Abstract: Systems and techniques are provided for rare scenario handling in autonomous vehicles. In some aspects, an AV management system can determine a target likelihood value range for identifying relevant rare scenarios. In some cases, the AV management system may use the target likelihood value range to generate new relevant rare scenarios that have a likelihood value that falls within the target likelihood value range. In some examples, the AV management system may initiate simulations of the generated relevant rare scenarios and capture synthetic AV scene data, which can be used to train machine learning models used in AVs. As a result, the performance of the AVs may be improved when faced with rare scenarios.

Abstract: Systems and techniques are provided for management of autonomous cargo by autonomous vehicles (AVs). An example method can include determining, based on data from one or more sensors, a location for deploying a ramp that enables robots to enter the AV, the location comprising an area free of obstacles having one or more dimensions above a threshold; generating an instruction configured to trigger the AV to stop at the location; based on a determination that the AV is at the stopping position, deploying the ramp; sending, to the robots, a message instructing the robots to enter a cabin of the AV via the ramp and guiding each robot to a respective location within the cabin; and based on a determination that the AV has reached a destination of one or more robots, deploying the ramp and guiding the one or more robots to exit the cabin via the ramp.

Abstract: An operation of an AV in a scene is simulated. The AV includes sensors detecting the scene and generating sensor data. The sensor data can be input into a control model that outputs control signals, in accordance with which the AV operates. A learning cost, i.e., a cost of training or applying the control model, is determined. A performance of the AV during the simulation is evaluated. A simulation cost, i.e., a cost of running the simulation is determined. The control model can be optimized based on the learning cost and the performance of the AV. Settings of the sensors can be optimized based on the simulation cost and the performance of the AV. The optimization of the control model or the settings of the sensors can be done through reinforcement learning.

Abstract: Particular embodiments described herein provide for a system and method for determining an intent of a third-party autonomous vehicle by an autonomous vehicle. The method can include identifying the third-party autonomous vehicle, identifying a third-party autonomous vehicle behavior signature associated with the third-party autonomous vehicle, capturing sensor data related to the third-party autonomous vehicle, analyzing the captured sensor data to determine behaviors of the third-party autonomous vehicle, and using a third-party autonomous vehicle behavior signature to determine if the behaviors of the third-party autonomous vehicle indicate a specific intent of the third-party autonomous vehicle. The third-party autonomous vehicle behavior signature can be created by identifying behaviors of the third-party autonomous vehicle and associating the behaviors with an intent of the third-party autonomous vehicle.

Abstract: Aspects of the disclosed technology provide solutions for generating synthetic driving scenarios using text-based inputs that describe an intended operating goal. A process of the disclosed technology can include steps for generating a first synthetic scene for testing an autonomous vehicle (AV), providing the first synthetic scene to a first machine-learning model to generate a first text description of the synthetic scene, and providing the first text description to a second machine-learning model to determine if the first text description aligns with the predetermined operating goal for the AV. In some aspects, the process can further include generating a second text description for the synthetic scene, if the first text description does not align with the predetermined operating goal for the AV and providing the second text description to a third machine-learning model to generate a second synthetic scene. Systems and machine-readable media are also provided.

Abstract: Systems and techniques are provided for training of camera-radar fusion models. An example method includes receiving, by a machine learning model, at least one detection generated by a first version of a camera-radar fusion model, wherein the at least one detection is based on camera sensor data corresponding to a scene at a given time, and radar sensor data corresponding to the scene at the given time; receiving, by the machine learning model, LIDAR sensor data corresponding to the scene at the given time; and determining, by the machine learning model, at least one proposed label for training a second version of the camera-radar fusion model, wherein the at least one proposed label is based on the at least one detection and the LIDAR sensor data.

Abstract: Systems and techniques are provided for performing RADAR sensing based on external sensor feedback. An example method includes receiving position data associated with at least one object, wherein the position data is based on sensor data obtained by at least one sensor; identifying, based on the position data, at least one subspace from a field of view of a radar sensor, and collecting radar sensing data from the at least one subspace, wherein the radar sensing data corresponds to the at least one object.

Abstract: Systems and techniques are provided for mitigating radar interference between radars on a same and/or different vehicles. An example process includes receiving a first signal associated with a first radar sensor; receiving a second signal associated with a second radar sensor; determining an interference between the first signal and the second signal; in response to determining the interference, determining one or more adjustments to an operation of at least one of the first and second radar sensors based on at least one of a safety parameter, a coverage parameter, and a respective context of one or more vehicles associated with at least one of the first and second radar sensors; and transmitting one or more instructions to adjust the operation of at least one of the first and second radar sensors during one or more time intervals.

Abstract: Machine learning model optimization systems and methods are disclosed. A system receives sensor data captured by one or more sensors of a vehicle during a first time period. The vehicle uses a first trained machine learning (ML) model for one or more decisions of a first decision type during the first time period. The system generates a second trained ML model at least in part by using the sensor data to train the second trained ML model. The system identifies an optimal trained ML model from a plurality of trained ML models. The plurality of trained ML models includes the first trained ML model and the second trained ML model. The system causes the vehicle to use the optimal trained ML model for one or more further decisions of the first decision type during a second time period after the first time period.

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: 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: Systems and techniques are provided for utilizing occupied space and free space metrics for object detections of a perception system. An example method can include generating an occupancy-space probability and a free-space probability for each cell in a grid map representing a scene. The occupancy-space and the free-space probabilities can be based on sensor data captured by a first sensor of an autonomous vehicle (AV) in the scene. The example method can include receiving object detection(s) in the scene based on the sensor data captured by a second sensor of the AV in the scene; comparing, for each cell in the grid map, the object detection(s) in the scene against the occupancy-space and free-space probabilities in the scene; and identifying a missing object or a non-existent object in the scene based on the comparison of the object detection(s) against the occupancy-space and free-space probabilities. System and machine-readable media are also provided.

Abstract: Systems and techniques are provided for mapping data from a vehicle platform to a different vehicle platform. An example method can include obtaining sensor data collected by an autonomous vehicle (AV) in a scene, the AV comprising a target vehicle platform, the sensor data describing, measuring, or depicting one or more elements in the scene; determining one or more differences between the sensor data associated with the target vehicle platform and additional sensor data associated with a reference vehicle platform, the reference vehicle platform being associated with one or more software models that are trained to process data from the reference vehicle platform; based on the one or more differences, mapping the sensor data associated with the target vehicle platform to the reference vehicle platform; and processing the mapped sensor data via the one or more software models.

Abstract: Systems and techniques are provided for fusing sensor data from multiple sensors. An example method can include obtaining a first set of sensor data from a first sensor and a second set of sensor data from a second sensor; detecting an object in the first set of sensor data and the object in the second set of sensor data; aligning the object in the first set of sensor data and the object in the second set of sensor data to a common time; based on at least one of the aligned object from the first set of sensor data and the aligned object from the second set of sensor data, aligning the first set of sensor data and the second set of sensor data to the common time; and fusing the aligned first set of sensor data and the aligned second set of sensor data.

Abstract: Systems and techniques are provided for fusing sensor data from multiple sensors. An example method can include obtaining a first set of sensor data from a first sensor and a second set of sensor data from a second sensor; detecting an object in the first set of sensor data and the object in the second set of sensor data; aligning the object in the first set of sensor data and the object in the second set of sensor data to a common time; and based on the aligned object from the first set of sensor data and the aligned object from the second set of sensor data, fusing the aligned object from the first set of sensor data and the aligned object from the second set of sensor data.

Abstract: Systems and techniques are described for generating visual projections of information for display on surfaces within a vehicle.

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 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: Systems and techniques are provided for determining a distribution for a neural network parameter in designing a neural network architecture of an autonomous vehicle (AV). An example method can include determining an exploration distribution of a neural network parameter for one or more neural networks of one or more AVs; determining, for a target context, a target distribution of the neural network parameter from the exploration distribution, the target context comprising at least one of a driving environment associated with a location, a hardware configuration of one or more AVs, a software configuration of the one or more AVs, and a task of the one or more AVs; and providing, to a computer of an AV, the target distribution for implementing one or more neural network parameter values in the target distribution to adjust a neural network of the computer of the AV for operation in the target context.

Abstract: Systems and techniques are provided for management of autonomous cargo by autonomous vehicles (AVs). An example method can include determining, based on data from one or more sensors, a location for deploying a ramp that enables robots to enter the AV, the location comprising an area free of obstacles having one or more dimensions above a threshold; generating an instruction configured to trigger the AV to stop at the location; based on a determination that the AV is at the stopping position, deploying the ramp; sending, to the robots, a message instructing the robots to enter a cabin of the AV via the ramp and guiding each robot to a respective location within the cabin; and based on a determination that the AV has reached a destination of one or more robots, deploying the ramp and guiding the one or more robots to exit the cabin via the ramp.