Abstract: A method and system where a first subsystem makes observations and performs surveillance using sensors in a mode that conserves a resource such as power, data transmission band width or processing cycles. This is accomplished by reducing illumination, pixel count, sampling rate or other functions that result in a limited granularity or data collection rate. A machine model is applied to the limited data and, when it evaluates to a suitable result or a prediction of an interesting condition, another subsystem or the same subsystem in a different mode collects data at a finer granularity with a higher data collection size or rate and evaluates that data to determine the nature of the first evaluation. The machine model may be trained in stages on a large scale server and on a small field processor. Data from the sensor may be used for training to improve the second step.

Abstract: A method and system where a first subsystem makes observations and performs surveillance using sensors in a mode that conserves a resource such as power, data transmission band width or processing cycles. This is accomplished by reducing illumination, pixel count, sampling rate or other functions that result in a limited granularity or data collection rate. A machine model is applied to the limited data and, when it evaluates to a suitable result or a prediction of an interesting condition, another subsystem or the same subsystem in a different mode collects data at a finer granularity with a higher data collection size or rate and evaluates that data to determine the nature of the first evaluation. The machine model may be trained in stages on a large scale server and on a small field processor. Data from the sensor may be used for training to improve the second step.

Abstract: A system and method of navigating in areas. A machine learning model is trained in multiple levels with data concerning basic interpretation of sensors and with analysis of the layout of areas. The model is downloaded to a second processor which may further train the model with sensor data gathered after the download. Additional sensor data along with data from a server or other sources may be used as an input to the model and the second or another processor evaluates the model with the inputs to create outputs which determine the state of compliance. Specific applications include movement around in areas of interest. A vehicle which is controlled by a driver or by data from the machine loading model and it's analysis may be included. The model is used to calculate a path which may be displayed in visual, auditory or tactile modes.

Abstract: A method includes, by a central computing device, receiving instructions to provide access to an autonomous vehicle of multiple autonomous vehicles in a parking area, identifying one or more blocking autonomous vehicles of the multiple autonomous vehicles to be moved to provide access to the autonomous vehicle, and causing each of the blocking autonomous vehicles to perform a pre-computed movement based on a determined state of the blocking autonomous vehicle, wherein the blocking autonomous vehicle performing the pre-computed movement allows the first autonomous vehicle to be accessible.

Abstract: A method includes receiving, by a computing device of an autonomous vehicle of multiple autonomous vehicles, instructions to travel to a target location, determining, by the computing device of the autonomous vehicle, that the autonomous vehicle is blocked from traveling to the target location by one or more blocking autonomous vehicles of the multiple autonomous vehicles located at one or more blocking locations, and causing, by the computing device of the autonomous vehicle, coordinated movements by the autonomous vehicle and the one or more blocking autonomous vehicles to be performed to allow the autonomous vehicle to travel to the target location, wherein the coordinated movements include at least one of the blocking autonomous vehicles returning to its respective blocking location after allowing the autonomous vehicle to travel to the target location.

Abstract: A method includes, by a central computing device, determining that a first autonomous vehicle at a first location is to relocate to a second location, wherein a pathway for the first autonomous vehicle to reach the second location is blocked by one or more second autonomous vehicles, computing coordinated movements for multiple autonomous vehicles including the first autonomous vehicle and the one or more second autonomous vehicles, wherein the coordinated movements are computed to allow the first autonomous vehicle to reach the second location and the coordinated movements include having the first autonomous vehicle wait until after at least one of the second autonomous vehicles performs its coordinated movements, and causing the multiple autonomous vehicles to execute the coordinated movements.

Abstract: A method includes, by a central computing device, receiving instructions to provide access to a first autonomous vehicle of multiple autonomous vehicles in an array, wherein the first autonomous vehicle is blocked by one or more blocking autonomous vehicles of the multiple autonomous vehicles in the array, and causing coordinated movements to be performed by one or more blocking autonomous vehicles to create a gap in the array, wherein the gap provides a temporary access aisle to provide access to the first autonomous vehicle.

Abstract: A method, by a computing device of a first autonomous escort vehicle of a convoy that includes multiple autonomous escort vehicles, that includes: receiving, from a central computing device associated with the convoy, an instruction to prevent one or more environmental vehicles from interfering with movements of the convoy, wherein the instruction is determined by the central computing device based on first sensor data from one or more autonomous escort vehicles in the convoy and the movements of the convoy; determining, based on second sensor data from one or more sensors of the first autonomous escort vehicle, a set of movements for preventing the one or more environmental vehicles from interfering with the movements of the convoy; and performing the set of movements.

Abstract: A method includes determining that an autonomous vehicle is in a zone associated with one or more zone rules; causing, in response to determining that the autonomous vehicle is in the zone, the autonomous vehicle to operate in a controlled mode of operation associated with the zone rules; determining that the autonomous vehicle has exited the zone; and releasing, in response to determining that the autonomous vehicle has exited the zone, the autonomous vehicle from the controlled mode of operation.

Abstract: In one embodiment, a method includes receiving sensor data from one or more sensors of each of one or more vehicles, processing a combination of the sensor data to generate an assessment of an area surrounding the one or more vehicles based on one or more points-of-view of the area, the one or more points-of-view of the area generated based on synchronizing the combination of the sensor data, and detecting an occurrence of an event based on the assessment of the area. The method further includes identifying one or more instructions corresponding to the event, the instructions associated with a particular vehicle and sending one or more executable instructions based on the instructions to the particular vehicle.

Abstract: A system and method for counting persons using passages to an area by analyzing vibrations in the floor or the air above the floor with sensors and a machine learning system. The machine learning system uses a model, usually implemented as a neural network on a processor. The network is trained in levels and implemented in layers. Different levels classify and analyze vibrations by timing and frequency, by movements of persons, and by identity of persons The same person is identified by patterns in the vibrations and the vibrations are correlated to determine and count when a person uses a combination of passages. Location information for the person is used to identify persons in places and doing activities of interest. The model may be trained on one processor and downloaded to another processor for evaluation. Additional sensors and levels of training may be implemented on the latter processor.

Abstract: An autonomous vehicle which may be miniature in size vehicle for operation on the public roads is disclosed. The vehicle carriers a marker which makes the vehicle more visible. The marker is varied in illumination, reflectivity, position or other ways to increase visibility at selected times. The variation may be controlled by a sensor detecting a nearby vehicle, the condition of other vehicles and the speed or other state of the subject vehicle. The purpose is to avoid accidents. The motion of the marker may affect stability of wind resistance of the vehicle. A processor can evaluate sensor and other information to decide the variations with a first determination to place the marker or visibility element in a first condition and a second determination to place the marker or visibility element in a second condition. Speeds of the subject vehicle and other vehicles may be taken into account.

Abstract: A method of confirming the identity of a person issued a token and to track that person Possession of the token by the same person is confirmed by using sensors in the token which track the movements of the person. A machine learning system is trained to evaluate the sensor data detecting transfer of possession of the token. The state of continuous possession since the token was issued or set to an enabled state is confirmed and the token is tracked. The method of identity confirmation is used in various contexts such as for to control entry to a location, use of a facility or service. It is also useful to determine continuous possession of a weapon to prevent misuse after the weapon is stolen, dropped or lost. Servers, beacons and outside sources of data or inputs to be measured by the sensor can also be used.

Abstract: A method and system where a first subsystem makes observations and performs surveillance using sensors in a mode that conserves a resource such as power, data transmission band width or processing cycles. This is accomplished by reducing illumination, pixel count, sampling rate or other functions that result in a limited granularity or data collection rate. A machine model is applied to the limited data and, when it evaluates to a suitable result or a prediction of an interesting condition, another subsystem or the same subsystem in a different mode collects data at a finer granularity with a higher data collection size or rate and evaluates that data to determine the nature of the first evaluation. The machine model may be trained in stages on a large scale server and on a small field processor. Data from the sensor may be used for training to improve the second step.

Abstract: A system and method of navigating in areas. A machine learning model is trained in multiple levels with data concerning basic interpretation of sensors and with analysis of the layout of areas. The model is downloaded to a second processor which may further train the model with sensor data gathered after the download. Additional sensor data along with data from a server or other sources may be used as an input to the model and the second or another processor evaluates the model with the inputs to create outputs which determine the state of compliance. Specific applications include movement around in areas of interest. A vehicle which is controlled by a driver or by data from the machine loading model and it's analysis may be included. The model is used to calculate a path which may be displayed in visual, auditory or tactile modes.

Abstract: A method and a system to present samples of products to customers by transporting the samples to the customer's location with an autonomous vehicle. The sample can be a product, a component of a product, a material or a device to gather information in defining the product. The autonomous vehicle is adapted for off road travel and may enter buildings, it can be carried to a nearby location by a street adapted vehicle. Information may be transmitted electronically but physical presence is essential. The customer or the customer's agent receives a presentation of the product definer and a selection of a final product is made. In other cases the autonomous vehicle delivery separate or installed technical equipment to examine the presentation location and assist in the final product selection. For example, photographs from multiple locations can measure a room for installation of carpets or draperies, etc.

Abstract: A system and method for counting persons using passages entering or exiting an area by analyzing vibrations in the floor with sensors and a machine learning system. The machine learning system uses a model, usually implemented as a neural network on a processor. The network is trained in levels and implemented in layers. Different levels classify and analyze vibrations by timing and frequency, by movements of persons, and by identity of persons The same person is identified by patterns in the vibrations and the vibrations are correlated to determine when a person uses a combination of passages and is thereby counted. Location information for the person is used to identify persons in places and doing activities of interest. The model may be trained on one processor and then downloaded to another processor for evaluation. Additional sensors and levels of training may be implemented on the latter processor.

Abstract: A miniature autonomous vehicle for operation on the public roads is disclosed. The small size allows efficiency for small payloads, but produces a danger of being overlooked by other vehicles. The size of the vehicle is less than driver operated vehicles and may be restricted to less than 200 pounds. Sensors determine the vehicles speed and the presence of environmental vehicles and use a processor to calculate the need for additional visibility. A visibility structure and support structure with lights or markers is controlled by the processor. The markers are controlled in their operation or position by the processor on the basis of the sensor data. Extending or raising and retracting or lowering the structure affects the air resistance and stability of the vehicle. The structure can be raised when the vehicle stops or is in traffic and lowered at road speeds in light or absent traffic.

Abstract: A method includes receiving a request for access associated with a pre-assigned parking space of a particular one of a plurality of autonomous vehicles in a parking area, determining that the pre-assigned parking space of the particular autonomous vehicle has at least one blocking parking space that is pre-assigned to another autonomous vehicle, determining a state of the at least one blocking parking space with respect to the autonomous vehicle pre-assigned to it, and accessing pre-computed coordinated movements for the autonomous vehicles corresponding to the state of the at least one blocking parking space to provide the requested access.

Abstract: A method including computing coordinated movements for a plurality of autonomous vehicles to provide access to a particular one of the autonomous vehicles, wherein each of the coordinated movements is computed to avoid movement of any one of the autonomous vehicles interfering with movement of any other one of the autonomous vehicles, and the requested access comprises one or more passengers entering into or exiting from the particular one of the autonomous vehicles, and causing the autonomous vehicles to execute autonomously the coordinated movements to provide the requested access. In addition, or alternatively, the requested access may comprise cargo being loaded into or unloaded from the particular one of the autonomous vehicles.