Abstract: A robot navigation system includes a robot, a navigation beacon, and a cover structure. The robot includes a chassis, an omni-directional receiver, and at least one directional receiver. The navigation beacon includes an omni-directional infrared emitter and at least one directional infrared emitter. The cover structure is configured to block infrared transmissions between the at least one directional infrared emitter and the directional receiver while simultaneously permitting transmissions between the omni-directional infrared emitter and the omni-directional receiver. The cover structure may be made of a black silicone material.

Abstract: A threshold learning control system for learning a controller of a robot. The system includes a threshold learning module, a regime classifier, and an exploratory controller, each receiving sensory inputs from a sensor system of the robot. The regime classifier determines a control regime based on the received sensor inputs and communicates the control regime to the threshold learning module. The exploratory controller also receives control parameters from the threshold learning module. A control arbiter receives commands from the exploratory controller and limits from the threshold learning module. The control arbiter issues modified commands based on the received limits to the robot controller.

Abstract: A robotic vehicle (10,100,150A,150B150C,160,1000,1000A,1000B,1000C) includes a chassis (20,106,152,162) having front and rear ends (20A,152A,20B,152B) and supported on right and left driven tracks (34,44,108,165). Right and left elongated flippers (50,60,102,154,164) are disposed on corresponding sides of the chassis and operable to pivot. A linkage (70,156,166) connects a payload deck assembly (D1,D2,D3,80,158,168,806), configured to support a removable functional payload, to the chassis. The linkage has a first end (70A) rotatably connected to the chassis at a first pivot (71), and a second end (70B) rotatably connected to the deck at a second pivot (73). Both of the first and second pivots include independently controllable pivot drivers (72,74) operable to rotatably position their corresponding pivots (71,73) to control both fore-aft position and pitch orientation of the payload deck (D1,D2,D3,80,158,168,806) with respect to the chassis (20,106,152,162).

Abstract: A navigational control system for altering movement activity of a robotic device operating in a defined working area, comprising a transmitting subsystem integrated in combination with the robotic device, the transmitting subsystem comprising beam emitters for emitting a number of directed beams, each directed beam having a predetermined emission pattern, and a receiving subsystem functioning as a base station that includes a navigation control algorithm that defines a predetermined triggering event for the navigational control system and a set of detection units positioned within the defined working area in a known spaced-apart relationship, the set of detection units being configured and operative to detect one or more of the directed beams emitted by the transmitting system; and wherein the receiving subsystem is configured and operative to process the one or more detected directed beams under the control of the navigational control algorithm to determine whether the predetermined triggering event has occu

Abstract: A grasper includes a base, a finger, a tendon cable and a magnetic breakaway mechanism. The finger has a proximal end connected to the base by a proximal joint. The tendon cable is configured to move the finger relative to the base. The magnetic breakaway mechanism releasably couples the finger to the base.

Abstract: A threshold learning control system for learning a controller of a robot. The system includes a threshold learning module, a regime classifier, and an exploratory controller, each receiving sensory inputs from a sensor system of the robot. The regime classifier determines a control regime based on the received sensor inputs and communicates the control regime to the threshold learning module. The exploratory controller also receives control parameters from the threshold learning module. A control arbiter receives commands from the exploratory controller and limits from the threshold learning module, The control arbiter issues modified commands based on the received limits to the robot controller.

Abstract: The invention is related to methods and apparatus that use a visual sensor and dead reckoning sensors to process Simultaneous Localization and Mapping (SLAM). These techniques can be used in robot navigation. Advantageously, such visual techniques can be used to autonomously generate and update a map. Unlike with laser rangefinders, the visual techniques are economically practical in a wide range of applications and can be used in relatively dynamic environments, such as environments in which people move. One embodiment further advantageously uses multiple particles to maintain multiple hypotheses with respect to localization and mapping. Further advantageously, one embodiment maintains the particles in a relatively computationally-efficient manner, thereby permitting the SLAM processes to be performed in software using relatively inexpensive microprocessor-based computer systems.

Abstract: System and method for behavior based control of an autonomous vehicle. Actuators (e.g., linkages) manipulate input devices (e.g., articulation controls and drive controls, such as a throttle lever, steering gear, tie rods, throttle, brake, accelerator, or transmission shifter) to direct the operation of the vehicle. Behaviors that characterize the operational mode of the vehicle are associated with the actuators. The behaviors include action sets ranked by priority, and the action sets include alternative actions that the vehicle can take to accomplish its task. The alternative actions are ranked by preference, and an arbiter selects the action to be performed and, optionally, modified.

Abstract: A control system for a mobile robot (10) is provided to effectively cover a given area by operating in a plurality of modes, including an obstacle following mode (51) and a random bounce mode (49). In other embodiments, spot coverage, such as spiraling (45), or other modes are also used to increase effectiveness. In addition, a behavior based architecture is used to implement the control system, and various escape behaviors are used to ensure full coverage.

Abstract: An operator control unit having a user interface that allows a user to control a remote vehicle, the operator control unit comprising: a transmission unit configured to transmit data to the remote vehicle; a receiver unit configured to receive data from the remote vehicle, the data received from the remote vehicle comprising image data captured by the remote vehicle; and a display unit configured to display a user interface comprising the image data received from the remote vehicle and icons representing a plurality of controllable elements of the remote vehicle, and configured to allow the user to input a control command to control at least one of the plurality of controllable elements. Inputting a control command to control the at least one controllable element comprises selecting the icon representing the at least one controllable element, inputting an action for the at least one controllable element, and requesting that the at least one controllable element performs the action.

Abstract: Systems and methods for switching between autonomous and manual operation of a vehicle are described. A mechanical control system can receive manual inputs from a mechanical operation member to operate the vehicle in manual mode. An actuator can receive autonomous control signals generated by a controller. When the actuator is engaged, it operates the vehicle in an autonomous mode, and when disengaged, the vehicle is operated in manual mode. Operating the vehicle in an autonomous mode can include automatically controlling steering, braking, throttle, and transmission. A system may also allow the vehicle to be operated via remote command.

Abstract: A method of localizing a mobile robot includes receiving sensor data of a scene about the robot and executing a particle filter having a set of particles. Each particle has associated maps representing a robot location hypothesis. The method further includes updating the maps associated with each particle based on the received sensor data, assessing a weight for each particle based on the received sensor data, selecting a particle based on its weight, and determining a location of the robot based on the selected particle.

Abstract: A system and method of sorting graphics files with a graphic server and image search engine is disclosed. The method preferably comprises the steps of: receiving a plurality of search results where each of the search results comprising one or more associated graphics; using a general purpose computer to identifying one or more groups of said graphics that depict or otherwise possess similar visual features; and returning the plurality of search results to a user in accordance with said identified groups. The preferred embodiment effectively clusters graphics files, particularly image files, based on upon shared scale-invariant features in order to enable the user to readily identify collections of images relevant to the user while skip past collections of less relevant images.

Abstract: A grasper includes a base, a finger, a tendon cable and a magnetic breakaway mechanism. The finger has a proximal end connected to the base by a proximal joint. The tendon cable is configured to move the finger relative to the base. The magnetic breakaway mechanism releasably couples the finger to the base.

Abstract: A method of simultaneous localization and mapping includes initializing a robot pose and a particle model of a particle filter. The particle model includes particles, each having an associated map, robot pose, and weight. The method includes receiving sparse sensor data from a sensor system of the robot, synchronizing the received sensor data with a change in robot pose, accumulating the synchronized sensor data over time, and determining a robot localization quality. When the accumulated sensor data exceeds a threshold accumulation and the robot localization quality is greater than a threshold localization quality, the method includes updating particles with accumulated synchronized sensor data. The method includes determining a weight for each updated particle of the particle model and setting a robot pose belief to the robot pose of the particle having the highest weight when a mean weight of the particles is greater than a threshold particle weight.

Abstract: An operator control unit includes a user interface that allows a user to control a remote vehicle, a transmission unit configured to transmit data to the remote vehicle, and a receiver unit configured to receive data from the remote vehicle. The data received from the remote vehicle includes image data captured by the remote vehicle. The operator control unit includes a display unit configured to display the user interface including the image data received from the remote vehicle and icons representing a plurality of controllable elements of the remote vehicle, and configured to allow the user to input a control command to control at least one of the plurality of controllable elements.

Abstract: An autonomous mobile robot includes a robot body, a drive system, a sensor system, and a controller. The drive system supports the robot body and maneuvers the robot over a floor surface. The sensor system includes an inertial measurement unit for measuring a pose of the robot and issues a sensor signal including data having information regarding a pose of the robot. The controller communicates with the drive and sensor systems and executes a behavior system. The behavior system receives the sensor signal from the sensor system and executes a behavior. The behavior system executes an anti-stasis behavior in response to sensor signals indicating that the robot is constrained to evaluate a state of constraint. In addition, the behavior system executes an anti-tilt behavior in response to sensor signals indicating that the robot is tilted with respect to a direction of gravity to evaluate a state of tilt.