Abstract: In one embodiment, a cleaning robot stores multiple floorplans. The robot automatically determines which floorplan it is in by localizing and trying to match its detected environment to the stored map. The best fit is the map for the current floor. If there is no match above a confidence threshold, the robot assumes it is a new floor or the floorplan has changed (e.g., furniture has moved), and the robot initiates a discovery mode to map the floorplan and add it to the robot's memory.

Abstract: Embodiments provide a plurality of personalized, user selectable styles. Each style is determined by a combination of dimensions. Each style, except the default balanced style, prioritizes one of the dimensions over the other cleaning dimensions. In one embodiment, the styles are cleaning styles and the cleaning dimensions are cleaning time, coverage and obstacle avoidance. The cleaning styles are gentle, fast, thorough and balanced. The gentle style protects expensive furniture, with obstacle avoidance prioritized over cleaning time and coverage. The fast style cleans quickly, prioritizing cleaning time over coverage and obstacle avoidance. The thorough style prioritizes coverage over cleaning time and obstacle avoidance. The balanced style prioritizes all three cleaning dimensions substantially the same. The prioritization is achieved through adjustments to the autonomous robot navigation. User selection of a style can be achieved directly or automatically based on various mechanisms, such as user history.

Abstract: This disclosure describes various methods and apparatus for detecting and characterizing debris pickup during a cleaning operation. A debris detection sensor is described capable of counting the number of particles retrieved by a robotic vacuum during the cleaning operation and associating particles identified with particular areas. The location information can be obtained using various sensors on-board the robotic vacuum. In some embodiments, a cleaning operation can be rerouted when senor readings from the debris detection sensor deviate from historical sensor readings by a predetermined amount.

Abstract: In one embodiment, a method is disclosed for a robot (e.g., cleaning robot) to produce a bird's eye view (planar) map by transforming from a robot camera view and stitching together images tagged by location. The planar map can then be presented on a user interface as a floorplan, showing the location of objects (such as rugs). A camera is mounted in the cleaning robot sufficiently high in the cleaning robot housing to provide an angled view downward at a floor. The camera's field of view is captured as an image, and a portion or segment of that image is cropped. The cropped segment is transformed from the camera perspective to a planar view (before or after cropping), and is combined with other images to form a map of a floorplan.

Abstract: The present disclosure describes techniques for a robotic cleaning device to determine a plan to clean an environment based on types of surfaces in the environment. The plan can include a route to take in the environment and/or one or more configurations to apply to the robotic cleaning device during the route. Determining the plan can include inserting detected surface types into an environmental map of the environment. The environmental map can then be used on future routes such that the robotic cleaning device can know a surface type of a surface before the robotic cleaning device reaches the surface. In some examples, a type of a surface of the environment can be detected by the robotic cleaning device based on optical polarization of light.

Abstract: Embodiments provide a plurality of personalized, user selectable styles. Each style is determined by a combination of dimensions. Each style, except the default balanced style, prioritizes one of the dimensions over the other cleaning dimensions. In one embodiment, the styles are cleaning styles and the cleaning dimensions are cleaning time, coverage and obstacle avoidance. The cleaning styles are gentle, fast, thorough and balanced. The gentle style protects expensive furniture, with obstacle avoidance prioritized over cleaning time and coverage. The fast style cleans quickly, prioritizing cleaning time over coverage and obstacle avoidance. The thorough style prioritizes coverage over cleaning time and obstacle avoidance. The balanced style prioritizes all three cleaning dimensions substantially the same. The prioritization is achieved through adjustments to the autonomous robot navigation. User selection of a style can be achieved directly or automatically based on various mechanisms, such as user history.

Abstract: A robotic surface treatment apparatus treats corners of rooms more effectively through intricate guidance of the apparatus through inside and outside corners. In one aspect, contact and/or non-contact sensors provide information to one or more on-board processors on the apparatus to enable selective overriding of obstacle avoidance program code and allow the apparatus to get closer to walls to facilitate treatment. In another aspect, the sensors provide information to the on-board processors to control backup motion of the apparatus to cover previously-missed areas when turning corners. In yet another aspect, the apparatus is shaped to have its treatment mechanism positioned more closely to the front of the apparatus to enable treatment more closely to walls near corners. In one embodiment, the robotic surface treatment apparatus is a robotic vacuum. The vacuum may have its cleaning brush positioned near a flat front portion of the apparatus.

Abstract: Techniques that optimize performance of simultaneous localization and mapping (SLAM) processes for mobile devices, typically a mobile robot. In one embodiment, erroneous particles are introduced to the particle filtering process of localization. Monitoring the weights of the erroneous particles relative to the particles maintained for SLAM provides a verification that the robot is localized and detection that it is no longer localized. In another embodiment, cell-based grid mapping of a mobile robot's environment also monitors cells for changes in their probability of occupancy. Cells with a changing occupancy probability are marked as dynamic and updating of such cells to the map is suspended or modified until their individual occupancy probabilities have stabilized.

Abstract: A distance measuring system and method employing a laser distance sensor may have utility in various applications. In accordance with one aspect of the present invention, a laser distance sensor may acquire accurate distance measurements with a short baseline.

Abstract: Techniques that optimize performance of simultaneous localization and mapping (SLAM) processes for mobile devices, typically a mobile robot. In one embodiment, erroneous particles are introduced to the particle filtering process of localization. Monitoring the weights of the erroneous particles relative to the particles maintained for SLAM provides a verification that the robot is localized and detection that it is no longer localized. In another embodiment, cell-based grid mapping of a mobile robot's environment also monitors cells for changes in their probability of occupancy. Cells with a changing occupancy probability are marked as dynamic and updating of such cells to the map is suspended or modified until their individual occupancy probabilities have stabilized.

Abstract: A robotic surface treatment apparatus treats corners of rooms more effectively through intricate guidance of the apparatus through inside and outside corners. In one aspect, contact and/or non-contact sensors provide information to one or more on-board processors on the apparatus to enable selective overriding of obstacle avoidance program code and allow the apparatus to get closer to walls to facilitate treatment. In another aspect, the sensors provide information to the on-board processors to control backup motion of the apparatus to cover previously-missed areas when turning corners. In yet another aspect, the apparatus is shaped to have its treatment mechanism positioned more closely to the front of the apparatus to enable treatment more closely to walls near corners. In one embodiment, the robotic surface treatment apparatus is a robotic vacuum. The vacuum may have its cleaning brush positioned near a flat front portion of the apparatus.

Abstract: A multi-function robotic device may have utility in various applications. In accordance with one aspect, a multi-function robotic device may be selectively configurable to perform a desired function in accordance with the capabilities of a selectively removable functional cartridge operably coupled with a robot body. Localization and mapping techniques may employ partial maps associated with portions of an operating environment, data compression, or both.

Abstract: A multi-function robotic device may have utility in various applications. In accordance with one aspect, a multi-function robotic device may be selectively configurable to perform a desired function in accordance with the capabilities of a selectively removable functional cartridge operably coupled with a robot body. Localization and mapping techniques may employ partial maps associated with portions of an operating environment, data compression, or both.