Methods, systems, and apparatus for receiving a reference to an object located in an environment of a robot, accessing mapping data that indicates, for each of a plurality of object instances, respective probabilities of the object instance being located at one or more locations in the environment, wherein the respective probabilities are based at least on an amount of time that has passed since a prior observation of the object instance was made, identifying one or more particular object instances that correspond to the referenced object, determining, based at least on the mapping data, the respective probabilities of the one or more particular object instances being located at the one or more locations in the environment, selecting, based at least on the respective probabilities, a particular location in the environment where the referenced object is most likely located, and directing the robot to navigate to the particular location.

A technique for displaying a representative path associated with a robotic device. The technique includes detecting at least one reference point within a first image of a workspace, generating the representative path based on path instructions associated with the robotic device and the at least one reference point, and displaying the representative path within the workspace.

A robotic system that includes a mobile robot linked to a plurality of remote stations. One of the remote stations includes an arbitrator that controls access to the robot. Each remote station may be assigned a priority that is used by the arbitrator to determine which station has access to the robot. The arbitrator may include notification and call back mechanisms for sending messages relating to an access request and a granting of access for a remote station.

Methods, systems, and apparatus, including computer-readable media storing executable instructions, for enhancing robot learning. In some implementations, a robot stores first embeddings generated using a first machine learning model, and the first embeddings include one or more first private embeddings that are not shared with other robots. The robot receives a second machine learning model from a server system over a communication network. The robot generates a second private embedding for each of the one or more first private embeddings using the second machine learning model. The robot adds the second private embeddings to the cache of the robot and removes the one or more first private embeddings from the cache of the robot.

A deep-sea exploration multi-joint underwater robot system and a spherical glass pressure housing including a titanium band are provided. The system includes a multi-joint underwater robot having a multiple of first and second pressure housings withstanding deep-sea pressure and shielding built-in equipment from seawater and performing close precision seabed exploration obtaining marine research data to transmit underwater status data, a mothership receiving and storing marine research and underwater status data and monitoring and controlling moving directions of multi-joint underwater robot, and a depressor having third pressure housing, linked with mothership by primary cable and multi-joint underwater robot by secondary cable, and preventing transmission of primary cable water resistance to multi-joint underwater robot, wherein first spherical pressure housings are mounted on robot body frame, second cylindrical pressure housings are mounted between left and right legs, and the third cylindrical pressure housing is mounted inside the depressor platform.

Generally, a system for use in a robotic surgical system may be used to determine an attachment state between a tool driver, sterile adapter, and surgical tool of the system. The system may include sensors used to generate attachment data corresponding to the attachment state. The attachment state may be used to control operation of the tool driver and surgical tool. In some variations, one or more of the attachment states may be visually output to an operator using one or more of the tool driver, sterile adapter, and surgical tool. In some variations, the tool driver and surgical tool may include electronic communication devices configured to be in close proximity when the surgical tool is attached to the sterile adapter and tool driver.

A system, method, and apparatus for changing a set of old tools for a set of new tools may be presented. The system may comprise a crawler robot, a robotic arm, a tool changer, a vision system, and at least one of a tool rack or a storage area. The tool changer may be an end effector of the robotic arm. The tool changer may comprise a number of grippers and a number of movement assemblies. The number of grippers may perform at least one of moving a set of new tools to the crawler robot or removing the set of old tools from the crawler robot. The number of movement assemblies may be associated with the number of grippers. The vision system may be associated with at least one of the robotic arm and the tool changer.

Crosstalk mitigation among cameras in neighboring monitored workcells is achieved by computationally defining a noninterference scheme that respects the independent monitoring and operation of each workcell. The scheme may involve communication between adjacent cells to adjudicate non-interfering camera operation or system-wide mapping of interference risks and mitigation thereof. Mitigation strategies can involve time-division and/or frequency-division multiplexing.

A robotic system includes a robotic vehicle having a propulsion system, one or more sensors that image data representative of an external environment, and a controller that determines a waypoint for the robotic vehicle to move toward. The controller determines limitations on movement of the robotic vehicle toward a waypoint. The limitations are based on the image data. The controller controls the propulsion system to move the robotic vehicle to the waypoint subject to the limitations on the movement to avoid colliding with one or more objects. The controller determines one or more additional waypoints subsequent to the robotic vehicle reaching the waypoint, determines one or more additional limitations on the movement of the robotic vehicle toward each of the respective additional waypoints, and control the propulsion system of the robotic vehicle to sequentially move the robotic vehicle to the one or more additional waypoints.

A robotic system includes one or more optical sensors configured to separately obtain two dimensional (2D) image data and three dimensional (3D) image data of a brake lever of a vehicle, a manipulator arm configured to grasp the brake lever of the vehicle, and a controller configured to compare the 2D image data with the 3D image data to identify one or more of a location or a pose of the brake lever of the vehicle. The controller is configured to control the manipulator arm to move toward, grasp, and actuate the brake lever of the vehicle based on the one or more of the location or the pose of the brake lever.