above method steps is also disclosed. A vehicle including the computing device is also disclosed. A computer program product including a computer readable medium storing instructions executable by a computer processor to perform any of the above method steps is also disclosed.

[0038] Figure 1 An example system 100 is shown that includes a computer 105 programmed to identify a current location of a vehicle 101 and a destination location, and predict a stowage parameter based on the current location and the destination location of the vehicle 101. In the context of the present disclosure, a stowage parameter is a value or rule that specifies a way in which an object can be stored or stowed in the vehicle 101 at a location (e.g., for transport between the current location and the destination location). The computer 105 can maintain a list of stowage parameters in the vehicle 101 based on the vehicle 101 location and objects stowed in the vehicle 101. The computer 105 can maintain the list of possible stowage parameters according to each parameter and / or a substantially unique identifier of a descriptor (e.g., “hanging,” “enclosed,” “supported,” etc.) as well as a set of coordinates specifying a vehicle 101 location associated with each respective parameter. The computer 105 can store the set of geographic coordinates indicating the settings of the vehicle 101 location and / or can store identifiers of objects that can also be associated with the stowage parameters. Based on the vehicle 101 location and the object, the computer 105 can determine a stowage parameter required at a particular location. The computer 105 can then actuate one or more vehicle 101 components based on the stowage parameter, for example, to navigate the vehicle 101 to the destination location.

[0039] The computer 105 in the vehicle 101 is programmed to receive collected data 115 from one or more sensors 110. For example, the data 115 of the vehicle 101 can include a location of the vehicle 101, a location of a target, etc. The location data can be in a known form, such as geographic coordinates such as latitude and longitude coordinates obtained via a known navigation system that uses a global positioning system (GPS). The navigation system can continuously monitor the location data 115 of the current location of the vehicle 101. A user can input location data 115 of a destination location into the navigation system, for example, to receive directions to the destination location. Other examples of data 115 can include measurements of vehicle 101 systems and components, such as a vehicle 101 speed, a vehicle 101 trajectory, etc.

[0040] The computer 105 is generally programmed for communication over a network of the vehicle 101, for example, including a communication bus as known. Via the network, bus, and / or other wired or wireless mechanisms (e.g., a wired or wireless local area network in the vehicle 101), the computer 105 can transmit messages to and / or receive messages from various devices in the vehicle 101, for example, controllers, actuators, sensors, etc., including the sensors 110. Alternatively or additionally, in cases where the computer 105 actually includes multiple devices, the vehicle network can be used for communication between devices represented in the disclosure as the computer 105. Additionally, the computer 105 can be programmed for communication with the network 125, as described below, which can include various wired and / or wireless networking technologies, for example, cellular, Bluetooth®, low power (BLE), wired and / or wireless packet networks, etc.

[0041] The data storage 106 can be of any known type, for example, a hard drive, solid state drive, server, or any volatile or non-volatile media. The data storage 106 can store collected data 115 transmitted from the sensors 110.

[0042] The sensors 110 can include a variety of devices. For example, as known, various controllers in the vehicle 101 can operate as sensors 110 to provide data 115 via the network or bus of the vehicle 101, for example, data 115 related to vehicle speed, acceleration, position, subsystem and / or component status, etc. Further, other sensors 110 can include cameras, motion detectors, etc., i.e., sensors 110 to provide data 115 for evaluating the position of a target, projecting a path of a target, evaluating the position of a road lane, etc. The sensors 110 can also include short range radar, long range radar, laser radar (LIDAR), and / or ultrasonic transducers.

[0043] The collected data 115 can include a variety of data collected in the vehicle 101. Examples of collected data 115 are provided above, and, in addition, the data 115 is generally collected using one or more sensors 110, and can additionally include data computed in the computer 105 and / or at the server 130 from such data. Generally, the collected data 115 can include any data that can be acquired by the sensors 110 and / or computed from such data.

[0044] Vehicle 101 can include a plurality of vehicle components 120. As used herein, each vehicle component 120 includes one or more hardware components adapted to perform a mechanical function or operation, such as moving vehicle 101, decelerating or stopping vehicle 101, steering vehicle 101, etc. Non-limiting examples of components 120 include propulsion components (including, e.g., internal combustion engines and / or electric motors, etc.), transmission components, steering components (e.g., can include one or more of steering wheels, steering racks, etc.), braking components, parking assistance components, adaptive cruise control components, loading elements, etc.

[0045] Vehicle 101 can include suspension components. Suspension components control the height of the vehicle 101 body relative to the driving surface. For example, suspension components can include springs, shock absorbers, etc., to maintain a consistent height of the vehicle 101 body while vehicle 101 is in transit. Suspension components can be adjusted to change the height of the vehicle 101 body. For example, suspension components can be actuated between a driving position and a loading position. When suspension components are in the driving position, the vehicle 101 body is farther from the driving surface than when suspension components are in the loading position. Suspension components can be in the driving position, for example, while vehicle 101 is in transit. Suspension components can be in the loading position, for example, at the current location and / or the destination location, to assist in loading objects. Computer 105 can actuate suspension components from the driving position to the loading position based on loading parameters.

[0046] Vehicle 101 can include a human-machine interface (HMI) 120, e.g., one or more of a display, a touchscreen display, a microphone, a speaker, etc. A user can input data 115 into HMI 120, e.g., a current location of vehicle 101, a destination location of vehicle 101, an object to be loaded at one of the current location and the destination location, etc. For example, a user can input object data 115, e.g., object characteristics, an identifier associated with the object, and an image of the object, etc., into HMI 120, and computer 105 can determine loading parameters for loading the object. As another example, a user can input location data 115, e.g., a destination location, into HMI 120, and computer 105 can determine loading parameters for storing an object associated with the destination location, e.g., available at the destination location. HMI 120 can communicate with computer 105 via vehicle 101 network, e.g., HMI 120 can send a message including user input, e.g., location data 115 and / or object data 115, to computer 105. Computer 105 can determine loading parameters based on the message from HMI 120.

[0047] The vehicle 101 includes a plurality of seats 120. The seats 120 can support users in a cabin of the vehicle 101. The seats 120 can be arranged in the cabin of the vehicle 101 to accommodate users and objects, such as luggage. The seats 120 can be foldable from a seated position back to a stowed position. In one example, in the seated position, a seat back can extend upward relative to a seat bottom, for example, the seat can support a user in a regular seated position. Continuing the example, in the stowed position, the seat back can extend substantially parallel to the seat bottom, for example, the seat back can rest across the seat bottom and can support an object stowed in the vehicle 101.

[0048] Each seat 120 can include a seat sensor 110. The seat sensor 110 can detect the presence of a user seated on the seat 120. The seat sensor 110 can send data 115 to the computer 105, and the computer 105 can determine whether a user is in the seat 120. The computer 105 can compare the data 115 from the seat sensor 110 to a threshold. When the data 115 from the user detection sensor 110 is above the threshold, the computer 105 can determine that a user is in the seat 120. For example, if the seat sensor 110 is a weight sensor, the computer 105 can compare the collected user weight data 115 to a weight threshold. When the user weight data 115 exceeds the weight threshold, the computer 105 can determine that a user is in the seat 120. When the data 115 from the seat sensor 110 is below the threshold (e.g., the user weight data 115 is below the weight threshold), the computer 105 can determine that a user is not in the seat 120.

[0049] The vehicle 101 is an “autonomous” vehicle 101 when the computer 105 is operating the vehicle 101. For purposes of this disclosure, the term “autonomous vehicle” is used to refer to a vehicle 101 operating in a fully autonomous mode. A fully autonomous mode is defined as a mode in which each of propulsion (typically via a powertrain including electric motors and / or internal combustion engines), braking, and steering of the vehicle 101 is controlled by the computer 105. A semi-autonomous mode is a mode in which at least one of propulsion (typically via a powertrain including electric motors and / or internal combustion engines), braking, and steering of the vehicle 101 is controlled at least partially by the computer 105 rather than by a human operator.

[0050] The system 100 can also include a network 125 that provides communication between other devices, such as a server 130 and a data storage device 135. The network 125 represents one or more mechanisms by which the vehicle computer 105 can communicate with the remote server 130. Thus, the network 125 can be one or more of various wired or wireless communication mechanisms, including any desired combination of wired (e.g., cable and fiber) and / or wireless (e.g., cellular, wireless, satellite, microwave, and radio frequency) communication mechanisms, as well as any desired network topology (or topologies when multiple communication mechanisms are used). Exemplary communication networks include wireless communication networks (e.g., using Bluetooth®, BLE, IEEE 802.11, vehicle-to-vehicle (V2V) such as dedicated short-range communications (DSRC), etc.), local area networks (LANs), and / or wide area networks (WANs), including the Internet. BLE, IEEE 802.11, vehicle-to-vehicle (V2V) such as dedicated short-range communications (DSRC), etc.), local area networks (LANs), and / or wide area networks (WANs), including the Internet.

[0051] The system 100 can include a user device 140. As used herein, a “user device” is a portable computing device that includes a memory, a processor, a display, and one or more input mechanisms (such as a touchscreen, buttons, etc.), as well as hardware and software for wireless communication as described herein. Thus, the user device 140 can be any of a variety of computing devices that include a processor and a memory, such as a smartphone, a tablet, a personal digital assistant, etc. The user device 140 can communicate with the vehicle computer 105 using the network 125. For example, the user device 140 can be communicatively coupled to each other and / or to the vehicle computer 105 using wireless technologies such as described above. The user device 140 includes a user device processor 145.

[0052] The computer 105 can predict loading parameters based on object data 115 and / or location data 115. The computer 105 can receive object data 115 and / or location data 115 from the HMI 120, a cloud computer (e.g., a computer connected to the network 125 and external to the vehicle 101), a sensor 110 (e.g., a camera that captures images of objects), the user device 140, etc. The computer 105 can determine loading parameters by analyzing the object data 115 and / or the location data 115, for example, the computer 105 can determine whether an object is loadable into the vehicle 101 based on object data 115 (e.g., object characteristics), and can predict whether an object will be loaded based on location data 115. The computer 105 can actuate vehicle components 120 according to the loading parameters.

[0053] Computer 105 may include a machine learning program to predict loading parameters of vehicle 101. The machine learning program can monitor the position of vehicle 101 and the objects loaded at that position substantially continuously. In other words, the machine learning program can store object data 115, position data 115, and stored parameters. For example, the machine learning program may include a vehicle activity log that records the position of vehicle 101 and the objects stored in vehicle 101 at various times. The vehicle activity log can store position data 115 and object data 115; for example, it can store historical data 115 of vehicle 101, such as data from previous trips. The vehicle activity log can be populated with object data 115 and position data 115 from human-machine interface 120; for example, a user can input object and position data 115 from network 125, and the vehicle activity log can communicate with network 125 to receive object data 115. Sensors 110 (e.g., a camera) can capture images of objects from GPS, etc. The machine learning program can predict loading parameters based on location data 115. For example, the machine learning program can predict the same loading parameters identified when location data 115 indicates that vehicle 101 should return to its previous position. Additionally, the machine learning program can predict loading parameters based on object data 115. For example, the machine learning program can predict loading parameters based on objects loaded in vehicle 101, such as the type and size of the objects.

[0054] Computer 105 can predict loading parameters based on application rules derived from a machine learning program. For example, when vehicle 101 is at a certain location, if stored object data 115 corresponds to stored object data 115 at that location, the machine learning program can increase the probability that the object corresponding to that object data 115 will be loaded at that location. Otherwise, the machine learning program may decrease that probability. Computer 105 can predict loading parameters based on the probabilities determined by the machine learning program; for example, when the probability is higher than a threshold, computer 105 can predict the stored loading parameters.

[0055] Figure 2 and Figure 3 An exemplary vehicle 101 is shown. Vehicle 101 includes a plurality of loading elements 122a, 122b, 122c, and 122d, collectively referred to as loading element 122. A loading element is any component in vehicle 101 capable of supporting and / or storing objects during transport of vehicle 101. For example, loading element 122a may be, for example, a swing arm for suspending objects, loading element 122b may be, for example, a shelf for supporting objects, loading element 122c may be, for example, a storage box for enclosing objects, and loading element 122d may be a seat back when seat 120 is in a loading position, for example, the seat back of seat 120 may support objects.Figure 2 The example shows two objects 215a and 215b (collectively referred to as objects 215) supported by loading elements 122a and 122c respectively. Figure 3 The example illustrates two objects 215a and 215b supported by loading elements 122b and 122d, respectively. Loading elements 122 can be actuated individually and / or collectively to support multiple (e.g., one or more) objects in vehicle 101. In other words, computer 105 can actuate one or more loading elements 122 based on object data 115. As described below, computer 105 can determine the loading element 122 for each object and can actuate the loading element 122 to support each object.

[0056] Object 215 can be any object that a user can transport in vehicle 101. For example, a user can transfer object 215 from its current location to vehicle 101 and transport object 215 from vehicle 101 to its destination location. Object 215 can be, for example, luggage, parcels, crates, or any other object that a user can carry onto vehicle 101. Computer 105 can determine the characteristics of object 215. Object characteristics are any physical properties of object 215. For example, object characteristics can include the object's dimensions, such as applicable length, height, width, perimeter, etc. As another example, a characteristic can be the object's mass or weight. As yet another example, a characteristic can be the object's physical features, such as being susceptible, fragile, durable, etc. Computer 105 can determine that object 215 is fragile based on its material type, such as glass, ceramic, plastic, metal, etc. When the material type of object 215 presents a risk of breakage, such as glass, ceramic, etc., computer 105 can determine that object 215 is fragile and can predict "fragile" loading parameters to protect object 215. For example, computer 105 may store a list of specified object materials (e.g., plastic, glass, cloth, etc.) and a lookup table of loading parameters associated with each object material; for example, plastic may be associated with a "tough" parameter, and glass may be associated with a "fragile" parameter. Vehicle 101 may include multiple sensors 110 capable of detecting the characteristics of object 215, such as vehicle image sensors, as described in Table 1 below. Alternatively or additionally, a user may identify the characteristics of object 215 via user device 140.

[0057] Table 1 shows an example source of object data 115 that computer 105 can analyze to determine the properties of object 215.

[0058]

[0059] Table 1

[0060] Table 2 illustrates an example dataset, such as a lookup table, that the computer 105 can store to determine a stow element 122 in the vehicle 101 for an object based on characteristics of the object.

[0061]

[0062] Table 2

[0063] The computer 105 can predict a stow parameter based on the object data 115 and the location data 115. The object data 115 can be characteristics of the object 215. The computer 105 can compare the object 215 characteristics to a list of possible stow parameters. For example, when the object 215 has one or more handles or loops, the computer 105 can determine that the object 215 is hangable and can predict the stow parameter to be “hang.” In this case, the computer 105 can assign the object 215 to the swing arm 122a. As another example, when the material type of the object is at risk of breaking, such as glass, porcelain, etc., the computer 105 can determine that the object is fragile and can predict the stow parameter to be “enclose.” In this case, the computer 105 can assign the object to the storage bin 122c. As yet another example, when the weight and / or size of the object 215 is above a threshold, the computer 105 can determine that the object is large, e.g., the object 215 exceeds the carrying capacity of the swing arm 122a and / or the size of the storage bin 122c, and can predict the stow parameter to be “support.” In this case, the computer 105 can assign the object 215 to the shelf 122b. Alternatively, as described below, the computer 105 can assign the object 215 to the seat back 122d when the seat 120 is in a stow position. The object 215 can exceed the carrying capacity and / or size of the shelf 122b when the computer 105 assigns the object 215 to the seat back 122d, i.e., the weight and / or size of the object 215 can exceed a second threshold. The location data 115 can be geographic coordinate data of the vehicle 101 as described above. The computer 105 can correlate the location data 115 of the vehicle 101 to the object data 115, e.g., the computer 105 can identify objects that are stowed in the vehicle 101 at a particular location. The computer 105 can store the location data 115 and the object data 115 such that the computer 105 can predict particular object data 115 that can be received with particular location data 115, e.g., the computer 105 can predict whether an object will be stowed at a location.

[0064] The computer 105 can predict a loading parameter based on messages sent from each sensor in the set of seat sensors 110. As described above, the seat sensors 110 can detect whether a user is in the seat 120. The computer 105 can actuate the seat 120 from a seated position to a loading position. When the seat sensor 110 detects a user in the seat 120, the seat sensor 110 can send a message to the computer 105, and the computer 105 can hold the seat 120 in the seated position to support the user. Otherwise, the computer 105 can actuate the seat 120 from the seated position, as indicated by the hidden line (i.e., dashed line) in FIG. 1, to the loading position to support an object 215 loaded in the vehicle 101 cabin. For example, when the size and / or weight of the object 215 is above a second threshold, e.g., when the object 215 is larger than the shelf 122b and / or exceeds the load capacity of the shelf 122b, the computer 105 can actuate the seat 120 to the loading position and assign the object to the seat back 122d. Figure 3

[0065] The computer 105 can actuate the loading elements 122 based on the loading parameter, e.g., the loading elements 122 can be associated with the loading parameter. Further for example, the computer 105 can actuate the loading elements 122 from a first position to a second position. For example, each loading element 122 can include an actuator to move the loading element 122 from the first position to the second position. The actuator can be any suitable mechanism such as a motor (e.g., an electric motor) attached to a pivot lever, a hydraulic cylinder attached to a pivot lever. In another example, a spring can bias the loading element 122 to the second position, e.g., a solenoid, a latch, etc. can hold the loading element 122 in the first position, and the computer 105 can send a message to release the solenoid, latch, etc. so that the spring can move the loading element 122 to the second position. The computer 105 can send a message to an effector to move the loading element 122 from the first position to the second position, e.g., to open a cover, lower a shelf, or hook, etc.

[0066] In the first position, the loading element 122 can be positioned in the vehicle 101 such that the loading element 122 is disposed along the interior trim of the vehicle 101, e.g., carpet, pillar trim, seat back, etc., as shown in FIG. 1. In the second position, the loading element 122 can be positioned in the vehicle 101 such that the loading element 122 is disposed along the interior trim of the vehicle 101, e.g., carpet, pillar trim, seat back, etc., as shown in FIG. 1. Figure 2 ​In the second position, the loading element 122 can extend into the vehicle 101 cargo compartment such that the loading element 122 can support one or more objects 215. The computer 105 can predict a loading parameter for each of the plurality of objects 215, for example, the computer 105 can determine a characteristic of each object 215. In this case, the computer 105 can actuate one or more loading elements 122 from the first position to the second position to support each object 215 based on the characteristic of each object 215. In other words, the loading element 122 can be adjusted according to the objects 215 loaded in the vehicle 101.

[0067] Figure 4 An exemplary process 300 for predicting a loading parameter based on a current location and a destination location of the vehicle 101 and actuating a vehicle component 120 based on the loading parameter is shown. The process 300 begins in block 305, where the computer 105 determines a current location of the vehicle 101. As described above, the computer 105 can determine the current location of the vehicle 101 based on geographic coordinates provided via a navigation system, such as a GPS navigation system.

[0068] Next, in block 310, the computer 105 determines a destination location of the vehicle 101. As described above, the computer 105 can determine the destination location of the vehicle 101 based on messages received via the HMI 120, the user device 140 (e.g., the location data 115), a vehicle activity log input to a machine learning program, etc.

[0069] In block 315, computer 105 determines whether the destination location matches, i.e., is within a threshold distance (e.g., 10 meters, 50 meters, 100 meters, etc.) of stored location data, of a specified location. In this context, the destination location can be “matched” to stored location data based on geographic coordinates in location data 115 and one or more sets of geographic coordinates included in map data or other data stored in computer 105 memory (or location data 115 can be a street address or some other set of data for a specified location). Computer 105 memory also typically stores respective location descriptors (e.g., “grocery store,” “shopping center,” “school,” “home,” “post office,” etc.) associated with respective sets of geographic coordinates (latitude and longitude). Location data 115 matches stored location data when it is within a threshold distance (e.g., within a certain radius) of stored location data. As noted above, computer 105 can store objects and / or location data 115 as a vehicle activity log. When location data 115 matches stored location data, e.g., vehicle 101 returns to a previous location based on geographic coordinates, address, etc., a machine learning program can predict object data 115 (e.g., objects 215 to be loaded) to be received at that location using known techniques. If computer 105 determines that location data 115 matches stored location data, process 300 continues to block 320. Otherwise, process 300 continues to block 325.

[0070] In block 320, computer 105 determines whether location data 115 is associated with a loading parameter; computer 105 can query its memory, data storage, etc., to determine whether a loading parameter is stored for location data 115. As noted above, computer 105 can store location data 115 along with object data 115 associated with (e.g., received with) location data 115 to predict objects 215 that will be loaded into vehicle 101 at a particular location, e.g., a current location and / or a destination location. When a probability output by a machine learning program is above a threshold, e.g., an object is likely to be loaded in vehicle 101 at a current location and / or a destination location, computer 105 can predict that loading parameter. If computer 105 determines that location data 115 is associated with a loading parameter, computer 105 can select the loading parameter, and process 300 continues to block 340. Otherwise, process 300 continues to block 325.

[0071] In block 325, the computer 105 predicts whether the object 215 will be loaded in the vehicle 101 at one of the current location and the destination location. As described above, the computer 105 can receive object data 115 associated with the object 215 to be loaded in the vehicle 101. For example, the computer 105 can query its memory, data storage, etc. to determine whether the object data 115 is associated with the user’s location data 115. As another example, the computer 105 can receive reference data 115 (e.g., object data 115 associated with other users’ location data 115) via the network 125 to determine the loading parameters when the object data 115 is not associated with the user’s location data 115. In other words, the reference data 115 can identify objects 215 that are typically loaded in the vehicle 101 at that location. In this case, the computer 105 can predict the loading parameters based on the reference data 115. The computer 105 can analyze the object data 115, e.g., the characteristics of the object 215, to determine whether the object 215 can be loaded, i.e., whether the object fits in the loading location in the vehicle 101. For example, the computer 105 can determine whether the size (e.g., dimensions) and / or weight of the object 215 is above a threshold for the vehicle 101. If the computer 105 determines that the object can be loaded in the vehicle 101, the process 300 continues to block 335. Otherwise, the process 300 continues to block 330.

[0072] In block 330, the computer 105 can send a message to the server 130 requesting a second vehicle via the network 125. The message can include location data 115, e.g., the user’s current location and destination location, and object data 115. The second vehicle can be selected based on the object data 115 (e.g., the object 215 fits in the second vehicle) and the location data 115 (e.g., the location of the second vehicle is within a threshold distance, e.g., a radius, from the current location). After requesting the second vehicle, the process 300 ends.

[0073] In block 335, the computer 105 predicts the loading parameters based on the object data 115. As described above, the computer 105 can determine the loading parameters based on the characteristics of the object 215, and can assign the object to a loading element 122 that corresponds to the loading parameters (e.g., hangable, fragile, heavy, etc.).

[0074] Next, in block 340, the computer 105 actuates the vehicle component 120 based on the loading parameters. For example, the computer 105 can actuate a suspension component from a driving position to a loading position to assist the user in loading the object 215 in the vehicle 101. As another example, the computer 105 can actuate the loading element 122 from a first position to a second position. As described above, the computer 105 can actuate one or more loading elements 122 to support one or more objects 215 in the vehicle 101. After loading the object 215 in the vehicle 101, the computer 105 can actuate the suspension component from the loading position to the driving position, and the process 300 ends.

[0075] As used herein, the adverb modifying adjective "substantially" means that the shape, structure, measurement, value, calculation, etc. can deviate from the precise described geometry, distance, measurement, value, calculation, etc. because of imperfections in the material, machining, manufacturing, data acquirer measurements, calculations, processing time, communication time, etc.

[0076] The computers 105 generally each include instructions executable by one or more computers such as those identified above and for carrying out the blocks or steps of processes described above. Computer-executable instructions can be compiled or interpreted from computer programs created using a variety of programming languages and / or technologies, including, without limitation, and either alone or in combination, Java TM , C, C++, Visual Basic, Java Script, Perl, HTML, etc. In general, a processor (e.g., a microprocessor) receives instructions, from, for example, memory, computer-readable media, etc., and executes these instructions, thereby performing one or more processes, including one or more of the processes described herein. Such instructions and other data can be stored and transmitted using a variety of computer-readable media. A file in the computers 105 is generally a collection of data stored on a computer readable medium, such as a storage media, random access memory, etc.

[0077] Computer-readable media includes any media that participates in providing data (e.g., instructions) that can be read by a computer. This can be accomplished through numerous means, including, for example, non-volatile media, volatile media, etc. Non-volatile media includes, for example, optical or magnetic disks, and other persistent memory. Volatile media includes dynamic random access memory (DRAM), which typically constitutes the main memory. Common forms of computer-readable media include, for example, a floppy disk, a flexible disk, hard disk, magnetic tape, any other magnetic medium, a CD-ROM, DVD, any other optical medium, punch cards, paper tape, any other physical medium with patterns of holes, a RAM, a PROM, and EPROM, a FLASH-EPROM, any other memory chip or cartridge, or any other medium from which a computer can read.

[0078] With respect to the media, processes, systems, methods, etc. described herein, it is to be understood that, although the steps of such processes etc. have been described as occurring according to a certain ordered sequence, such processes could be practiced with the described steps performed in an order other than the order described herein. It is further understood that certain steps could be performed simultaneously, that other steps could be added, or that described steps could be omitted. For example, in process 300, one or more of the steps could be omitted, or steps could be performed in a different order than shown in process 300. In other words, the descriptions of systems and / or processes herein are provided for the purpose of illustrating certain embodiments and are not intended to limit the disclosed subject matter. Figure 4

[0079] Accordingly, it is to be understood that the present disclosure, including the above description and the accompanying drawings and the appended claims, is intended to be illustrative and not restrictive. Many embodiments and applications other than the examples provided would be apparent to those of skill in the art upon reading the above description. The scope of the invention should be determined, not with reference to the above description, but should instead be determined with reference to the appended claims, along with the full range of equivalents to which such claims are entitled. It is anticipated and intended, for example, that future developments in the field of the technology discussed herein will occur and that the disclosed systems and methods will be incorporated into such future embodiments. In general, it is to be understood that the subject matter disclosed is capable of modification and variation.

[0080] Unless otherwise stated, or as is clear from the context, the use of any of the verbs "comprise", "comprises", "comprising", "include", "includes", "including", "contain", "contains", "containing", "have", "has", "having", or "hold" is to be interpreted as specifying the presence of the stated features or steps and is not one of exclusivity.​

Claims

1. A method for a vehicle, comprising: identifying a current location and a destination location of a vehicle; predicting a loading parameter based on inputting characteristics of an object, the current location and the destination location, and a vehicle activity log into a machine learning program, wherein the vehicle activity log stores historical data of vehicle locations at various times and objects stored in the vehicle at various times; and actuating a vehicle component based on the loading parameter; wherein the vehicle component comprises a loading element; actuating at least a portion of the loading element to move from a first location on the vehicle to a second location on the vehicle based on the loading parameter; wherein the loading parameter specifies a manner in which the object is loaded for transport from the current location to the destination location.

2. The method of claim 1, wherein the vehicle component further comprises a suspension component or a seat, the method comprising actuating the suspension component from a driving position to a loading position based on the loading parameter; or the method comprising actuating the seat from a seating position to a loading position based on the loading parameter.

3. The method of claim 1, further comprising predicting one loading parameter for each object of a plurality of objects.

4. The method of claim 1, further comprising receiving a message from a user device, and predicting the loading parameter based on the message from the user device.

5. The method of claim 1, further comprising predicting the loading parameter based on user input.

6. The method of claim 1, further comprising predicting the loading parameter based on a message from each sensor of a set of seat sensors.

7. A system for a vehicle, the system comprising a computer programmed to: identify a current location and a destination location of a vehicle; predict a loading parameter based on inputting characteristics of an object, the current location and the destination location, and a vehicle activity log into a machine learning program, wherein the vehicle activity log stores historical data of vehicle locations at various times and objects stored in the vehicle at various times; and actuate a vehicle component based on the loading parameter; the vehicle component comprises a loading element; actuate at least a portion of the loading element to move from a first location on the vehicle to a second location on the vehicle based on the loading parameter; wherein the loading parameter specifies a manner in which the object is loaded for transport from the current location to the destination location.

8. The system of claim 7, wherein the vehicle component further comprises a suspension component or a seat; the computer is further programmed to: actuate the suspension component from a driving position to a loading position based on the loading parameter, or actuate the seat from a seating position to a loading position based on the loading parameter; the loading element is one of a shelf, a hook, and a storage bin.

9. The system of claim 7, wherein the computer is further programmed to predict one loading parameter for each object of a plurality of objects.

10. The system of claim 7, wherein the computer is further programmed to receive a message from a user device and predict the loading parameter based on the message from the user device.

11. The system of claim 7, wherein the computer is further programmed to predict the loading parameters based on user input.

12. The system of claim 7, wherein the computer is further programmed to predict the loading parameters based on messages from each sensor in a set of seat sensors.

13. A system for a vehicle, comprising: a loading element, a vehicle component comprising the loading element; the loading element comprising an actuator arranged to move at least a portion of the loading element from a first position on the vehicle to a second position on the vehicle; and a computer programmed to: identify a current location and a destination location of the vehicle; predict a loading parameter based on inputting characteristics of an object, the current location and the destination location, and a vehicle activity log to a machine learning program, wherein the vehicle activity log stores historical data of vehicle locations at various times and objects stored in the vehicle at various times; and actuate the vehicle component based on the loading parameter; wherein the loading parameter specifies a manner in which to load the object for transport from the current location to the destination location.

Images