Systems and methods for autonomous provision replenishment are disclosed. Parts used in a manufacturing process are stored in an intermediate stock queue. When the parts are consumed by the manufacturing process and the number of parts in the queue falls below a threshold, a provision-replenishment signal is generated. One or more self-driving material-transport vehicles, a fleet-management system, and a provision-notification device.

A method and apparatus for controlling a vehicle are provided. A lane in which a target vehicle is driving, and an object in a vicinity of the lane are detected from an image of surroundings of the target vehicle, a degree of danger of the object is evaluated, driving information of the target vehicle is determined based on the degree of danger, and the target vehicle is controlled based on the driving information.

An autonomous vehicle (AV) includes a vehicle computing system configured to receive map data of a geographic location, obtain position estimate data of the autonomous vehicle and determine a route of the autonomous vehicle including a plurality of roadways in the plurality of submaps. The autonomous vehicle determines a route including a plurality of roadways, determines a first roadway in the plurality of roadways closest to the position estimate and a second roadway outside the plurality of roadways closest to the position estimate of the autonomous vehicle, and determines a pose relative to the first roadway or the second roadway based on a distance between the position estimate of the autonomous vehicle and a roadway associated with a prior pose of the autonomous vehicle to control travel of the autonomous vehicle based on the vehicle pose.

A model prediction control part of a control device includes an obstacle avoidance control unit that operates when there are a plurality of actual obstacles to be avoided. The obstacle avoidance control unit decides the position of a virtual obstacle from the positions of the plurality of actual obstacles acquired by an acquisition part so as to be positioned between the plurality of actual obstacles, and performs model prediction control by using, as the stage cost, the addition result of a standard cost and a virtual obstacle evaluation term for which a prescribed function, which uses, as parameters, at least the position of the virtual obstacle and the position of a moving body, is multiplied by a virtual obstacle weight. Using this configuration, when the moving body is caused to follow with respect to a target trajectory by the model prediction control, a collision with an obstacle can be avoided suitably.

A power machine can be configured to automatically travel along a planned path based on pursuit of a target point. A location of the target point along the planned path can be determined based one or more of local curvature of the planned path or travel speed of the power machine. In some cases, a circular buffer can be used to store mapping data.

The present invention provides a method and a device for map editing, includes: controlling a robot to build a node at a predefined time interval and to save a submap produced by a scanning process performed by the robot on a workspace at each node, when the robot moves in the workspace; combining the submaps to obtain an entire map through a first algorithm, where plural node marks respectively representing the submaps are shown on the entire map; selecting two node marks having parts determined to be abnormal on the entire map, and showing the submaps represented by the two node marks; and overlapping parts having same structure features in the two submaps correspondingly, and combining the parts through a second algorithm, and applying the combined parts into the entire map again to form a corrected entire map.

Systems and methods for managing data. The methods comprise by a computing system: generating publication identifiers and version values for source data to be stored into a data warehouse; causing a plurality of fact tables in the data warehouse to be populated with the source data and the publication identifiers; causing a publication table in the data warehouse to be updated to include the publication identifiers and the version values so as to be respectively associated with resource names; receiving a query for information directed to the plurality of fact tables; retrieving the publication identifiers from the publication table, in response to the query; and obtaining source data from each said fact table of the plurality of fact tables that is associated with publication identifiers that are stored in both the fact table and the publication table.

An auto clean machine, comprising: a light source configured to emit light to illuminate at least one light region outside and in front of the auto clean machine; a first image sensing area, configured to sense a first brightness distribution of the light region; a second image sensing area below the first image sensing area, configured to sense a second brightness distribution of the light region; and a processor, configured to control movement of the auto clean machine according the first brightness distribution and the second brightness distribution. The processor generates a wall detection result based on the first brightness distribution of the light region, generates a cliff detection result based on the second brightness distribution of the light region, and controls the movement of the auto clean machine according to the wall detection result and the cliff detection result.

Provided are systems and methods that perform multi-task and/or multi-sensor fusion for three-dimensional object detection in furtherance of, for example, autonomous vehicle perception and control. In particular, according to one aspect of the present disclosure, example systems and methods described herein exploit simultaneous training of a machine-learned model ensemble relative to multiple related tasks to learn to perform more accurate multi-sensor 3D object detection. For example, the present disclosure provides an end-to-end learnable architecture with multiple machine-learned models that interoperate to reason about 2D and/or 3D object detection as well as one or more auxiliary tasks. According to another aspect of the present disclosure, example systems and methods described herein can perform multi-sensor fusion (e.g., fusing features derived from image data, light detection and ranging (LIDAR) data, and/or other sensor modalities) at both the point-wise and region of interest (ROI)-wise level, resulting in fully fused feature representations.

Various examples are directed to systems and method operating an autonomous vehicle. A vehicle system may receive a plurality of inputs from a user of a vehicle, where the plurality of inputs includes a first labeling input received from the user and a first alert input received from the user. After determining that no user input has been received for an input threshold time, the vehicle system provides an alert prompt to the cockpit output device. This may cause the cockpit output device to provide the alert prompt to signal to the user to provide an alert input indicating that the user is alert.