Abstract: Generally, the disclosed systems and methods implement improved detection of objects in three-dimensional (3D) space. More particularly, an improved 3D object detection system can exploit continuous fusion of multiple sensors and/or integrated geographic prior map data to enhance effectiveness and robustness of object detection in applications such as autonomous driving. In some implementations, geographic prior data (e.g., geometric ground and/or semantic road features) can be exploited to enhance three-dimensional object detection for autonomous vehicle applications. In some implementations, object detection systems and methods can be improved based on dynamic utilization of multiple sensor modalities. More particularly, an improved 3D object detection system can exploit both LIDAR systems and cameras to perform very accurate localization of objects within three-dimensional space relative to an autonomous vehicle.

Abstract: Aspects of the disclosure provide for localizing a vehicle. In one instance, a weather condition in which the vehicle is currently driving may be identified. A plurality of sensor inputs including intensity information, elevation information, and radar sensor information may be received. For each of the plurality of sensor inputs, an alignment score is determined by comparing the intensity information, elevation information, and radar sensor information to a corresponding pre-stored image for each of the intensity information, the elevation information, and the radar sensor information. A set of weights for the plurality of sensor inputs may be determined based on the identified weather condition. The alignment scores may then be combined using the set of weights in order to localize the vehicle.

Abstract: A method includes obtaining steering data of the vehicle from one or more steering sensors, determining whether the vehicle is operating in one of a turning state and a non-turning state based on the steering data, performing a localization routine based on a first echo set of the 3D data points from among the plurality of 3D data points when the vehicle is operating in the turning state, and performing the localization routine based on a second echo set of the 3D data points from among the plurality of 3D data points when the vehicle is operating in the non-turning state, where a number of the plurality of 3D data points of the first echo set is greater than a number of the plurality of 3D data points of the second echo set.

Abstract: An autonomous vehicle includes sensor subsystem(s) that output a sensor signal. A perception subsystem (i) detects an agent in a vicinity of the autonomous vehicle and (ii) generates a motion signal that describes at least one of a past motion or a present motion of the agent. An intention prediction subsystem processes the sensor signal to generate an intention signal that describes at least one intended action of the agent. A behavior prediction subsystem processes the motion signal and the intention signal to generate a behavior prediction signal that describes at least one predicted behavior of the agent. A planner subsystem processes the behavior prediction signal to plan a driving decision for the autonomous vehicle.

Abstract: A method for determining measured values using at least two different measuring methods involves, with each of the measuring methods, determining provisional measured values and suppling data for an integrity of the determined provisional measured values. The determined provisional measured values are merged to give combined measured values and information on the integrity of the combined measured values is determined. Depending on the data concerning the integrity of the determined provisional measured values and the combined measured values and depending on a period of time during which the determined provisional measured values and the combined measured values in each case meet specified requirements regarding their integrity, it is decided which of the measured values are supplied for further processing.

Abstract: In an embodiment, yield data representing yields of crops that have been harvested from an agricultural field and field characteristics data representing characteristics of the agricultural field is received and used to determine a plurality of management zone delineation options. Each option, of the plurality of management zone delineation options, comprises zone layout data for an option. The plurality of management zone delineation options is determined by: determining a plurality of count values for a management class count; generating, for each count value, a management delineation option by clustering the yield data from and the field characteristics data, assigning zones to clusters, and including the zones in a management zone delineation option. One or more options from the plurality of management zone delineation options are selected and used to determine one or more planting plans. A graphical representation of the options and the planting plans is displayed for a user.

Abstract: A method may include obtaining sensor data relating to an autonomous vehicle (AV) and a total measurable world around the AV. The method may include identifying an operating environment of the AV and determining a projected computational load for computing subsystems that facilitate a driving operation performable by the AV corresponding to the identified environment. The method may include off-loading first computing subsystems of the computing subsystems in which computations of the first computing subsystems may be processed by an off-board cloud computing system and processing computations associated with second computing subsystems of the computing subsystems by an on-board computing system.

Abstract: A system for operating an autonomous agent with incomplete environmental information can include and/or interface an autonomous operating system and an autonomous agent. A method for operating an autonomous agent with incomplete environmental information includes any or all of: receiving a set of inputs; determining a set of known objects in the ego vehicle's environment; determining a set of blind regions in the ego vehicle's environment; and inserting a set of virtual objects into the set of blind regions; selecting a set of virtual objects based on the set of blind regions; operating the autonomous agent based on the set of virtual objects; and/or any other suitable processes.

Abstract: A system for context-aware decision making of an autonomous agent includes a computing system having a context selector and a map. A method for context-aware decision making of an autonomous agent includes receiving a set of inputs, determining a context associated with an autonomous agent based on the set of inputs, and optionally any or all of: labeling a map; selecting a learning module (context-specific learning module) based on the context; defining an action space based on the learning module; selecting an action from the action space; planning a trajectory based on the action S260; and/or any other suitable processes.

Abstract: A method for determining potential damage to a vehicle battery. In the method, at least one acceleration data set relating to a vertical acceleration of a motor vehicle, which includes the vehicle battery, is determined. The at least one acceleration data set is then checked for the presence of a predetermined damage criterion, which indicates the potential damage to the vehicle battery. Finally, only for the case that the damage criterion is determined in the at least one acceleration data set, a control signal for actuating an actuator device of the motor vehicle is generated.

Abstract: A method for characterizing the curvature of a road section, including: selecting, from among the points of the section, the points marking a curvature of the section; computing, for each selected point of the section contained between the second and the penultimate one, an indicator of curvature of the section at this point; identifying each bend contained in the road section, each bend including a set of successive selected points of the section; and for each bend contained in the road section, comparing the indicator of curvature of at least one of the points of the bend with a predetermined threshold. If the indicator of curvature computed for at least one of the selected points of the bend exceeds the predetermined threshold, recording, in a database, a data record including at least the set of points of the bend, and an item of data characterizing the curvature of the bend.

Abstract: A method performed by a first computing system includes receiving, from a second computing system, a message identifying a symptom of a first vehicle; and sending a repair tip to the second computing system. The repair tip includes a first phrase describing a first procedure performed on a second vehicle that exhibited the symptom, wherein the first procedure performed on the second vehicle yielded a result insufficient to determine that a component of the second vehicle associated with the symptom is defective. The repair tip also includes a second phrase describing a second procedure performed on a given vehicle, wherein the given vehicle is either (i) the second vehicle or (ii) a third vehicle that also exhibited the symptom, wherein the second procedure performed on the given vehicle yielded a result sufficient to determine that a component of the given vehicle associated with the symptom is defective.

Abstract: One or more information maps are obtained by an agricultural work machine. The one or more information maps map one or more agricultural characteristic values at different geographic locations of a field. An in-situ sensor on the agricultural work machine senses an agricultural characteristic as the agricultural work machine moves through the field. A predictive map generator generates a predictive map that predicts a predictive agricultural characteristic at different locations in the field based on a relationship between the values in the one or more information maps and the agricultural characteristic sensed by the in-situ sensor. The predictive map can be output and used in automated machine control.

Abstract: A navigation system for a host vehicle may include a processor programmed to: receive from a center camera onboard the host vehicle a captured center image including a representation of at least a portion of an environment of the host vehicle, receive from a left surround camera onboard the host vehicle a captured left surround image including a representation of at least a portion of the environment of the host vehicle, and receive from a right surround camera onboard the host vehicle a captured right surround image including a representation of at least a portion of the environment of the host vehicle; provide the center image, the left surround image, and the right surround image to an analysis module configured to generate an output relative to the at least one captured center image; and cause a navigational action by the host vehicle based on the generated output.

Abstract: Multiple exemplary systems for preventing jackknifing are disclosed. The systems comprise an electric motor for extending a shaft into a fifth wheel coupling when a tractor trailer is traveling at above a predetermined speed in a forward direction, physically preventing the tractor trailer from jackknifing. In order to avoid dependence on integration with a tractor, sensors on a trailer are used to determine speed without communication with the tractor or any instruments therein, via reception of one or more waves. When the trailer is determined to be traveling at below the predetermined speed in a forward direction, or at any speed in a backward direction, the shaft is retracted to allow the trailer to freely rotate with respect, to the tractor.

Abstract: An unmanned aerial vehicle (UAV) landing method includes detecting, via one or more visual sensors, a gesture or movement of an operator of a UAV; and controlling to decelerate, with aid of one or more processors and in response to the detected gesture or movement, one or more rotor blades of the UAV to cause the UAV to land autonomously.

Abstract: A method of retrieving a map is disclosed. The method includes receiving a grid data of the map comprising lane segments, wherein the grid data includes an array of grids each associated with a list including none or at least one of the lane segments intersecting the respective grid; receiving coordinates of a location; identifying a first grid including the location based on the grid data; identifying a target grid that has an associated list including at least one of the lane segments as first lane segment; and outputting the first lane segment.

Abstract: A system and method for avoiding or mitigating collisions by an autonomous vehicle is provided. Raw sensor data for the vehicle's environment is received, such as through a perception system of the vehicle. A trajectory is also received, the trajectory having a width corresponding to a distance that is at least as wide as the vehicle. The trajectory and raw sensor data are projected onto a grid, such as a static occupancy grid, having a plurality of cells. It is determined whether any cell that overlaps with the trajectory includes the raw sensor data. It is further determined, based on the raw sensor data, whether an obstacle is present along the trajectory. When no obstacles are determined to be present along the trajectory, the trajectory may be verified. However, where obstacles are determined to be present, the vehicle may take an action to avoid collision.

Abstract: The angle of a trailer with respect to a tow vehicle is an important parameter to the stability of the vehicle and trailer. A tow vehicle pulling a trailer in a straight line is generally more stable than when the vehicle is turning. While turning, the angle between the tow vehicle and the trailer is not a straight line but is another angle depending on how sharply the tow vehicle is turning. To safely operate a vehicle towing a trailer, for a given steering input and speed, there is a maximum angle between the tow vehicle and trailer whereby exceeding the angle causes instability and may cause the trailer or tow vehicle to roll over or jackknife. Accordingly, the angle between the trailer and tow vehicle must be determined to ensure the vehicle and trailer will continue to be in control.

Abstract: A system for controlling stop of a vehicle includes a steering angle comparison device that detects a current steering angle of the vehicle and compares the detected current steering angle with a preset limit steering angle when a malfunction of a steering system in the vehicle is detected during autonomous driving, a partial braking induction determination device that determines a position of a tire of the vehicle to be subjected to partial braking for steering control of the vehicle according to a result of the comparing between the current steering angle and the limit steering angle, and a partial braking control device that determines an amount of braking to be applied to each determined tire of the vehicle and applies a braking pressure corresponding to the amount of braking to each tire of the vehicle to perform the steering control by the partial braking.