This application provides a swimming pool robot, including a robot body, a filter, a control unit, and a moving mechanism. Operating environments of the swimming pool robot at least include a first operating environment and a second operating environment. The moving mechanism at least includes a first moving mechanism configured to drive the swimming pool robot to move in the first operating environment and a second moving mechanism configured to drive the swimming pool robot to move in the second operating environment. The first operating environment is an underwater environment. The second operating environment is a non-underwater environment. The control unit is capable of controlling, based on a current operating environment of the swimming pool robot, a moving mechanism corresponding to the current operating environment of the swimming pool robot to drive the swimming pool robot to move. According to this application, operating efficiency of the robot can be improved.

An operation system performs autonomous operation by using an operation server for an autonomous driving vehicle. The operation server includes a memory unit containing three-dimensional map data. An autonomous driving vehicle connects to the operation server via a wireless network. A vehicle control unit creates a traveling route based on the map data received and, when an elevator of a building is to be used, creates elevator usage information and elevator control information, including the boarding and exiting floors. The elevator is equipped with an elevator control unit that is connected to the operation server to control ascending and descending of an elevator cage. A control unit of the autonomous driving vehicle transmits the elevator usage information and the elevator control information to the elevator control unit. The elevator control unit gives a voice announcement from a voice output unit in the elevator cage.

A method and device for operation planning of a movable platform, and a storage medium are provided. The method includes: obtaining a three-dimensional model of an operation area of a movable platform; controlling a motion trajectory of a virtual movable platform in the three-dimensional model based on a detected motion control operation; determining multiple target position points on the motion trajectory based on a detected position confirmation operation, where the multiple target position points are used to generate an operation path of the movable platform in the operation area. By simulating the control of the movable platform in the real world, controlling the motion trajectory of the virtual movable platform in the three-dimensional model of the operation area, and thereby determining target position points, the operation path determined using this method is safer, more reasonable, and has higher accuracy.

A computer-implemented method when executed by data processing hardware causes the data processing hardware to perform operations. The operations include detecting a candidate support surface at an elevation less than a current surface supporting a legged robot. A determination is made on whether the candidate support surface includes an area of missing terrain data within a portion of an environment surrounding the legged robot, where the area is large enough to receive a touchdown placement for a leg of the legged robot. If missing terrain data is determined, at least a portion of the area of missing terrain data is classified as a no-step region of the candidate support surface. The no-step region indicates a region where the legged robot should avoid touching down a leg of the legged robot.

A semantic local map generation device may include a multi-sensor unit including a RGBD sensor and an inertial measurement unit (IMU) sensor attached to a body of a robot, and a data processing unit operatively connected to the multi-sensor unit and configured for estimating a pose of the robot and a semantic point cloud with respect to a driving region from sensor data obtained from the multi-sensor unit, and generate a semantic local map based on the estimated pose and the estimated semantic point cloud.

The present disclosure relates to a system that comprises a lab space housing multiple workstations comprising at least two workstations each performing a different type of bio lab task from another. The lab space can have a lab floor space comprising an occupied lab floor space on which the multiple workstations are occupied, and an unoccupied lab floor space on which a stand-alone robotic arm moves through.

A robot comprises an auger-based drive system, a memory, and a processor coupled with the memory and configured to control movement of the robot, via the auger-based drive system, relative to grain in a grain bin. The processor is further configured to direct traversal, by the robot, of a landing zone portion of a surface of a pile of the grain during load-in of the grain to disperse broken grain and foreign material away from the landing zone portion. The landing zone portion is located in a center of the grain bin where the grain lands as it is augured into the grain bin during load-in. The dispersal is affected in part by rotation of augers of the auger-based drive system.

Disclosed are apparatuses, systems, and techniques that train and use trained language models to assist users with complex systems installation, troubleshooting, and/or maintenance. A method can include determining, responsive to data received from a real robot having one or more real sensors and operating in a real environment, that the real robot needs assistance to navigate from a current state of the real robot within the real environment, causing simulated data to be obtained from one or more simulated sensors within a simulated environment at least partially modeling the real environment, the one or more simulated sensors including at least one simulated sensor different from the one or more real sensors, and using the simulated data to control operation of the real robot within the real environment in order to navigate the real robot from the current state.

A method including receiving a data structure including a model including a virtual object. The virtual object has spatial elements that form an area of the virtual object. The method also includes applying a ray tracing algorithm to the model. The ray tracing algorithm directs virtual rays from a remote point in the model towards the virtual object. The method also includes determining intersection values. Each of the intersection values represents a corresponding number of times that the virtual rays intersect a corresponding one of the spatial elements. The method also includes generating, from the intersection values, a coverage value representing a percentage of the area that is covered by the virtual rays. The method also includes returning the coverage value.

According to an aspect, an apparatus may obtain map data associated with a tunnel system of an underground worksite, obtain a start position and an end position for a mining vehicle configured to operate in the tunnel system. The apparatus may further obtain vehicle information including at least kinematic restrictions and space restrictions associated with structural body members of the mining vehicle and a movable work device of the mining vehicle, the kinematic restrictions including movability limits of the movable work device, and determine at least partly based on the map data, the start and end positions, the vehicle information, and a collision free continuous route between the start and end positions for the mining vehicle. The collision free continuous route having at least one collision free position for the movable work device within the movability limits of the movable work device along the collision free continuous route.