Abstract: An unmanned aerial vehicle (UAV) landing method includes detecting, via one or more visual sensors, a gesture or movement of an operator of a UAV; and controlling to decelerate, with aid of one or more processors and in response to the detected gesture or movement, one or more rotor blades of the UAV to cause the UAV to land autonomously.

Abstract: A novel imaging system is provided for capturing imaging data. According to the disclosed embodiments, the imaging system comprises one or more cameras configured to capture the same scene within each camera's field of view. The imaging system also includes a plurality of bandpass filters that may be positioned in front of one or more cameras. Each bandpass filter may allow the transmission of incident electromagnetic signals between different pairs of first and second wavelengths. Accordingly, when the bandpass filters are positioned in front of the one or more cameras, each camera captures a different spectral image, i.e., containing only certain frequency components of the same scene being imaged in the cameras. The bandpass filters may be selectively aligned with one or more cameras by rotating and/or translating the filters relative to the cameras' positions in the imaging system.

Abstract: A method for controlling a gimbal includes detecting a motion of the gimbal, determining whether a received control signal indicates that the motion of the gimbal corresponds to a user-intended motion, controlling the gimbal to move along a moving direction of the motion in response to determining that the received control signal indicates the motion of the gimbal corresponds to the user-intended motion, and controlling the gimbal to move along an opposite direction to the moving direction of the motion in response to determining that the received control signal does not indicate the motion of the gimbal corresponds to the user-intended motion.

Abstract: Calculations are performed, based on a switching criterion, to select at least one of a direct communication link or an indirect communication link to transmit data between a movable object and a remote terminal. The data is transmitted using the at least one of the direct communication link or the indirect communication link selected based on the calculations. During at least a portion of a duration for the transmission of the data using the at least one of the direct communication link or the indirect communication link, backup data is transmitted using a backup communication link to ensure connectivity between the movable object and the remote terminal in event of interruption in the selected at least one of the direct communication link or the indirect communication link occurs. The backup data including at least a portion of the data transmitted between the movable object and the remote terminal.

Abstract: A system includes an optical element configured to separate light into a first light beam and a second light beam, a first optical module configured to capture a first image having a first field of view from the first light beam, a second optical module configured to capture a second image having a second field of view different from the first field of view from the second light beam, and one or more processors configured to generate a scaled image by scaling one of the first image or the second image, and generate a combined image by aligning the scaled image and an unscaled one of the first image or the second image.

Abstract: An unmanned aerial vehicle (UAV) includes an audio source collecting microphone detecting a target audio signal, background noise-producing components producing background noise different from the target audio signal, background microphones collecting the background noise, and noise emitters each configured to reduce the background noise by emitting an audio signal having a reverse phase of the collected background noise collected by the corresponding background microphone. The background microphones further collect reduced background noise. The UAV further includes a processor receiving signals which comprise the target audio signal and the reduced background noise, and generating a processed signal based on the collected reduced background noise to reduce interference by the background noise to the target audio signal.

Abstract: The present disclosure provides a laser diode package module. The laser diode package module includes a substrate including a first surface; a cover disposed on the first surface of the substrate; an accommodation space formed between the substrate and the cover; a laser diode die disposed in the accommodation space; and a reflective surface disposed in the accommodation space for outputting light of the laser diode die reflected by the reflective surface and transmitted through a light-transmitting area. The light-transmitting area is at least partially disposed on a surface of the cover opposite the substrate.

Abstract: Systems and devices to perform knowledge-driven dynamic conversations and select content within automated agents such as chatbots and virtual assistants are disclosed. In an example, operations to facilitate a knowledge-based conversation session with a human user using an automated agent include: receiving a conversational input regarding a support issue; analyzing the conversational input to determine an intent and applicable entity properties associated with the intent; performing a multi-turn conversation to identify a solution using the intent and the applicable entity properties, by exchanging iterative questions and answers between the automated agent and the user to dynamically recalculate applicability of the solution to the support issue; and outputting information associated with the identified solution.

Abstract: Techniques are disclosed for sharing sensor information between multiple vehicles. A system for sharing sensor information between multiple vehicles, can include an aerial vehicle including a first computing device and first scanning sensor, and a ground vehicle including a second computing device and second scanning. The aerial vehicle can use the first scanning sensor to obtain first scanning data and transmit the first scanning data to the second computing device. The ground vehicle can receive the first scanning data from the first computing device, obtain second scanning data from the second scanning sensor, identify an overlapping portion of the first scanning data and the second scanning data based on at least one reference object in the scanning data, and execute a navigation control command based on one or more roadway objects identified in the overlapping portion of the first scanning data and the second scanning data.

Abstract: Techniques are disclosed for collaborative map construction using multiple vehicles. Such a system may include a ground vehicle including a first computing device and a first scanning sensor, and an aerial vehicle including a second computing device and a second scanning sensor. The ground vehicle can obtain a first real-time map based on first scanning data using the first scanning sensor, and transmit a first real-time map and position information to the aerial vehicle. The aerial vehicle can receive the first real-time map and the position information from the first computing device, obtain a second real-time map based on second scanning data collected using the second scanning sensor, and obtain a third real-time map based on the first real-time map and the second real-time map.

Abstract: Techniques for monitoring vehicle traffic are disclosed. A vehicle monitoring system comprises one or more sensing devices disposed within a vicinity of one or more vehicles in a road environment and one or more sensors on-board the one or more sensing devices, wherein said one or more sensors operate to collect information of the one or more vehicles in the road environment. Furthermore, the vehicle monitoring system comprises a data manager, running on one or more microprocessors, wherein the data manager operates to receive the collected information of the one or more vehicles, and analyze the collected information of the one or more vehicles to monitor the one or more vehicles in the road environment.

Abstract: A method for controlling an unmanned aerial vehicle (UAV) includes receiving, by a processor of the UAV, a plurality of images captured by an imaging device coupled to the UAV, identifying, by the processor, a target in at least one image of the plurality of images, determining, by the processor, whether the target is a stationary target or a moving target based on analyzing the plurality of images, and automatically effecting, by the processor, movement of the UAV based on determining the target is the stationary target or the moving target.

Abstract: An environment sensing method includes obtaining sound data captured by a sound sensor and image data captured by a vision sensor, and determining an environment recognition result according to the sound data and the image data.

Abstract: Improved methods, systems and apparatus for storing and repairing multimedia files are provided that overcome the limitations of existing multimedia file repair technologies. Backup copies of the multimedia container information associated with given multimedia content data are stored, along with the multimedia content data, on an external storage detachably coupled to a recording device. A primary copy of the multimedia container information is stored on an internal storage associated with the recording device. The recording of the primary container information and the content data is performed in real-time or nearly real-time as the content data is captured by the recording device. In the case of an abnormal event (e.g., battery failure, disconnect of storage media), container information may be selected from the primary copy or the backup copies of the container information, thereby increasing the likelihood that the container file can be successfully repaired or regenerated.

Abstract: An imaging system includes a first optical module including a first image sensor, a second optical module comprising a second image sensor, and an image processor. The first optical module has a first focal length range. The second optical module has a second focal length range. The first focal length range and the second focal length range are different. The image processor is configured to receive image data for a first image from the first optical module and/or image data for a second image from the second optical module and generate data to show the first image and/or the second image within a display.

Abstract: An unmanned aerial vehicle (UAV) landing method includes detecting, via one or more sensors on-board the UAV, a positional change of the UAV while the UAV is airborne; and generating, with aid of one or more processors on-board the UAV and in response to the detected positional change, one or more command signals to decelerate one or more rotor blades of the UAV, thereby causing the UAV to land autonomously.

Abstract: The present disclosure provides a method for vehicle deviation warning. The method includes obtaining vibration data when a vehicle vibrates; determining whether the vehicle deviated from a driving lane based on the vibration data; and issuing a warning signal if the vehicle deviated from the driving lane.

Abstract: A novel imaging system is provided for capturing imaging data. According to the disclosed embodiments, the imaging system comprises one or more cameras configured to capture the same scene within each camera's field of view. The imaging system also includes a plurality of bandpass filters that may be positioned in front of one or more cameras. Each bandpass filter may allow the transmission of incident electromagnetic signals between different pairs of first and second wavelengths. Accordingly, when the bandpass filters are positioned in front of the one or more cameras, each camera captures a different spectral image, i.e., containing only certain frequency components of the same scene being imaged in the cameras. The bandpass filters may be selectively aligned with one or more cameras by rotating and/or translating the filters relative to the cameras' positions in the imaging system.

Abstract: An apparatus for housing an unmanned aerial vehicle (UAV) in or on a vehicle includes a landing connection component configured to form a connection between the UAV and the vehicle when the UAV is landed in or on the vehicle, and a cover movable between a plurality of positions to permit the UAV to take off and land in or on the vehicle. The cover includes an antenna or a satellite dish integrated thereto. An orientation of the antenna or the satellite dish is adjustable for tracking a motion of the UAV when the UAV is in flight.

Abstract: Mappings of keys to actions can automate various vehicle systems. Some automations can provide lane departure warnings or emergency light reminders. Mapping keys can be matched based on vehicle condition data gathered from vehicle sensors. When a mapping key matches vehicle condition data, the vehicle action automation system can cause the vehicle to perform the one or more actions from that mapping. Mapping keys can be rules-based and/or model-based. Keys for lane departure mappings can specify vibration patterns expected when a vehicle drives over lane delineators. These vibration-based mappings can include keys with vibration patterns, e.g., defining vibration frequencies or vibration locations. Keys for emergency light mappings can be based on conditions such as (1) the vehicle being on the road, stopped, not in traffic, and not at a stop signal; (2) components of the vehicle having failed; or (3) weather conditions.