Abstract: A method for controlling a movable object includes obtaining current location information of an obstacle while the movable object tracks a target, determining whether the obstacle is located in a reactive region relative to the movable object based on the current location information of the obstacle. In response to determining that the obstacle is located in the reactive region, the method further includes determining, based on the current location information of the obstacle, whether the obstacle is located in a first sub-region or a second sub-region of the reactive region, where an area of the second sub-region is smaller than an area of the first sub-region; in response to determining that the obstacle is located in the first sub-region, reducing an acceleration of the movable object; and in response to determining that the obstacle is located in the second sub-region, reducing a velocity of the movable object.

Abstract: A method for controlling a movable object includes obtaining current location information of an obstacle while the movable object tracks a target, determining whether the obstacle is located in a reactive region relative to the movable object based on the current location information of the obstacle, and, in response to determining that the obstacle is not located in the reactive region, selecting an optimized set of candidate movement characteristics having an optimized route optimization score from multiple sets of candidate movement characteristics, and adjusting one or more movement characteristics of the movable object based on the optimized set of candidate movement characteristics such that a distance between the movable object and the obstacle is maintained at or beyond a predefined distance. Each set of candidate movement characteristics among the multiple sets of candidate movement characteristics corresponds to a route optimization score.

Abstract: A method for controlling a movable object includes detecting a live object within a proximity of the movable object, determining an operation mode to operate the movable object with the live object detected within the proximity of the movable object, and applying a control scheme associated with the operation mode to control an operation of the movable object.

Abstract: An image rectification method includes determining one or more reference points in a raw image captured using a lens for a plurality of target pixels in a target image, obtaining a subsection of the raw image based on the one or more reference points, and calculating a target pixel value for each of the plurality of target pixels based on one or more pixel values of one or more pixels in the subsection of the raw image.

Abstract: Local sensing based navigation maps can form a basis for autonomous navigation of a mobile platform. An example method includes obtaining real-time environment information that indicates an environment within a proximity of the mobile platform based on first sensor(s) carried by the mobile platform, detecting navigation features based on sensor data obtained from the first sensor(s) or second sensor(s) carried by the mobile platform, integrating information corresponding to the navigation features with the environment information to generate a local navigation map, and generating navigation command(s) for controlling a motion of the mobile platform based on the local navigation map.

Abstract: A method for controlling a movable object includes obtaining current location information of an obstacle while the movable object tracks a target, determining whether the obstacle is located in a reactive region relative to the movable object based on the current location information of the obstacle, and, in response to determining that the obstacle is not located in the reactive region, selecting an optimized set of candidate movement characteristics having an optimized route optimization score from multiple sets of candidate movement characteristics, and adjusting one or more movement characteristics of the movable object based on the optimized set of candidate movement characteristics such that a distance between the movable object and the obstacle is maintained at or beyond a predefined distance. Each set of candidate movement characteristics among the multiple sets of candidate movement characteristics corresponds to a route optimization score.

Abstract: The present disclosure provides an environment sensing system. The sensing system includes a laser detection module, the laser detection module including a first laser module, a second laser module, a third laser module, and a fourth laser module, a field of view (FOV) angle of each laser module being less than or equal to 120°. The first laser module and the second laser module are disposed on a front side of a movable platform to detect an area in front of the movable platform, the FOVs of the first laser module and the second laser module partially overlap. The third laser module and the fourth laser module are respectively disposed on both sides of the movable platform to detect a front left area and a front right area of the movable platform.

Abstract: The present disclosure provides a method for controlling a lidar device. The method includes obtaining a first irradiation amount or a first irradiance generated by the lidar device on a laser irradiated object; and controlling the lidar device based on the first irradiation amount or the first irradiance.

Abstract: A method for controlling a movable object includes acquiring one or more images captured by an imaging device borne by the movable object and at least partially blocked by an obstructive object attached to the movable object, detecting at least portion of the obstructive object projected in the one or more images, and processing the one or more images with the projected obstructive object to assist an operation of the movable object.

Abstract: A method for controlling a movable object includes obtaining current location information of an obstacle while the movable object tracks a target, and determining whether a location of the obstacle corresponds to a reactive region relative to the movable object based on the current location information of the obstacle. In response to determining that the location of the obstacle corresponds to the reactive region, one or more movement characteristics of the movable object is adjusted in a reactive manner to prevent the movable object from colliding with the obstacle. In response to determining that the location of the obstacle does not correspond to the reactive region, the one or more movement characteristics of the movable object is adjusted in a proactive manner to maintain a distance between the movable object and the obstacle to be larger than a predefined distance.

Abstract: A method for supporting image processing for a movable object includes acquiring one or more images captured by an imaging device borne by the movable object. The imaging device is at least partially blocked by an obstructive object attached to the movable object. The method further includes applying a template to the one or more images to obtain one or more projected locations of the obstructive object within the one or more images and detecting at least portion of the obstructive object at the one or more projected locations within the one or more images.

Abstract: The subject matter described herein includes a modular and extensible approach to integrate noisy measurements from multiple heterogeneous sensors that yield either absolute or relative observations at different and varying time intervals, and to provide smooth and globally consistent estimates of position in real time for autonomous flight. We describe the development of the algorithms and software architecture for a new 1.9 kg MAV platform equipped with an IMU, laser scanner, stereo cameras, pressure altimeter, magnetometer, and a GPS receiver, in which the state estimation and control are performed onboard on an Intel NUC 3rd generation i3 processor. We illustrate the robustness of our framework in large-scale, indoor-outdoor autonomous aerial navigation experiments involving traversals of over 440 meters at average speeds of 1.5 m/s with winds around 10 mph while entering and exiting buildings.

Abstract: Systems, methods, and devices are provided for controlling a movable object using multiple sensors. In one aspect, a method for calibrating one or more extrinsic parameters of a movable object having a plurality of sensors in an initial configuration is provided. The method can comprise: detecting that the initial configuration of the plurality of sensors has been modified; receiving inertial data from at least one inertial sensor during operation of the movable object; receiving image data from at least two image sensors during the operation of the movable object; and estimating the one or more extrinsic parameters based on the inertial data and the image data in response to detecting that the initial configuration has been modified, wherein the one or more extrinsic parameters comprise spatial relationships between the plurality of sensors in the modified configuration.

Abstract: A method of building a two-dimensional (2D) elevation map includes receiving sensor data regarding a 2D coordinate in a 2D coordinate system, computing a surface height for the 2D coordinate based on the sensor data, assigning a confidence indicator to the computed surface height based on the sensor data, and storing the computed surface height and the assigned confidence indicator for the 2D coordinate in a database, thereby building the 2D elevation map.

Abstract: A method for controlling a movable object includes obtaining current location information of an obstacle while the movable object tracks a target, and determining whether a location of the obstacle corresponds to a reactive region relative to the movable object based on the current location information of the obstacle. In response to determining that the location of the obstacle corresponds to the reactive region, one or more movement characteristics of the movable object is adjusted in a reactive manner to prevent the movable object from colliding with the obstacle. In response to determining that the location of the obstacle does not correspond to the reactive region, the one or more movement characteristics of the movable object is adjusted in a proactive manner to maintain a distance between the movable object and the obstacle to be larger than a predefined distance.

Abstract: A method includes obtaining previous state information of a movable object, receiving inertial data from at least one inertial sensor carried by the movable object, receiving image data from at least two image sensors carried by the movable object, and estimating updated state information of the movable object based on at least one of the previous state information, the inertial data, or the image data.

Abstract: An image rectification method includes determining one or more reference points in a raw image captured using a lens for a plurality of target pixels in a target image, obtaining a subsection of the raw image based on the one or more reference points, and calculating a target pixel value for each of the plurality of target pixels based on one or more pixel values of one or more pixels in the subsection of the raw image.

Abstract: Systems, methods, and devices are provided for controlling a movable object using multiple sensors. In one aspect, a method for calibrating one or more extrinsic parameters of a movable object having a plurality of sensors in an initial configuration is provided. The method can comprise: detecting that the initial configuration of the plurality of sensors has been modified; receiving inertial data from at least one inertial sensor during operation of the movable object; receiving image data from at least two image sensors during the operation of the movable object; and estimating the one or more extrinsic parameters based on the inertial data and the image data in response to detecting that the initial configuration has been modified, wherein the one or more extrinsic parameters comprise spatial relationships between the plurality of sensors in the modified configuration.

Abstract: A method for controlling a movable object includes detecting a live object within a proximity of the movable object, determining an operation mode to operate the movable object with the live object detected within the proximity of the movable object, and applying a control scheme associated with the operation mode to control an operation of the movable object.

Abstract: A method for supporting image processing for a movable object includes acquiring one or more images captured by an imaging device borne by the movable object. The imaging device is at least partially blocked by an obstructive object attached to the movable object. The method further includes applying a template to the one or more images to obtain one or more projected locations of the obstructive object within the one or more images and detecting at least portion of the obstructive object at the one or more projected locations within the one or more images.