Abstract: A system for deterministic trajectory selection based on uncertainty estimation includes a set of one or more computing systems. A method for deterministic trajectory selection includes receiving a set of inputs; determining a set of outputs; determining uncertainty parameters associated with any or all of the set of inputs and/or any or all of the set of outputs; and evaluating the uncertainty parameters and optionally triggering a process and/or action in response.

Abstract: A plurality of virtual individual sequences that can be reproduced by use of a display device in a motor vehicle are provided. At least some of the provided individual sequences are reproduced by use of the display device while traveling a route with the motor vehicle. A selection and determination of a reproduction order of the individual sequences are effected so as to match a characteristic of the route and such that the individual sequences connect a specified entry sequence and end sequence to form a coherent experience.

Abstract: A network system dynamically determines a route, including start and end points, for vehicles in a transportation network. The transportation network receives a service request from a user of the transportation network including an origin location for the trip and a destination location for the trip. The transportation network then generates a waypoint plan for one or more vehicles, which includes the requested origin and destination in addition to any previously requested origins and destinations included in the vehicles current route. The network system then determines a directionality for each of the waypoints in the waypoint plan and retrieves candidate start and end points that have an associated directionality within a threshold angle of the directionality of each waypoint and are proximate to the waypoint. The network system evaluates each combination of retrieved candidate points to select a route for the vehicle.

Abstract: Systems and methods are disclosed for navigating a host vehicle. In one implementation, at least one processor may be programmed to obtain images representative of an environment of a host vehicle; identify, from the images, a feature of a roadway used to navigate the host vehicle on a path, the identified feature of the roadway having an ambiguity along the path; obtain map data associated with the environment to resolve the ambiguity of the identified feature; and generate a trajectory to navigate the host vehicle on the roadway, using the map data associated with the environment.

Abstract: A vehicle can capture data for use in a simulator. Objects represented in the vehicle data can be instantiated in simulation and move according to object models/controllers. A user can tune how closely simulated motion of the object corresponds to the previously recorded data based on simulation costs. The scenarios can be used for testing and validating interactions and responses of a vehicle controller within a simulated environment. The scenarios can include simulated objects that traverse the simulated environment and perform actions based on the captured data and/or interactions within the simulated environment. Objects observed by the vehicle can be disregarded from simulation based on one or more filters. A user can override, augment, or otherwise modify simulations instantiated based on the one or more filters and captured data.

Abstract: Aspects of the disclosure relate to controlling a vehicle having an autonomous driving mode or an autonomous vehicle. For instance, a polygon representative of the shape and location of a first object may be received. A polyline contour representation of a portion of a polygon representative of the shape and location of a second object may be received. The polyline contour representation may be in half-plane coordinates and including a plurality of vertices and line segments. Coordinates of the polygon representative of the first object may be converted to the half-plane coordinate system. A collision location between the polyline contour representation and the polygon representative of the first object may be determined using the converted coordinates. The autonomous vehicle may be controlled in the autonomous driving mode to avoid a collision based on the collision location.

Abstract: Techniques are discussed for predicting occluded regions along a trajectory in an environment, a probability of occupancy associated with the predicted occluded regions, and controlling a vehicle to minimize occlusions and/or probabilities of occupancy. A vehicle may capture sensor data. Portions of an environment may be occluded by an object and may not be represented in the sensor data, and may be referred to as occluded regions. A candidate trajectory can be received and vehicle motion can be simulated to determine predicted occluded regions associated with the candidate trajectory. Data representing a predicted environment can be input to a machine learned model that can output information associated with the predicted occluded regions, such as a probability that the region is occupied by a vehicle or a pedestrian, for example. The candidate trajectory can be evaluated based on such probabilities, and the vehicle can be controlled based on the candidate trajectory.

Abstract: Among other things, a system provides speed behavior planning for vehicles with autonomous driving capabilities.

Abstract: A row unit has a frame with an upper portion and a lower portion. The upper portion has a parallel linkage and the lower portion is coupled to plural gauge wheels. A first sensor is configured to provide an output signal and a controllable device is coupled to the upper portion and configured to provide an adjustable down force. A dampening device is coupled to the upper portion and configured to provide adjustable dampening of the row unit based on the output signal.

Abstract: A system and method for proximate vehicle intention prediction for autonomous vehicles are disclosed. A particular embodiment is configured to: receive perception data associated with a host vehicle; extract features from the perception data to detect a proximate vehicle in the vicinity of the host vehicle; generate a trajectory of the detected proximate vehicle based on the perception data; use a trained intention prediction model to generate a predicted intention of the detected proximate vehicle based on the perception data and the trajectory of the detected proximate vehicle; use the predicted intention of the detected proximate vehicle to generate a predicted trajectory of the detected proximate vehicle; and output the predicted intention and predicted trajectory for the detected proximate vehicle to another subsystem.

Abstract: Predicting the future location of a user based on predicting the route that the user might take is disclosed. The routes used by the user in the past are indexed to generate a dictionary of routes which can be further augmented with contextual data. The prior routes are encoded within the dictionary such that each term representing a respective one of the prior routes comprises a collection of unique identifiers wherein each of the unique identifiers represents a segment of the respective one of the prior routes. Techniques of text prediction, term frequency for dictionary scores and other language processing techniques are used to predict the further route of the user.

Abstract: Aerial vehicles may include propulsion units having motors with drive shafts that may be aligned at a variety of orientations, propellers with variable pitch blades, and common operators for aligning the drive shafts at one or more orientations and for varying the pitch angles of the blades. The common operators may include plate elements to which a propeller hub is rotatably joined, and which may be supported by one or more linear actuators that may extend or retract to vary both the orientations of the drive shafts and the pitch angles of the blades. Operating the motors and propellers at varying speeds, gimbal angles or pitch angles enables the motors to generate forces in any number of directions and at any magnitudes. Attributes of the propulsion units may be selected in order to shape or control the noise generated thereby.

Abstract: A cleaning robot includes a detector configured to detect an obstacle; a determining portion configured to determine whether the cleaning robot is in an obstacle obstruction state; and a controller configured to control the first drive wheel to cross an obstacle and control the second drive wheel to cross the obstacle according to a detection result when the cleaning robot is in the obstacle obstruction state.

Abstract: An AV is described herein. The AV includes a lidar sensor system. The AV additionally includes a computing system that executes a gesture recognition component to determine, based upon lidar sensor data, whether a pedestrian in a driving environment of the AV is performing a hailing gesture. The AV can be configured to initiate a pickup maneuver to approach the pedestrian in response to determining that the pedestrian is performing a hailing gesture.

Abstract: A vehicle control device includes a sensor, a transfer case and a controller. The sensor detects a yaw rate of a vehicle. The transfer case distributes a drive force from a motive power source to front wheels and rear wheels. The controller determines a road surface friction coefficient to be low upon detecting an absolute value of the yaw rate during forward travel of the vehicle to be equal to or greater than a prescribed value other than zero, determines the road surface friction coefficient to be high upon detecting the absolute value is less than prescribed value, and controls a distribution amount of the transfer case based on a determination result of the road surface friction coefficient.

Abstract: A system for generating an alimentary combination help update is disclosed. The system comprises a computing device configured to receive a request for an alimentary combination from a user. Computing device may generate an initial physical transfer path as a function of the request. Computing device may identify a trouble state as a function of the request for the alimentary combination. The trouble state is classified to at least a source. Computing device may generate a modified physical transfer path as a function of the initial physical transfer path and the source. A method for generating an alimentary combination help update is also disclosed.

Abstract: A method for controlling operation of an autonomous vehicle and a related system includes: comparing, at a remote computing system operably connected with a processor in the autonomous vehicle, a first signal indicative of an environment in which the autonomous vehicle is arranged and a second signal indicative of the environment in which the autonomous vehicle is arranged. The method also includes generating, at the remote computing system, a restriction command to restrict operation of the autonomous vehicle if the comparison indicates that the first signal and the second signal do not correspond. The first signal is generated by the remote computing system based on input received from the processor of the autonomous vehicle. The second signal is a processed signal received from an external computing system operably connected with both the remote computing system and the processor in the autonomous vehicle.

Abstract: A refuse vehicle has a chassis supporting a plurality of wheels, as well as a motor. A vehicle body is also supported by the chassis and defines a receptacle for storing refuse. A lifting system is coupled to the vehicle body and is movable between a first position and a second position vertically offset from the first position. The refuse vehicle also has a processing unit in communication with the lifting system and the motor. The processing unit is configured to access and toggle through a plurality of preset operational modes stored within a memory to adjust performance parameters of the refuse vehicle.

Abstract: Thermal image based precision drone landing systems and methods are disclosed herein. An example system can include a landing surface for receiving an unmanned aerial vehicle, a heat-based guidance assembly comprising a plurality of heat emitting units, and a controller that controls operation of the plurality of heat emitting units to create a pattern that is recognized by the unmanned aerial vehicle and guides the unmanned aerial vehicle in landing on the landing surface.

Abstract: Some embodiments provide a fully-actuated suspension system which can provide adjustable displacement of a sprung mass from a neutral suspension position over an unsprung mass. The system includes a variable pressure air spring which can adjust the neutral suspension position and execute low-frequency displacements and a hydraulically-driven piston which can execute high-frequency displacements. The system can communicate information to a driver, via haptic feedback provided via actuator displacements, which can augment the driver's situational awareness. The system can provide augmented vehicle braking via displacing the unsprung mass of the vehicle towards the surface upon which the vehicle rests to increase the normal force and contact area of the unsprung mass on the surface, unload torsion of the wheel induced by applied braking pressure to the wheel, etc.