Abstract: Systems and methods for generating ground-level terrain elevation models, preparing vector street data to assist in generating such models, and finding approximate elevation of any point using such terrain models are provided. Lidar data can be analyzed, and Lidar elevation values at roadway/street intersections can be used to determine a model of the ground-level elevation in an area or region. Outliers can be removed. The ground-level elevation at any point in the mapped area can be determined using elevation levels for nearby roadway intersections.

Abstract: Systems and methods for a tightly coupled trajectory predictor with constant up-finding are provided. In certain embodiments, a system includes an inertial measurement unit that provides inertial measurements of a vehicle. The system also includes an up-finding sensor that provides up-finding measurements based on when a portion of the vehicle is pointing up. Further, the system includes one or more processors that bound errors from the inertial measurements in a navigation solution during navigation of the vehicle using the up-finding measurements.

Abstract: A waste sorting manipulator can include a gripper assembly for interacting with one or more waste objects to be sorted within a working area. There is at least one servo for moving the gripper assembly between the manipulator and the working area. There is also at least one slidable coupling mounted between the at least one servo and the gripper assembly for allowing relative movement between the at least one servo and the gripper assembly.

Abstract: A vehicle operable to pull a trailer comprising a payload is provided, that includes a plurality of sensors configured to capture sensor data related to the vehicle, the trailer, or both, and a controller configured to (i) receive the sensor data from the plurality of sensors, (ii) determine, based on the sensor data, one or more parameters associated with the trailer, the payload, or both, (iii) update, based on an analysis of the one or more parameters, a confidence level associated with an operation of the vehicle with the trailer and the payload, and (iv) based on the confidence level, responsively execute an autonomous control strategy comprising one or more adjustments to the operation of the vehicle.

Abstract: Embodiments are disclosed for an automatic identification of a driver. In one example, an in-vehicle computing system of a vehicle includes a sensor interface communicatively coupled to one or more data collection devices, a processor, and a storage device storing instructions executable by the processor to generate a two-dimensional current driver profile matrix for a current driver of the vehicle, the current driver profile matrix indicating a vehicle operating status in terms of a pair of driving parameters at sampled times during a current vehicle trip, and determine a probability that the current driver is one of a plurality of known drivers by comparing the current driver profile matrix to one or more stored driver profile matrices associated with the plurality of known drivers.

Abstract: Disclosed is a navigation system configured to track an object. The navigation system comprises a tracker configured to couple to the object and a localization device configured to track the tracker. The tracker and the localization device are configured to wirelessly communicate using a first communication method operable on a first spectrum and to wirelessly communicate using a second communication method operable on a second spectrum different from the first spectrum. The localization device utilizes the first communication method to track the tracker and utilizes the first communication method to manage an operating parameter of the tracker with respect to the second communication method.

Abstract: A vehicle motion control device generates a travel route where behavior of a vehicle traveling on a curve is small and comfortable ride is achieved even when the vehicle travels on a continuous curve. The control device includes a travel track generation unit that generates, based on information on a curvature of a first curve on a lane existing in a traveling direction of a vehicle and a curvature of a second curve connected to the first curve, a travel route by setting curvature of the travel route at a time of traveling on a curve having a smaller curvature between the first and second curves to be larger than the curvature of the curve and setting a curvature of the travel route at a time of traveling on a curve having a larger curvature between the first and second curves to be smaller than the curvature of the curve.

Abstract: A position estimation apparatus includes: an image information calculation unit that extracts each of image feature points from a plurality of images which are sequentially captured and associates the image feature points with each other between the plurality of images; a travel amount calculation unit that estimates the position of the mobile object; a three-dimensional image feature point calculation unit that estimates a three-dimensional position of the image feature point in a real space on the basis of a result of associating the image feature points with each other and the position of the mobile object; a position correction unit that corrects the three-dimensional position and the position of the mobile object so as to reduce a position error between a position of the three-dimensional position, when the three-dimensional position is reprojected onto any one of the plurality of images, in the relevant image and the image feature point; a route regeneration judgment unit that judges whether or not to r

Abstract: Embodiments of the disclosure provide methods and systems for continuous regulation of a nonholonomic mobile robot. An exemplary method may include identifying a current pose of the nonholonomic mobile robot in a world frame, where the current pose is represented by a first set of values defining a first set of states of the nonholonomic mobile robot in the world frame; receiving a final goal pose of the nonholonomic mobile robot, where the final goal pose is represented by a second set of values defining a second set of states of nonholonomic mobile robot in the world frame; determining a moving path for moving the nonholonomic mobile robot from the current pose to the final goal pose; and controlling the nonholonomic mobile robot to move from the current pose to the final goal pose according to the moving path, where the nonholonomic mobile robot moves to the final goal pose by converging the nonholonomic mobile robot from the first set of states to the second set of states simultaneously.

Abstract: Illustrative systems and methods for inserting an elongate flexible instrument into a target environment are described. An illustrative system includes a guide device positioned near an opening to the target environment and having a rotary mechanism and a motor configured to drive the rotary mechanism. The system further includes a sensor system associated with insertion of the elongate flexible instrument along an insertion axis and a processor communicatively coupled to the motor and the sensor system. The processor is configured to receive sensor data from the sensor system, evaluate the sensor data, and control, based on the evaluation, the motor to actuate the elongate flexible instrument along the insertion axis. In some examples, the processor controls the motor to vary a rate of rotation of the rotary mechanism based on a determined system status.

Abstract: A method, a computer program comprising instructions, and a device for processing sensor data in a motor vehicle. An assistance system for a motor vehicle in which a method is implemented, and a motor vehicle having such a system. Sensor data is received. At least one algorithm is applied to the sensor data to determine a first intermediate result. At least one rule is applied to the first intermediate result to determine a second intermediate result. The second intermediate result is evaluated with regard to plausibility. If the second intermediate result is implausible, one or more of the rules applied to the first intermediate result is reversed until the second intermediate result is plausible. The second intermediate result thereby obtained is finally output as an end result.

Abstract: A method for controlling an automated driving operation includes setting up respective independent models for executing planning and learning in the automated driving operation, including a vehicle planning model and a cognitive learning model. A semantic layer is generated to act as a bridge between the cognitive learning model and the vehicle planning model, the semantic layer including a first data adaptor and a second data adaptor. The method includes transforming real traffic data to a respective equivalent abstract representation such that it can be used by the cognitive learning model to generate a humanized reward model, via the first data adaptor. The method includes determining a trajectory plan, via the vehicle planning model, based in part on the humanized reward model. The vehicle has a controller that executes the automated driving operation based in part on the trajectory plan.

Abstract: Techniques are disclosed that enable training a meta-learning model, for use in causing a robot to perform a task, using imitation learning as well as reinforcement learning. Some implementations relate to training the meta-learning model using imitation learning based on one or more human guided demonstrations of the task. Additional or alternative implementations relate to training the meta-learning model using reinforcement learning based on trials of the robot attempting to perform the task. Further implementations relate to using the trained meta-learning model to few shot (or one shot) learn a new task based on a human guided demonstration of the new task.

Abstract: Disclosed are Ethernet-based vehicle control system and method. The system includes: a router for connecting a vehicle internal network and a vehicle external network when the vehicle internal network is formed by connecting an engine and a vehicle electronic element including a controller and a sensor; and a remote start module for performing remote start based on a remote start signal transmitted from a remote controller through the vehicle external network, wherein whether or not to perform the remote start is determined based on drive system state information generated by the vehicle electronic element and transferred via the router. When performing a remote start is controlled in response to an engine RPM during the remote start, efficient management of engine protection and fuel consumption can be achieved. When performing a remote start is controlled in response to the position of the transmission, safe remote start can be achieved.

Abstract: Described herein is a visual indication system implemented on a mobile machine. The visual indication system at least partially surrounds the mobile machine and includes a plurality of displayable regions. Objects surrounding the mobile machine are detected using an object detection sensor. A direction with respect to the mobile machine is detected for each of the objects. A current state of the mobile machine is determined. An object-directed indicator for each of the objects is generated based on the current state of the mobile machine. The object-directed indicator for each of the objects is displayed on the visual indication system at a particular displayable region based on the direction of the particular object.

Abstract: Among other things, we describe techniques for detecting objects in the environment surrounding a vehicle. A computer system is configured to receive a set of measurements from a sensor of a vehicle. The set of measurements includes a plurality of data points that represent a plurality of objects in a 3D space surrounding the vehicle. The system divides the 3D space into a plurality of pillars. The system then assigns each data point of the plurality of data points to a pillar in the plurality of pillars. The system generates a pseudo-image based on the plurality of pillars. The pseudo-image includes, for each pillar of the plurality of pillars, a corresponding feature representation of data points assigned to the pillar. The system detects the plurality of objects based on an analysis of the pseudo-image. The system then operates the vehicle based upon the detecting of the objects.

Abstract: Example implementations may relate to determining a strategy for a drop process associated with a light detection and ranging (LIDAR) device. In particular, the LIDAR device could emit light pulses and detect return light pulses, and could generate a set of data points representative of the detected return light pulses. The drop process could involve a computing system discarding data point(s) of the set and/or preventing emission of light pulse(s) by the LIDAR device. Accordingly, the computing system could detect a trigger to engage in the drop process, and may responsively (i) use information associated with the environment around the vehicle, operation of the vehicle, and/or operation of the LIDAR device as a basis to determine the strategy for the drop process, and (ii) engage in the drop process in accordance with the determined strategy.

Abstract: The invention relates to an autonomous underwater vehicle (AUV). The AUV includes a frame and tunnel thrusters for propelling and orientating the AUV, where the tunnel thrusters have inlets and outlets, each of outlets being directed in a different orientation, and are mounted to the frame. The AUV further includes fasteners for connecting the frame to a hull, where the fasteners have an orientation that is substantially parallel to the tunnel thrusters. The hull has a substantially spherical shape and further includes (1) a bottom plate with inlet openings, (2) a top plate with outlet openings, where the top plate and the bottom plate are affixed to the fasteners and hold plate rings of the hull in place, and (3) each of the plate rings that further includes a corresponding retention ring and corresponding central plates.

Abstract: This provides a system and method for handling the interchange of trailers between an over the road (OTR) truck and an autonomous vehicle (AV) yard truck in a facility yard includes an interchange zone (IZ) that is bounded by a predetermined boundary structure, having an OTR entry gate and an OTR exit gate on a first side and an AV entry gate and an AV exit gate on a second side. The system and method further includes a management process that selectively opens and closes each of the OTR entry gate, the OTR exit gate, the AV entry gate and the AV exit gate according to a predetermined set of rules.

Abstract: An eye-safe light detection and ranging system includes a virtual protective housing. A short range pulse is emitted at every measurement point in a field of view before conditionally emitting a long range pulse. Short range pulses result in accessible emissions that are eye-safe at short distances and long range pulses result in accessible emissions that are eye-safe at longer distances.