A traveling processing unit causes a work vehicle to automatically travel along a target route set within a field. A detection processing unit detects an obstacle located on an outer periphery of the field, while the work vehicle is traveling along the target route in a headland area of the field. In a case where the obstacle is a ridge, the traveling processing unit causes the work vehicle to travel along an avoidance route inside the field than the target route.

This application provides a fork collision processing method and apparatus, a robot, a device, a medium, and a product. The method includes: determining a collision type when it is detected that a fork of a robot encounters a collision; determining a fork collision processing strategy according to the collision type; and processing the fork collision according to the fork collision processing strategy. In this application, when it is detected that the fork of the robot encounters a collision, the collision type of the fork collision is first determined, then the fork collision processing strategy is determined according to the determined collision type, and finally the fork collision event is processed according to the determined fork collision processing strategy.

Aspects of the subject disclosure may include, for example, a method in which a processing system configures one or more robots to perform tasks in an establishment, and assigns to the robots privileges and/or priorities in accordance with a policy. The method also includes detecting a situation in the establishment requiring performance of a task; facilitating the performance of the task by at least one of the robots; and dynamically reprogramming at least one of the robots in response to the situation to perform a specialized task to address the situation. Other embodiments are disclosed.

A robot is operated in an autonomous mode of operation to perform a plurality of tasks. It is determined that a later task of the plurality of tasks needs human assistance while performing a current task of the plurality of tasks. The human assistance is scheduled for the later task. A teleoperator is communicated with to perform the human assistance associated with the later task.

In one embodiment, a method includes sending a set of instructions to present, on a computing device, one or more available locations for a vehicle to pick-up or drop-off a user in an area. The one or more available locations are based on sensor data of the area that is captured by the vehicle. The method includes receiving a user selection to select a location associated with the area for the vehicle to pick-up or drop-off the user. The method includes adjusting a viability value of one or more locations to pick-up or drop-off the user. The viability value is adjusted based at least on the selected location. The method includes, based on the adjusted viability value of the one or more locations, determining a location from the one or more locations. The method includes instructing the vehicle to travel to the determined location.

A method for controlling a driving function of a movable device, including a vehicle or a robot. The method includes: reading in parameters for controlling the driving function; using a map, wherein the map has at least a first region and a second region, wherein at least one value of a swarm behavior is entered in the second region; locating the device in the map; using the parameters to ascertain the driving function, if the movable device is in the first region of the map; using the at least one value of the swarm behavior to ascertain the driving function, if the movable device is in the second region of the map; controlling the device with the ascertained driving function. A method for creating a map for ascertaining a driving function of a movable device, a computing unit, a computer program, and a machine-readable storage medium, are also described.

A system and method for a digital co-pilot are provided. The method includes receiving a plurality of inputs from a vehicle operating systems, wherein the plurality of inputs comprise engine parameters, control system parameters, or electrical system parameters, identifying one or more first trends in the plurality of inputs, diagnosing one or more first potential conditions based on the first trends, determining a first course of action based on diagnosing the one or more potential conditions, and generating one or more first commands to vehicle controls based on determining the first course of action.

An event driven detection model is disclosed. A model operates at a node to identify relevant video data from video streams generated by cameras. Video data that is not relevant is discarded. An objectness score is generated for the relevant video data. The objectness score and position data from position sensors is used to infer an event. When an event is inferred by the model, a decision may be made and performed.

A method for generating a trajectory for a vehicle based on an abstract space of control parameters associated with the vehicle may include applying a machine learning model to determine an abstract space representation of the trajectory, which includes a sequence of control parameters associated with the vehicle. For instance, application of the machine learning model may include performing a search of the abstract space parameterized by control parameters that include derivatives of the position of the vehicle. Examples of control parameters include velocity, acceleration, jerk, and snap. A physical space representation of the trajectory may be determined by at least mapping the sequence of control parameters to a sequence of positions for the vehicle. A motion of the vehicle may be controlled based at least on the physical space representation of the trajectory. Related systems and computer program products are also provided.

Techniques for segmenting sensor data are discussed herein. Data can be represented in individual levels in a multi-resolution voxel space. A first level can correspond to a first region of an environment and a second level can correspond to a second region of an environment that is a subset of the first region. In some examples, the levels can comprise a same number of voxels, such that the first level covers a large, low-resolution region, while the second level covers a smaller, higher-resolution region, though more levels are contemplated. Operations may include analyzing sensor data represented in the voxel space from a perspective, such as a top-down perspective. From this perspective, techniques may generate masks that represent objects in the voxel space. Additionally, techniques may generate segmentation data to verify and/or generate the masks, or otherwise cluster the sensor data.