Systems and methods for controlling a movable object within an environment are provided. In one aspect, a method may comprise: determining, using at least one of a plurality of sensors carried by the movable object, an initial location of the movable object; generating a first signal to cause the movable object to navigate within the environment; receiving, using the at least one of the plurality of sensors, sensing data pertaining to the environment; generating, based on the sensing data, an environmental map representative of at least a portion of the environment; receiving an instruction to return to the initial location; and generating a second signal to cause the movable object to return to the initial location, based on the environmental map.

Multi-sensor environmental mapping

Systems and methods for controlling an unmanned aerial vehicle within an environment are provided. In one aspect, a system comprises one or more sensors carried by the unmanned aerial vehicle and configured to provide sensor data and one or more processors. The one or more processors can be individually or collectively configured to: determine, based on the sensor data, an environment type for the environment; select a flight mode from a plurality of different flight modes based on the environment type, wherein each of the plurality of different flight mode is associated with a different set of operating rules for the unmanned aerial vehicle; and cause the unmanned aerial vehicle to operate within the environment while conforming to the set of operating rules of the selected flight mode.

Context-based flight mode selection

This article describes a method of navigation for an individual based on traditional inertial navigation system (INS) technology, but with very small and self-contained sensor systems. A conventional INS contains quite accurate, but large and heavy, gyroscopes and accelerometers, and converts the sensed rotations and accelerations into position displacements through an algorithm known as a strapdown navigator. They also, almost without exception, use an error compensation scheme such as a Kalman filter to reduce the error growth in the inertially sensed motion through the use of additional position and velocity data from GPS receivers, other velocity sensors (e.g., air, water, and ground speed), and heading aids such as a magnetic compass. This technology has been successfully used for decades, yet the size, weight, and power requirements of sufficiently accurate inertial systems and velocity sensors have prevented their adoption for personal navigation systems. Now, however, as described in this article, miniature inertial measurement units (IMUs) as light as a few grams are available. When placed on the foot to exploit the brief periods of zero velocity when the foot strikes the ground (obviating the need for additional velocity measurement sensors), these IMUs allow the realization of a conventional Kalman-filter-based aided strapdown inertial navigation system in a device no larger or heavier than a box of matches. A particular advantage of this approach is that no stride modeling is involved with its inherent reliance on the estimation of a forward distance traveled on every step — the technique works equally well for any foot motion, something especially critical for soldiers and first responders. Also described is a technique to exploit magnetic sensor orientation data even in indoor environments where local disturbances in the Earth’s magnetic field are significant. By carefully comparing INSderived and magnetically derived heading and orientation, a system can automatically deter

Indoor navigation with foot-mounted strapdown inertial navigation and magnetic sensors

The method and system may be used to control the movement of a remote aerial device in an incremental step manner during a close inspection of an object or other subject matter. At the inspection location, a control module “stabilizes” the remote aerial device in a maintained, consistent hover while maintaining a close distance to the desired object. The control module may retrieve proximal sensor data that indicates possible nearby obstructions to the remote aerial device and may transmit the data to a remote control client. The remote control module may determine and display the possible one or more non-obstructed directions that the remote aerial device is capable of moving by an incremental distance. In response to receiving a selection of one of the directions, the remote control module may transmit the selection to the remote aerial device to indicate the next movement for the remote aerial device.

System and method for controlling a remote aerial device for up-close inspection

This article describes a method of navigation for an individual based on traditional inertial navigation system (INS) technology, but with very small and self-contained sensor systems. A conventional INS contains quite accurate, but large and heavy, gyroscopes and accelerometers, and converts the sensed rotations and accelerations into position displacements through an algorithm known as a strapdown navigator. They also, almost without exception, use an error compensation scheme such as a Kalman filter to reduce the error growth in the inertially sensed motion through the use of additional position and velocity data from GPS receivers, other velocity sensors (e.g., air, water, and ground speed), and heading aids such as a magnetic compass. This technology has been successfully used for decades, yet the size, weight, and power requirements of sufficiently accurate inertial systems and velocity sensors have prevented their adoption for personal navigation systems. Now, however, as described in this article, miniature inertial measurement units (IMUs) as light as a few grams are available. When placed on the foot to exploit the brief periods of zero velocity when the foot strikes the ground (obviating the need for additional velocity measurement sensors), these IMUs allow the realization of a conventional Kalman-filter-based aided strapdown inertial navigation system in a device no larger or heavier than a box of matches. A particular advantage of this approach is that no stride modeling is involved with its inherent reliance on the estimation of a forward distance traveled on every step ��� the technique works equally well for any foot motion, something especially critical for soldiers and first responders. Also described is a technique to exploit magnetic sensor orientation data even in indoor environments where local disturbances in the Earth���s magnetic field are significant. By carefully comparing INSderived and magnetically derived heading and orientation, a system can automatically determine when sensed magnetic heading is accurate enough to be useful for additional error compensation.

Indoor navigation with foot-mounted strapdown inertial navigation and magnetic sensors [Emerging Opportunities for Localization and Tracking]

Systems and methods for airborne object detection using monocular sensors are provided. In one embodiment, a system for detecting moving objects from a mobile vehicle comprises: an imaging camera; a navigation unit including at least an inertial measurement unit; and a computer system coupled to the image camera and the navigation unit. The computer system executes an airborne object detection process algorithm, and calculates a transformation between two or more image frames captured by the imaging camera using navigation information associated with each of the two or more image frames to generate a motion compensated background image sequence. The computer system detects moving objects from the motion compensated background image sequence.

Systems and methods for monocular airborne object detection

Embodiments of the present invention provide improved systems and methods for matching scenes. In one embodiment, a processor for implementing robust feature matching between images comprises: a first process for extracting a first feature set from a first image projection and extracting a second feature set from a second image projection; a memory for storing the first feature set and the second feature set; and a second process for feature matching using invariant mutual relations between features of the first feature set and the second feature set; wherein the second feature set is selected from the second image projection based on the identification of similar descriptive subsets between the second image projection and the first image projection.

Systems and methods for matching scenes using mutual relations between features

A navigation system comprises an image sensor operable to obtain range data for a first scene, and a processing unit coupled to the image sensor. The processing unit is operable to identify one or more plane features, based on the range data, using each of a plurality of scales. The processing unit is further operable to combine each of the one or more plane features with a corresponding plane feature from each of the plurality of scales and to project the one or more combined plane features to a reference orientation.

System and method of extracting plane features

We present technologies that are being developed to address the need for a navigation solution in the absence of Global Navigation Satellite Systems (GNSS) measurements. The navigation system uses sensors such as vision systems, RADARS and LIDARS with feature extraction, matching and motion estimation algorithms. We present experimental results of using scale invariant feature transform, speeded up robust features, and modified Harris feature extraction algorithms and compare the performance. We also present methods to extract lines and planes that can aid in navigation. For motion estimation we present results for visual odometry as well as simultaneous localization and mapping navigation. We experimentally verify the algorithms in both a realtime Linux framework as well as offline. We also present ongoing work in vision integrated navigation in an attitude and heading reference system as well as an extended Kalman filter framework. All the methods we present in this paper are incremental navigation methods.

Sensor fusion for GNSS denied navigation

In some examples, a processor is configured to predict the presence of ice crystals (e.g., high altitude ice crystals) in a volume of airspace based on radar reflectivity values and one or more other types of information indicative of weather conditions in the volume of airspace, such as one or more of: ambient air temperature and altitude. For example, the processor may predict the ice crystals presence by at least estimating the iced water content level within a volume of airspace of interest based on radar reflectivity values for the volume of airspace (e.g., stored as in a three-dimensional buffer) and other information indicative of weather conditions of the volume of airspace. The processor may estimate the iced water content level using a model that relates the information indicative of weather conditions in and around the volume of interest to iced water content in the atmosphere.

Ondrej Kotaba

Papers

Systems and methods for monocular airborne object detection

Systems and methods for matching scenes using mutual relations between features

System and method of extracting plane features

Sensor fusion for GNSS denied navigation

Prediction of ice crystal presence in a volume of airspace