The present invention provides a method for automatic obstacle avoidance of a robot, and this method comprises: according to a depth sensor, obtaining depth data of movable areas of a scene in which the robot lies in; according to a preset depth threshold value, binarizing the depth data; according to an average value or a sum value of binarization processing result of areas, identifying an area where the robot is farther away from an obstacle as a moving direction of the robot. In the present invention, since the depth data is collected, no measurement dead zone is prone to occur; moreover, calculating the average value or the sum value of the binarized depth data only needs to perform a simple comparison, the processing is simpler, the processing speed is fast, and the requirement of the system and the cost are lower.

A double-threshold mechanism is used for implementing the follow-me function of a mobile robot. Initially, a user comes to a mobile robot and turns on its follow-me function. Then, the mobile robot is in the follow-me mode or can simply be described as following the user. When the user moves away from the robot, the robot determines whether the distance between itself and the user exceeds a first distance threshold. If so, the robot starts moving to follow the user. Otherwise, the robot stays put. While following the user's movement, the robot continues to monitor the distance between itself and the user. When the robot determines that the distance between them is less than a second distance threshold—because the user has slowed down or stopped, for example—the robot stops moving. The second distance threshold is lower than the first distance threshold.

A robot includes a mover, a determiner, and a controller. The mover moves the robot. The determiner determines a touch type by a predetermined object. The controller controls the mover so as to move the robot close to the predetermined object when the determiner determines that the touch type by the predetermined object is petting, or so as to move the robot apart from the predetermined object when the determiner determines that the touch type by the predetermined object is to hitting.

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.

A robotic system comprising a mobile robot including a body housing a rechargeable power source and first electrical contact means disposed on the body and a docking station including second electrical contact means, wherein the mobile robot is dockable on the docking station in order to charge the rechargeable power source. The first electrical contact means includes at least one electrical contact aligned on a first contact axis and the second electrical contact means includes at least one elongate contact, wherein when the robot is docked on the docking station such that electrical contact is established between the first electrical contact means and the electrical contact means. The at least one elongate contact extends in a direction that is transverse to the first contact axis which permits electrical contact to be established between the robot and the docking station while accommodating a degree of lateral and angular misalignment therebetween.

A line bypass system includes a support structure including a first support portion and a second support portion spaced apart from the first support portion. The support structure includes an attachment portion that attaches the first support portion to the second support portion. The first support portion and the second support portion define a first opening on a first side of the attachment portion and a second opening on a second side of the attachment portion. The first opening movably receives a first guide wire and the second opening movably receives a second guide wire.

Patient support apparatuses, such as beds, cots, stretchers, recliners, or the like, include control systems with one or more image, radar, and/or laser sensors to detect objects and determine if a likelihood of collision exists. If so, the control system controls the speed and steering of the patient support apparatus in order to reduce the likelihood of collision. The control system may be adapted to autonomously drive the patient support apparatus, to transmit a message to a remote device indicating whether it is occupied by a patient or not, and/or to transmit its route to the remote device. The remote device may determine an estimate of a time of arrival of the patient support apparatus at a particular destination and/or determine a distance of the patient support apparatus from the particular destination.

Modern farming is currently being done by powerful ground equipment or aircraft that weigh several tons and treat uniformly tens of hectares per hour. Automated farming can use small, agile, lightweight, energy-efficient automated robotic equipment that flies to do the same job, even able to farm on a plant-by-plant basis, allowing for new ways of farming. A hybrid airship-drone has both passive lift provided by a gas balloon and active lift provided by propellers. A hybrid airship-drone may be cheaper, more stable in flight, and require less maintenance than other aerial vehicles such as quadrocopters. However, hybrid airship-drones may also be larger in size and have more inertia that needs to be overcome for starting, stopping and turning.

Embodiments are generally directed apparatuses, methods, techniques and so forth to select two or more processing units of the plurality of processing units to process a workload, and configure a circuit switch to link the two or more processing units to process the workload, the two or more processing units each linked to each other via paths of communication and the circuit switch.

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.