Abstract: The disclosed computer-implemented method may include receiving, by a computing device, an original video to relight. Additionally, the method may include predicting, by the computing device using a de-lighting model trained on a hybrid dataset of lighting-rich data and motion-rich data, an albedo video corresponding to the original video. The method may also include generating, by the computing device using a relighting model trained on the hybrid dataset, a relit video based on the albedo video under a specified lighting condition based on an input high dynamic range (HDR) map. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: Methods for motion-controllable video diffusion include extracting optical flow fields from an input video and computing warped noise by iteratively warping noise between consecutive frames using the optical flow fields. The iteratively warping includes (i) re-Gaussianizing expanded pixel regions by sampling fresh Gaussian noise, and (ii) aggregating contracted pixel regions by merging noise particles and renormalizing variance to preserve spatial Gaussianity. An output video is generated by initializing a diffusion process with the warped noise and iteratively denoising to produce temporally coherent output frames. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: An automatic loading system for screening wood shavings, wherein discharging side of a material receiving and conveying mechanism is connected to feeding side of shaving arranging and conveying mechanisms, each shaving arranging and conveying mechanism includes first slide-down board, first conveying mechanism, second slide-down board, second conveying mechanism, third slide-down board, and third conveying mechanism sequentially disposed along wood shavings conveying direction, width of the first slide-down board is gradually reduced along wood shavings conveying direction to cause its discharging side's width corresponds to wood shavings'width, a baffle board is disposed above a feeding end of the second conveying mechanism with a set gap, and a feeding end of the third slide-down board locates below a discharging end of the second conveying mechanism at a first set distance, and a discharging end located above a feeding end of the third conveying mechanism at a second set distance.

Abstract: The disclosed computer-implemented method may include receiving, by a computing device, multi-view flat-lit performance data of a subject. Additionally, the method may include rendering, by the computing device, a dynamic sequence of novel-view flat-lit images of the subject based on a deformable three-dimensional Gaussian splatting (3DGS) model. The method may also include providing the rendered dynamic sequence of flat-lit images as input to a diffusion-based relighting model trained on the multi-view flat-lit performance data of the subject. Furthermore, the method may include generating, by the computing device using the diffusion-based relighting model, a relit sequence of the subject under a specified lighting condition. Various other methods, systems, and computer-readable media are also disclosed.

Abstract: Embodiments of this specification provide a map creating method and apparatus for an autonomous robot, a device, and a storage medium. The map creating method for an autonomous robot includes: acquiring an initial map selected from a target database, wherein the initial map includes an initial boundary; causing the autonomous robot to perform boundary detection to acquire a measured boundary, wherein positioning precision of the autonomous robot satisfies a preset condition; and correcting the initial boundary according to the measured boundary.

Abstract: The present disclosure relates to a method and an apparatus for establishing a positioning network. The positioning network includes a data processing center and at least one reference station, and one node in the positioning network represents one reference station. The method includes: determining, if a first historical positioning network capable of forming a new positioning network with a newly added node exists in a network list of the data processing center, whether the newly added node forms the new positioning network with the first historical positioning network; and determining, if the network list does not exist in the data processing center, whether the newly added node is capable of forming a new positioning network with nodes in a first node information list. Before network real-time kinematic (RTK) is formed, a user can use a single-baseline RTK positioning service. The network RTK is formed once a networking condition is met.

Abstract: Embodiments of this specification provide an autonomous robot, a moving path planning method and apparatus therefor, and a storage medium. The method includes: obtaining terrain distribution information of a target working area; determining, according to the terrain distribution information, whether a slope area exists in the target working area; and determining, if a slope area exists in the target working area, a width value between adjacent path segments according to the terrain distribution information during planning of a moving path in the slope area, to keep a work overlap value between the adjacent path segments within a specified range.

Abstract: A self-moving device including an image detection module, detecting an environment around the self-moving device to generate an environmental image; a first recognition module, recognizing a specific object in the image based on the environmental image to generate a first recognition signal; a first communication module, selectively sending the environmental image and/or the first recognition signal to a server and receiving a second recognition signal corresponding to the environmental image; and a control module, controlling an action of the self-moving device according to the first recognition signal and/or the second recognition signal. The techniques ensure that the self-moving device obtains an accurate recognition result in time and performs an action accordingly.

Abstract: A map establishing method includes: generating a working region map and an initial shadow section, the working region map being a map of a boundary, and the initial shadow section being a part of the boundary on which a positioning signal does not meet a quality requirement; generating an initial shadow region according to the initial shadow section; exploring the initial shadow region, and collecting positioning signal quality data and positioning coordinates during exploration; and generating a corrected shadow region according to the positioning signal quality data and the positioning coordinates. A self-moving device includes: a controller; a map generator; and an exploration assembly and a shadow region corrector. An automatic working system is provided with the self-moving device. An actual range of a shadow region is first explored, and then a corrected shadow region is obtained, so that a working region map can be updated.

Abstract: The embodiments relate to a self-moving device, moving and working in a working area, including: an image detection module, detecting an environment around the self-moving device to generate an environmental image; a first recognition module, recognizing a specific object in the image based on the environmental image to generate a first recognition signal; a first communication module, selectively sending the environmental image and/or the first recognition signal to a server and receiving a second recognition signal corresponding to the environmental image; and a control module, controlling an action of the self-moving device according to the first recognition signal and/or the second recognition signal. Beneficial effects of embodiments are as follows: It is ensured that the self-moving device can obtain an accurate recognition result in time and performs an action accordingly.

Abstract: Embodiments of this specification provide a map creating method and apparatus for an autonomous robot, a device, and a storage medium. The map creating method for an autonomous robot includes: acquiring an initial map selected from a target database, wherein the initial map includes an initial boundary; causing the autonomous robot to perform boundary detection to acquire a measured boundary, wherein positioning precision of the autonomous robot satisfies a preset condition; and correcting the initial boundary according to the measured boundary.

Abstract: A multi-machine cooperation method, a scheduling device, and a multi-machine cooperation system are described. The multi-machine cooperation method includes: determining, by a first autonomous robot when detecting an abnormal condition during operation, whether the abnormal condition can be independently processed; and when the abnormal condition cannot be independently processed, sending, by the first autonomous robot, an assistance request to another device in an Internet of Things in which the first autonomous robot is located. In the specification, a multi-machine cooperation operation between autonomous robots or between an autonomous robot and another device can be implemented.

Abstract: A self-moving device, including: a moving module, a task execution module, a control module. The control module is electrically connected to the moving module and the task execution module, controls the moving module to actuate the self-moving device to move, controls the task execution module to execute a working task. The self-moving device further includes a satellite navigation apparatus, electrically connected to the control module and configured to receive a satellite signal and output current location information of the self-moving device. The control module determines whether quality of location information output by the satellite navigation apparatus at a current location satisfies a preset condition, controls, if the quality does not satisfy the preset condition, the moving module to actuate the self-moving device to change a moving manner, to enable quality of location information output by the satellite navigation apparatus at a location after the movement to satisfy the preset condition.

Abstract: A self-moving device, including: a moving module, a task execution module, a control module. The control module is electrically connected to the moving module and the task execution module, controls the moving module to actuate the self-moving device to move, controls the task execution module to execute a working task. The self-moving device further includes a satellite navigation apparatus, electrically connected to the control module and configured to receive a satellite signal and output current location information of the self-moving device. The control module determines whether quality of location information output by the satellite navigation apparatus at a current location satisfies a preset condition, controls, if the quality does not satisfy the preset condition, the moving module to actuate the self-moving device to change a moving manner, to enable quality of location information output by the satellite navigation apparatus at a location after the movement to satisfy the preset condition.

Abstract: The present invention discloses an automatic operation system. The automatic operation system includes a lawn mower. The lawn mower may include: a housing; a moving module; a cutting module; an energy module, configured to provide energy for the intelligent lawn mower; an image capturing module, configured to capture image information near the intelligent lawn mower, and control movement and/or operation of the intelligent lawn mower according to the captured image information; and a control module, electrically connected to the moving module, the cutting module, and the image capturing module and configured to control the intelligent lawn mower to move and/or operate within an operation region. The intelligent lawn mower includes at least two operation modes, and the image capturing module has at least two operation positions relative to the housing when the intelligent lawn mower operates in the at least two operation modes.

Abstract: A self-moving robot includes a shell, a driving module, driving the self-moving robot to move on the ground; a mowing module, executing mowing work; an energy module, providing energy for the self-moving robot; a control module, controlling the self-moving robot to automatically move and execute work, the self-moving robot further includes a cleaning module executing ground cleaning work; the self-moving robot has a mowing mode and a cleaning mode, under the mowing mode, the control module controls the self-moving robot to execute mowing work, and under the cleaning mode, the control module controls the self-moving robot to execute cleaning work.

Abstract: The present invention provides a self-moving device and a working method for same. The self-moving device may include: a first control module and a second control module. The first control module and the second control module are configured to communicate with each other and work collaboratively to control a moving mechanism and a working module. The second control module is configured to: control the self-moving device to perform a safety assurance operation; and perform self-checking on hardware and a control program related to control of performing of the safety assurance operation. In the first control module and the second control module, only the second control module is configured to perform the self-checking according to a predetermined plan during working of the self-moving device. Implementations of this application provide a self-moving device with high safety performance.

Abstract: Embodiments of this specification provide a working map construction method and apparatus, a robot, and a storage medium. The method includes: determining a moving path of a robot when the robot moves forward as a first forward moving path; determining, after the robot moves backward, a position of the robot when the robot changes from moving backward to moving forward again as a correction position; determining an auxiliary position on the first forward moving path according to the correction position in a case that the correction position is not on the first forward moving path; and determining a correction path according to the correction position and the auxiliary position, so as to construct a working map of the robot according to the correction path and the first forward moving path.

Abstract: A self-moving device, including: a moving module, a task execution module, a control module. The control module is electrically connected to the moving module and the task execution module, controls the moving module to actuate the self-moving device to move, controls the task execution module to execute a working task. The self-moving device further includes a satellite navigation apparatus, electrically connected to the control module and configured to receive a satellite signal and output current location information of the self-moving device. The control module determines whether quality of location information output by the satellite navigation apparatus at a current location satisfies a preset condition, controls, if the quality does not satisfy the preset condition, the moving module to actuate the self-moving device to change a moving manner, to enable quality of location information output by the satellite navigation apparatus at a location after the movement to satisfy the preset condition.

Abstract: The present disclosure relates to a method and an apparatus for establishing a positioning network. The positioning network includes a data processing center and at least one reference station, and one node in the positioning network represents one reference station. The method includes: determining, if a first historical positioning network capable of forming a new positioning network with a newly added node exists in a network list of the data processing center, whether the newly added node forms the new positioning network with the first historical positioning network; and determining, if the network list does not exist in the data processing center, whether the newly added node is capable of forming a new positioning network with nodes in a first node information list. Before network real-time kinematic (RTK) is formed, a user can use a single-baseline RTK positioning service. The network RTK is formed once a networking condition is met.