Abstract: Aspects of the disclosed technology provide solutions for improving object detection and in particular, for improving object detection by an autonomous vehicle (AV) perceptions stack. In some aspects, a process of the disclosed technology can include steps for receiving first sensor data corresponding with an environment around the first vehicle, wherein the first sensor data represents one or more objects in the environment, receiving second sensor data corresponding with the environment around the first vehicle, and formulating a navigation route, by the first vehicle, based on the one or more occluded objects in the environment. Systems and machine-readable media are also provided.

Abstract: Disclosed are systems and techniques for managing an autonomous vehicle. In some aspects, an autonomous vehicle may obtain one or more radio frequency (RF) signals corresponding to a wireless device. In some cases, the autonomous vehicle may determine a location probability map associated with the wireless device based on the one or more RF signals. In some examples, the autonomous vehicle may adjust a behavior of the autonomous vehicle based on the location probability map associated with the wireless device.

Abstract: The subject disclosure relates to techniques for minimizing damage for collisions including an autonomous vehicle. A process of the disclosed technology can include predicting that a crash involving the autonomous vehicle is imminent, altering at least one operational parameter of the autonomous vehicle after predicting the crash is imminent, performing a first simulation on the autonomous vehicle, wherein the first simulation is a simulation of the autonomous vehicle taking a first action to minimize damage from the crash, and generating a first damage estimate for the first simulation.

Abstract: A method for three dimensional visualization and manipulation of downhole data. A measured signal is received a downhole environment and a three dimensional virtualization of the measured signal is generated. A stereographic viewer displays the three dimensional virtualization of the measured signal. The three dimensional virtualization can be manipulated in response to an input from a user, thereby creating a manipulated three dimensional virtualization. The stereographic viewer can display the manipulated three dimensional virtualization.

Abstract: The subject disclosure relates to techniques for enabling sharing of knowledge among a fleet of autonomous vehicles. A process of the disclosed technology can include generating an update for a continuous deep learning neural network on-board the autonomous vehicle based on driving scenarios encountered by the autonomous vehicle during its deployment and providing the update for the continuous deep learning neural network to additional vehicles in the fleet on autonomous vehicles, wherein the update for the continuous deep learning neural network is configured to be incorporated into a joint kernel for use by the additional vehicles in the fleet on autonomous vehicles.

Abstract: The present technology is directed to a sensor system. The sensor system may include a transmitter on a vehicle configured to transmit an electromagnetic signal in the frequency range 0.1 Hz to 10 kHz resulting in an electromagnetic field. The sensor system may also include a receiver on the vehicle configured to receive a secondary electromagnetic signal from a metallic or conductive object surrounding the vehicle, wherein the secondary electromagnetic signal represents the disturbance the electromagnetic field created by the electromagnetic signal from the vehicle. The present technology is also directed to a processor configured to determine that the magnitude of the disturbance caused by the secondary electromagnetic field is above a threshold. When the magnitude of the disturbance is above a threshold, it can be reasoned that there is an anomaly causing the disturbance that is likely a large metallic object.

Abstract: The present technology is directed to identifying road surface features and underground features using a ground-penetrating radar (GPR) sensor. The present technology may include activating the GPR sensor on a vehicle to transmit a pulsed electromagnetic signal toward a ground surface. The present technology may also include receiving the pulsed electromagnetic signal reflected from the road surface features and underground features by the GPR sensor. The present technology may also include filtering the pulsed electromagnetic signal to generate a shallow-GPR data or deep-GPR data, wherein the shallow-GPR data is used to identify the road surface features and the deep-GPR is used to identify the underground features. The present technology may also include adjusting operational parameters based on at least one of the road surface features and the underground features.

Abstract: The present technology is directed to customizing a driving behavior of an autonomous vehicle (AV) and verifying safety of the driving behavior based on a simulation. An AV management system can determine driving parameter(s) relating to a driving behavior of an AV and determine a degree of similarity between the driving parameters and a plurality of stored driving parameters. Based on a determination that the degree of the similarity is outside of a predetermined range, the AV management system can generate a scenario to test a safety of the driving parameters, perform a simulation of the AV in the scenario, and compare a simulation result with a predetermined safety threshold. Based on a determination that the simulation result is equal to or above the predetermined safety threshold, the AV management system can adjust the driving behavior of the AV based on the driving parameters.

Abstract: The present technology is directed to dynamically adjusting an autonomous vehicle (AV) system based on deep learning optimizations. An AV management system can generate a downscaling signal based on a result of comparing a complexity of an environment for an AV to navigate with a predetermined complexity threshold. Further, the AV management system can perform a downscaling of a neural network associated with an AV system based on the downscaling signal and determine a scenario to test the downscaled neural network in a simulation. The AV management system can adjust one or more parameters of the AV system based on simulated outputs and perform the simulation of the AV based on the adjusted one or more parameters of the AV system and the downscaled neural network to generate simulated performance data. Furthermore, the AV management system can compare the simulated performance data with a predetermined performance threshold.

Abstract: The present technology pertains to obtaining sensor data and processed sensor data related to a base world scenario encountered by an AV entity. The sensor data and processed sensor data may be assessed to determine an importance value for the base world scenario. When the importance value is above a threshold, a closed course staging system may stage a re-creation of the base world scenario in a closed course environment (i.e., a closed course scenario). An AV may then interact with the closed course scenario. Sensor data and processed sensor data from the AV’s interaction with the closed course scenario may then be added to training data used to train ML models for AVs.

Abstract: Disclosed are systems, apparatuses, methods, and computer-readable media to autonomous driving vehicles and, in particular, for preventing latency violations in autonomous vehicle control systems. A method includes navigating the autonomous vehicle into first region of an environment at a first time, determining a runtime performance of the autonomous vehicle control system in the first region based on the environment, recording the runtime performance into runtime information of the autonomous vehicle, and determining a route to a destination location for the autonomous vehicle to navigate based on mapping information determined based on the runtime information.

Abstract: Apparatus and methods can be implemented to monitor the condition of the production and intermediate casing strings in oil and gas field operations. A series of measurements can be made in a multi-pipe structure and received responses can be operated on by employing a mapping optimization procedure in which a surrogate model is updated. Estimates of one or more properties of the pipes of the multi-pipe structure can be generated using coefficients of the updated surrogate model. Additional apparatus, systems, and methods are disclosed.

Abstract: In some embodiments, a downhole drilling system may include a pulse-generating circuit, a drill bit including a first pair of electrodes electrically coupled to the pulse-generating circuit to receive a first electrical pulse from the pulse-generating circuit and form a first electrical arc between the first pair of electrodes during a pulsed drilling operation. The system further includes a sensor to record responses to the first electrical pulse during the pulsed drilling operation and a sensor analysis system communicatively coupled to the sensor, where the sensor analysis system is configured to obtain a first measurement from the sensor representing the responses recorded by the sensor during the pulsed drilling operation. Additionally, the system may determine a first value of a dielectric constant associated with a portion of a formation in proximity to the drill bit, where the first value of the dielectric constant is based on the first measurement.

Abstract: A method and system for visualizing data to detect a collar. A method may comprise disposing an electromagnetic logging tool downhole; emitting an electromagnetic field from the transmitter; energizing a casing with the electromagnetic field to produce an eddy current; recording the eddy current from the casing with the receiver; creating a variable-density-log from the recorded eddy current; selecting a wrapping period for the variable-density-log; creating a wrapped-variable-density-log from the variable-density-log using the wrapping period; and determining at least one collar location and a pipe index with the wrapped-variable-density-log. A system for to detect a collar may comprise an electromagnetic logging tool. The electromagnetic logging tool may comprise a transmitter and a receiver, wherein the transmitter and the receiver may be a coil. The system may further comprise an information handling system.

Abstract: Fiber optic sensors are described for detecting the operational position of a downhole moveable device. In one example, an electric or magnetic field is emitted into the wellbore and interacts with the moveable assembly, thereby producing a secondary electric or magnetic field. The secondary field is detected by a fiber optic sensor which produces a corresponding response signal. The response signal is then processed in a variety of ways to determine the operational position of the moveable device. In another example, the operational position is determined using fiber optic temperature or acoustic sensors. A temperature or acoustic vibration reading is acquired before and after actuation of the moveable device. The two readings are then compared to determine the operation position of the moveable device.

Abstract: A method and a system for tuning a pad. The method may comprise disposing a downhole tool into a borehole, configuring the pad in a first configuration, taking a first measurement of the formation in the first configuration, configuring the pad in a second configuration, taking a second measurement of the formation in the second configuration, determining a tuning coefficient to reduce a tool body effect in the first measurement and the second measurement, computing a first weighted measurement from the tuning coefficient and the first measurement, computing a second weighted measurement from the tuning coefficient and the second measurement, and computing a tuned impedance from a ratio of the first weighted measurement and the second weighted measurement. A system for determining a formation boundary may comprise a downhole tool, an arm, and a pad. The system may further comprise a conveyance and an information handling system.

Abstract: Apparatus, systems, and methods for ranging operate to use a wireline active ranging system to initially determine a relative distance and relative direction from a first well (e.g., ranging well) to a second well (e.g., target well) and an EM azimuthal logging tool to maintain or adjust the distance from the target well while drilling the ranging well. Additional apparatus, systems, and methods are disclosed.

Abstract: A method and system for visualizing data to detect a collar. A method may comprise disposing an electromagnetic logging tool downhole; emitting an electromagnetic field from the transmitter; energizing a casing with the electromagnetic field to produce an eddy current; recording the eddy current from the casing with the receiver; creating a variable-density-log from the recorded eddy current; selecting a wrapping period for the variable-density-log; creating a wrapped-variable-density-log from the variable-density-log using the wrapping period; and determining at least one collar location and a pipe index with the wrapped-variable-density-log. A system for to detect a collar may comprise an electromagnetic logging tool. The electromagnetic logging tool may comprise a transmitter and a receiver, wherein the transmitter and the receiver may be a coil. The system may further comprise an information handling system.

Abstract: A system includes a tool to dispose in a wellbore lined with pipe. The tool includes first and second receiver coils having a non-uniform winding along a longitudinal axis, a third receiver coil having a non-uniform winding coaxial with at least one of the first and second receiver coils, and a transmitter. The system includes a processor to execute instructions to perform operations including causing the transmitter to emit an induced magnetic field, measuring the induced magnetic field using the first receiver coil to create a first measurement and using the first and second receiver coils to create a second measurement. The operations include determining a static magnetic field, selecting the first or second measurement based on a magnitude of the static magnetic field to determine a selected measurement, and determining at least one property of the pipe using the selected measurement.

Abstract: The disclosure provides a well integrity monitoring tool for a wellbore, a method, using a nuclear tool and an EM tool, for well integrity monitoring of a wellbore having a multi-pipe configuration, and a well integrity monitoring system. In one example, the method includes: operating a nuclear tool in the wellbore to make a nuclear measurement at a depth of the wellbore, operating an EM tool in the wellbore to make an EM measurement at the depth of the wellbore, determining a plurality of piping properties of the multi-pipe configuration at the depth employing the EM measurement, determining, employing the piping properties, a processed nuclear measurement from the nuclear measurement, and employing the processed nuclear measurement to determine an integrity of a well material at the depth and within an annulus defined by the multi-pipe configuration.