Abstract: Various embodiments relate generally to computer vision and automation to autonomously identify and deliver for application a treatment to an object among other objects, data science and data analysis, including machine learning, deep learning, and other disciplines of computer-based artificial intelligence to facilitate identification and treatment of objects, and robotics and mobility technologies to navigate a delivery system, more specifically, to an agricultural delivery system configured to identify and apply, for example, an agricultural treatment to an identified agricultural object. In some examples, a method may include, receiving data representing a policy specifying a type of action for an agricultural object, selecting an emitter with which to perform a type of action for the agricultural object as one of one or more classified subsets, and configuring the agricultural projectile delivery system to activate an emitter to propel an agricultural projectile to intercept the agricultural object.

Abstract: Systems, methods and apparatuses for inspecting a tank containing a flammable fluid are provided. The system includes a vehicle having a propeller, a latch mechanism, a pressure switch, and an inspection device. The system includes a control unit in communication with the propeller, the latch mechanism, and the inspection device, and electrically connected to the pressure switch. The control unit powers on responsive to the pressure switch detecting an ambient pressure greater than a minimum threshold. The control unit receives, from the latch mechanism, an indication of a state of the latch mechanism. The control unit determines that the cable used to lower the vehicle into the tank containing the flammable fluid is detached from the vehicle. The control unit commands the propeller to move the vehicle through the flammable fluid. The control unit determines a quality metric of a portion of the tank.

Abstract: Systems and methods for determining a degree of wetness of a road surface from Light Detection and Ranging (LiDAR) point clouds are provided. The method comprises generating, using a LiDAR system, at least one point cloud, wherein the LiDAR system comprises a processor, and, using the processor, identifying and isolating one or more road surface points within a point cloud of the at least one point cloud, wherein the one or more road surface points indicate a road surface portion within an environment of the point cloud, analyzing the one or more road surface points to determine a number of the one or more road surface points that are zero intensity returns, and, based on the number of zero intensity returns, determining a degree of wetness of the road surface.

Abstract: Systems and methods for identifying water on a road surface via ultrasonic return intensity analysis are provided. The method comprises generating, using a processor, a road surface mapping of a road surface of an environment of a vehicle, transmitting, using one or more ultrasonic transducers, one or more ultrasonic waves in a direction of the road surface, receiving, using the one or more ultrasonic transducers, one or more returned ultrasonic waves, wherein the one or more returned ultrasonic waves return to the one or more ultrasonic transducers after reflecting off the road surface, determining an intensity of the one or more returned ultrasonic waves, and, when the intensity is below a threshold intensity, determining that a location at which the returned ultrasonic waves reflected off of the road surface has water present.

Abstract: Systems and methods for determining a presence of water along a surface from Light Detection and Ranging (LiDAR) point clouds is provided. The method comprises generating, using a LiDAR system coupled to a vehicle, at least one point cloud, wherein the LiDAR system comprises a processor, and, using the processor, identifying and isolating a ground plane within the at least one point cloud, identifying one or more objects within the at least one point cloud, determining whether a reflection of the one or more objects is present in the at least one point cloud below the ground plane, and, when the reflection is present, determining that water is present along a surface.

Abstract: An example implementation includes a device that includes a base infrastructure inspection unit and a plurality of modular sensor units attached to the base infrastructure inspection unit. The base infrastructure inspection unit includes a set of one or more processors and a memory device having code executable by the one or more processors. The executable code synchronizes the plurality of sensor units, captures two or more data streams of infrastructure inspection data, combines the data with metadata indicating synchronization between respective ones of the plurality of sensor units, and provides combined metadata and infrastructure inspection data for inclusion in a photorealistic image based on a three-dimensional (3D) model of the infrastructure.

Abstract: A video processing pipeline receives data derived from a feed of images of a plurality of objects passing in front of an inspection camera module forming part of a quality assurance inspection system. Quality assurance metrics for the object are generated by one or more containerized image analysis inspection tools forming part of the video processing pipeline using the received data for each object. Overlay images are later generated that characterize the quality assurance metrics. These overlay images are combined with the corresponding image of the object to generate an enhanced image of each of the objects. These enhanced images are provided to a consuming application or process for quality assurance analysis.

Abstract: An autonomous tool including a multi-sensor package enabling identification of the position of the tool in a construction site so that the tool may navigate to locations where tasks are performed. The tool may include at least one sensor from the group of a drive system encoder, stereo camera, inertial measurement unit, optical flow sensor, and LiDAR. The tool may include a holonomic drive allowing at least one tool of the mobility platform to reach the extremities of a construction site. The platform may be used as part of a system that receives design information relating to the construction site and tasks to be performed by the tool and then generates commands that control the tool to navigate along a path generated to include landmarks within range of and therefore detectable by the sensors for a large percentage of the path.

Abstract: Various embodiments of an apparatus, methods, systems and computer program products described herein are directed to an agricultural observation and treatment system and method of operation. The agricultural treatment system uses a treatment unit for spraying fluid at agricultural objects. The treatment unit is configured with a treatment head assembly that includes a moveable treatment head with one or more spraying tips. A first and second motor assembly are operated by the treatment unit to control the movement of the treatment head. The first motor assembly includes a first motor rotatable in a first rotational axis. A first linkage assembly is connected to the first motor and the treatment head assembly. The first linkage assembly is rotatable by the first motor. The second linkage assembly is rotatable by the second motor.

Abstract: Systems and methods for detecting a presence of water along a surface and adjusting a speed of a vehicle are provided. The method comprises generating one or more data points from one or more sensors coupled to a vehicle, and, using a processor, determining, based on the one or more data points, whether water is present along a surface, when water is present along the surface, determining a speed adjustment of the vehicle based on the water present along the surface, and generating a control signal configured to cause the vehicle to adjust a speed of the vehicle according to the speed adjustment.

Abstract: Systems and methods of manipulating/controlling robots. In many scenarios, data collected by a sensor (connected to a robot) may not have very high precision (e.g., a regular commercial/inexpensive sensor) or may be subjected to dynamic environmental changes. Thus, the data collected by the sensor may not indicate the parameter captured by the sensor with high accuracy. The present robotic control system is directed at such scenarios. In some embodiments, the disclosed embodiments can be used for computing a sliding velocity limit boundary for a spatial controller. In some embodiments, the disclosed embodiments can be used for teleoperation of a vehicle located in the field of view of a camera.

Abstract: An end effector device and system for suction-based grasping of bagged objects that can include a body structure with a vacuum line opening and an object engagement region, the vacuum line opening being configured to couple at least one pressure line of a vacuum pressure system to a defined internal channel of the body structure; the body structure comprising an internal structure that defines a concave inner chamber with a chamber opening at the object engagement region; and the internal structure comprising an array of inlets positioned along at least one wall of the concave inner chamber, wherein each inlet defines an opening in the body to the defined internal channel. The body structure may additionally include a suction cup system that comprises a flexible sealing lip at the object engagement region; wherein the chamber opening being positioned within a grasping region of the sealing lip.

Abstract: Systems and methods for safety-enabled control. Input values provided to a control system can be validated. Command gating can be performed for control values provided by the control system. Validation of input values and command gating for control values can be performed in accordance with respective validation windows. Validation windows can be dynamically adjusted based on data received via a sensor or interface.

Abstract: An end effector device and system for suction-based grasping of bagged objects that can include a body structure with a vacuum line opening and an object engagement region, the vacuum line opening being configured to couple at least one pressure line of a vacuum pressure system to a defined internal channel of the body structure; the body structure comprising an internal structure that defines a concave inner chamber with a chamber opening at the object engagement region; and the internal structure comprising an array of inlets positioned along at least one wall of the concave inner chamber, wherein each inlet defines an opening in the body to the defined internal channel.

Abstract: Crosstalk mitigation among cameras in neighboring monitored workcells is achieved by computationally defining a noninterference scheme that respects the independent monitoring and operation of each workcell. The scheme may involve communication between adjacent cells to adjudicate non-interfering camera operation or system-wide mapping of interference risks and mitigation thereof. Mitigation strategies can involve time-division and/or frequency-division multiplexing.

Abstract: One embodiment provides a system, including: an inspection platform configured to move through underground infrastructure; an imaging device coupled to the inspection platform; the imaging device comprising a camera housing that arranges an array of four or more cameras in a predetermined configuration; the camera housing comprising a plurality of apertures, wherein each aperture houses a respective camera therein with a viewing axis offset about 30 degrees to about 120 degrees from a viewing axis of an adjacent camera within the array; and circuitry that operates the imaging device to capture a plurality of images using the four or more cameras; where the circuitry captures the plurality of images for a composite image of an interior region of the underground infrastructure, and where the region is larger than a single viewing field of any of the four or more cameras. Other embodiments are described and claimed.

Abstract: A method, comprises identifying a set of image data captured by at least one autonomous vehicle when the at least one autonomous vehicle was positioned in a lane of a roadway, and respective ground truth localization data of the at least one autonomous vehicle; determining a plurality of lane width values for the set of image data; labeling the set of image data with the plurality of lane width values, the plurality of lane width values representing a width of a lane in which the at least one autonomous vehicle was positioned; and training using the labeled set of image data, a machine learning model, such that the machine learning model is configured to predict a new lane width value for a new lane as output.

Abstract: Disclosed herein are systems and methods for operating a vehicle. In an embodiment, a system can identify a maximum distance bound based on one or more objects around a vehicle; for each of a plurality of candidate trajectories for the vehicle, determine a velocity from the maximum distance bound at an ending time of the candidate trajectory; determine an available distance for the candidate trajectory as a function of the determined velocity at the ending time of the candidate trajectory and a comfort deceleration parameter; determine a target velocity for the candidate trajectory; and determine a velocity difference between the target velocity and a final velocity of the candidate trajectory at the ending time of the candidate trajectory; select a first candidate trajectory based on the velocity difference; and operate the vehicle based on the selected first candidate trajectory.

Abstract: A method of detecting an object in a path of an vehicle using a LiDAR system includes emitting a LiDAR signal with the LiDAR system; receiving the LiDAR signal with the LiDAR system; determining a glancing angle distance; determining the LiDAR signal is received from beyond the glancing angle distance based on receipt of the LiDAR signal; and classifying the LiDAR signal as a return from an object based at least in part on the LiDAR signal coming from a distance beyond the glancing angle distance.

Abstract: A method comprises identifying a set of image data captured by at least one autonomous vehicle when the at least one autonomous vehicle was positioned in a lane of a roadway, and respective ground truth localization data of the at least one autonomous vehicle; determining a total number of lanes for the roadway; labeling the set of image data with the total number of lanes for the roadway; and training using the labeled set of image data, a machine learning model, such that the machine learning model is configured to predict a new total number of lanes for a new roadway as output.