Qualcomm Incorporated

Qualcomm Technologies, Inc.

Michael-David Nakayoshi Canoy

Kiet Tuan Chau

Paul E Bender

Stephen Alton Sprigg

Robert Howard Kimball

Michael Orlando DeVico

Yinyin Liu

Jason Frank Hunzinger

Roy Franklin Quick, Jr

Raymond T Hsu

Victor Hokkiu Chan

Anthony Sarah

Daphna Zeilingold

Jan Krzys Wegrzyn

Adrienne Milner

Ronen Stern

Susan Lynn Silveira

Ramakrishna Kintada

Vicki Christine Mealer-Burke

Eric Darnell Larkin, Sr

Kristin Parsley Atkins

Parag Arun Agashe

Qiang Wu

Eugene Izhikevich

Bibhu P Mohanty

Oleg Sinyavskiy

Jeffrey Alexander Levin

Filip Lukasz Piekniewski

Botond Szatmary

Csaba Petre

Venkat Rangan

Rajesh K Pankaj

Michael Alexander Howard

Noam A Ziv

Zachary Rattner

Siddharth Mohan

Anne Katrin Konertz

Mehraban Iraninejad

Jeff A Levin

Rohan Salvi

Greg M Hoagland

Boris Tsybakov

Sisil Sanjeev Mehta

Jonathan James Hunt

Eric Martin Hall

William Richard Bell, Ii

Senthilkumar Kaliannan Sundaram

Gina Marcela Escobar Mora

Kirtika Ruchandani

Gregory Cisewksi

Michael Orlando Devico

Sr Eric Darnell Larkin

Boris S Tsybakov

Methods and devices of various embodiments provide enhanced location services by leveraging a system of beacon devices each broadcasting data that is useful in calculating locations and report of the trustworthiness of neighbor beacon devices. Various embodiments include a method performed by a beacon device that may include obtaining location data using a first functionality, evaluating sensor data to identify a breach of trust condition at the beacon device, generating authentication data that indicates any identified breach of trust condition, receiving one or more neighbor beacon broadcast messages using a second functionality, determining whether the one or more neighbor beacon broadcast messages include trustworthy location data, and broadcasting an outgoing broadcast message that includes the obtained location data, timing data, the generated authentication data, and data indicating whether the one or more neighbor beacon broadcast messages include trustworthy location data.

Ground-based location systems and methods

Various embodiments provide methods for controlling landings of a UAV in a landing zone including a plurality of landing bays. Various embodiments include a method implemented on a computing device for receiving continuous real-time sensor data from a transceiver and from sensors onboard the UAV, and detecting a target landing bay within the plurality of landing bays within the landing zone that is available for landing based on the continuous real-time sensor data. Orientation and position coordinates for landing in the target landing bay may be calculated based on the continuous real-time sensor data. Information regarding positions and flight vectors of a plurality of autonomous UAVs may be obtained, and a flight plan for landing in the target landing bay may be generated based on the orientation and the position coordinates, positions and flight vectors of the plurality of autonomous UAVs and a current orientation and position of the UAV.

Autonomous landing and control

Methods, systems, and devices are disclosed for providing control of an unmanned aircraft (UA). A server may receive an indication from a UA that a transition from autonomous flight to pilot controlled flight is required while the UA is in autonomous flight. The server may select a pilot station for providing pilot controlled flight of the UA. Selecting a pilot station for providing pilot controlled flight of the UA may be based on a pilot criterion associated with the pilot station. A UA may detect a condition that requires a transition from autonomous flight to pilot controlled flight and establish a pilot criterion for pilot controlled flight based on the detected condition. The UA may send a request for a pilot that includes the pilot criterion and information about the condition.

Systems and methods for remote distributed control of unmanned aircraft

A method of generating executable code for a target platform in a neural network includes receiving a spiking neural network description. The method also includes receiving platform-specific instructions for one or more target platforms. Further, the method includes, generating executable code for the target platform(s) based on the platform-specific instructions and the network description.

Compiling network descriptions to multiple platforms

An embodiment method for continuous configuration of learning devices includes operations for storing, by a learning device within a decentralized system of a plurality of learning devices, events obtained while in a monitoring mode, activating a triggered mode for a reflex when at least one of the stored events corresponds to a trigger pattern, determining whether the reflex has a trigger weight exceeding a trigger weight threshold, conducting the predetermined action associated with the reflex when the trigger weight exceeds the trigger weight threshold, obtaining at least one additional event while in the triggered mode, adjusting the trigger weight of the reflex when the at least one additional event corresponds to a correction pattern or a reward pattern occurring in response to conducting the predetermined action, and creating a second reflex when the at least one additional event does not correspond to a known pattern.

Learning device with continuous configuration capability

Methods and apparatus are provided for using a breakpoint determination unit to examine an artificial nervous system. One example method generally includes operating at least a portion of the artificial nervous system; using the breakpoint determination unit to detect that a condition exists based at least in part on monitoring one or more components in the artificial nervous system; and at least one of suspending, examining, modifying, or flagging the operation of the at least the portion of the artificial nervous system, based at least in part on the detection.

Methods and apparatus for implementing a breakpoint determination unit in an artificial nervous system

Various embodiments for conducting proxy teaching for learning devices within a decentralized system, including an embodiment method with operations for obtaining, by a teacher signaling device, objectives data related to activities of one or more of the learning devices, generating, by the teacher signaling device, teaching routines based on the obtained objectives data, and broadcasting, by the teacher signaling device, teaching signals configured to teach one or more of the learning devices based on the generated teaching routines. Other embodiments may obtain objectives data by requesting reflex information from the learning devices or intercepting event report messages transmitted by the learning devices. Other embodiments may include broadcasting discovery signals to identify nearby learning devices and modifying teaching routines when objectives of the generated teaching routines cannot be achieved. Other embodiments may include transmitting an authorization request to a user device to determine whether to broadcast teaching signals.

Signaling device for teaching learning devices

Apparatus and methods for developing parallel networks. Parallel network design may comprise a general purpose language (GPC) code portion and a network description (ND) portion. GPL tools may be utilized in designing the network. The GPL tools may be configured to produce network specification language (NSL) engine adapted to generate hardware optimized machine executable code corresponding to the network description. The developer may be enabled to describe a parameter of the network. The GPC portion may be automatically updated consistent with the network parameter value. The GPC byte code may be introspected by the NSL engine to provide the underlying source code that may be automatically reinterpreted to produce the hardware optimized machine code. The optimized machine code may be executed in parallel.

Apparatus and methods for developing parallel networks using a general purpose programming language

A method for generating an event includes monitoring a first neural network with a second neural network. The method also includes generating an event based on the monitoring. The event is generated at the second neural network. The event may be generated based on a spike received at the second network during the monitoring.

Monitoring neural networks with shadow networks

Methods, systems, and process-readable media include an autonomous vehicle override control system that receives override commands from a pilot qualified on a first type of unmanned autonomous vehicle (UAV) and translates the inputs into suitable commands transmitted to a target UAV of a second UAV type. A pilot's certification for a first UAV type may be determined from the pilot's login credentials. The system may obtain a first control model for the first UAV type and a second control model for the target UAV. Pilot input commands processed through the first control model may be used to calculate movements of a virtual UAV of the type. The system may estimate physical movement of the target UAV similar to the first physical movement, and generate an override command for the target UAV using the second control model and the second physical movement. Control models may accommodate current conditions and pilot experience.

Control normalization for unmanned autonomous systems

Methods and apparatus are provided for training a neural device having an artificial nervous system by modulating at least one training parameter during the training. One example method for training a neural device having an artificial nervous system generally includes observing the neural device in a training environment and modulating at least one training parameter based at least in part on the observing. For example, the training apparatus described herein may modify the neural device's internal learning mechanisms (e.g., spike rate, learning rate, neuromodulators, sensor sensitivity, etc.) and/or the training environment's stimuli (e.g., move a flame closer to the device, make the scene darker, etc.). In this manner, the speed with which the neural device is trained (i.e., the training rate) may be significantly increased compared to conventional neural device training systems.

Methods and apparatus for modulating the training of a neural device

Methods, systems and devices for implementing different modes or persona of a wireless communication device that allow the wireless communication device to function as multiple devices corresponding to conditions and circumstances that may be defined by an enterprise. Operating modes or persona may be defined by a set of operating characteristics that may include user permissions, device functionality, capabilities enabled, and user restrictions that may be selected by the enterprise. Automatic switching between modes/persona may be controlled through triggers based on any of location, proximity, time, and context of the wireless communication device. Automatic switching of mode control capabilities may also controlled through such triggers, enabling an enterprise to limit the ability of users to override the automatic mode/persona implemented in response to an enterprise-defined trigger.

Automatic switching of modes and mode control capabilities on a wireless communication device

An embodiment delay device for use within a decentralized system of learning device delays broadcast messages to introduce a time shift into events. The delay device may receive a first message from a triggering device, generate a first pattern using at least a first event based on the received first message, determine whether the first pattern matches a known trigger pattern, wait a predetermined delay period in response to determining that the first pattern matches the known trigger pattern, and broadcast a second message in response to the predetermined delay period expiring. Delay periods may be user-configurable, such as via user inputs (e.g., dials, sliders, etc.) or learned based on messages from responding devices. The second message may be similar to the first message or a distinct message indicating the elapse of the delay period.

Delayed actions for a decentralized system of learning devices

Methods, devices, systems, and non-transitory process-readable media for evaluating operating conditions of an autonomous aircraft before performing a mission by executing brief near-flight testing maneuvers at a low elevation. A processor of the autonomous aircraft may receive near-flight testing maneuver instructions that indicate a near-flight testing maneuver to be executed by the autonomous aircraft. The processor may control motors to cause the aircraft to execute a near-flight testing maneuver within a testing area, obtain data indicating stability and performance information while executing the near-flight testing maneuvers, and take an action in response to the obtained data. Actions may include adjusting a position of a payload, a weight, or a portion of the aircraft based on the obtained data, and adjusting a flight plan. The near-flight testing maneuvers may include a sequence of moves for testing stability of the aircraft and payload executing a flight path under anticipated flying conditions.

Near-flight testing maneuvers for autonomous aircraft

Systems, methods, and devices of the various embodiments enable content controls to be implemented by a modem of a mobile device to ensure the controls are implemented regardless of whether an application processor of the mobile device has been rooted. In an embodiment, content controls may be implemented by a modem or list component separate from the application processor when in a subsidized content delivery mode. In an embodiment, content controls may include a whitelist and/or a blacklist of IP addresses that addresses of content requests may be compared against to filter authorized content from unauthorized content. Content requests for authorized content may be sent to the content location, while content requests for unauthorized content may be dropped. In the various embodiments, a whitelist and/or blacklist may be updated on demand and/or automatically by a whitelist/blacklist management portal.

Network access and control for mobile devices

Growing community of inventors

San Diego, CA, United States of America

Michael-David Nakayoshi Canoy