Systems and methods for robotic path planning are disclosed. In some implementations of the present disclosure, a robot can generate a cost map associated with an environment of the robot. The cost map can comprise a plurality of pixels each corresponding to a location in the environment, where each pixel can have an associated cost. The robot can further generate a plurality of masks having projected path portions for the travel of the robot within the environment, where each mask comprises a plurality of mask pixels that correspond to locations in the environment. The robot can then determine a mask cost associated with each mask based at least in part on the cost map and select a mask based at least in part on the mask cost. Based on the projected path portions within the selected mask, the robot can navigate a space.

A hybrid modular storage fetching system is described. In an example implementation, an automated guided vehicle of the hybrid modular storage fetching system includes a drive unit that provides motive force to propel the automated guided vehicle within an operating environment. The automated guided vehicle may also include a container handling mechanism including an extender and a carrying surface, the container handling mechanism having three or more degrees of freedom to move the carrying surface along three or more axes. The container handling mechanism may retrieve an item from a first target shelving unit using the carrying surface and the three or more degrees of freedom and place the item on a second target shelving unit. The automated guided vehicle may also include a power source coupled to provide power to the drive unit and the container handling mechanism.

An autonomous driving device includes a map recording a content having different type for each position while one or a plurality of contents and positions are associated with each other, an acquisition unit acquiring the content corresponding to a first position on the map, a specification storage unit storing a plurality of autonomous driving modes of the vehicle and the type of content necessary for the execution of the modes in association with each other, a selection unit selecting an executable autonomous driving mode based on the type of content acquired by the acquisition unit and the type of content stored in the specification storage unit, and a control unit controlling the vehicle at the first position in the selected autonomous driving mode, the selection unit determines one autonomous driving mode based on an order of priority set in advance when there is a plurality of executable autonomous driving modes.

Provided is a process that includes: obtaining a first version of a map of a workspace; selecting a first undiscovered area of the workspace; in response to selecting the first undiscovered area, causing the robot to move to a position and orientation to sense data in at least part of the first undiscovered area; and obtaining an updated version of the map mapping a larger area of the workspace than the first version.

An example method includes gathering, via a first module of a first type, first simultaneous localization and mapping data and gathering, via a second module of a second type, second simultaneous localization and mapping data. The method includes generating, via a simultaneous localization and mapping module, a first map based on the first simultaneous localization and mapping data and the second simultaneous localization and mapping data, the first map being of a first map type and generating, via the simultaneous localization and mapping module, a second map based on the first simultaneous localization and mapping data and the second simultaneous localization and mapping data, the second map being of a second map type. The map of the first type is used by vehicles with module(s) of the first and/or second types and the map of the second type is used by vehicles with a module of the second type exclusively.

An example robot performs a scan to obtain image data of a given region. The robot performs image analysis on the image data to detect a set of undesirable objects, and generates a reference map that excludes the set of undesirable objects, where the reference map is associated with the location of the robot at the time of the scan.

A method of operating an autonomous cleaning robot is described. The method includes initiating a training run of the autonomous cleaning robot and receiving, at a mobile device, location data from the autonomous cleaning robot as the autonomous cleaning robot navigates an area. The method also includes presenting, on a display of the mobile device, a training map depicting portions of the area traversed by the autonomous cleaning robot during the training run and presenting, on the display of the mobile device, an interface configured to allow the training map to be stored or deleted. The method also includes initiating additional training runs to produce additional training maps and presenting a master map generated based on a plurality of stored training maps.

A method of sensing a loaded state of articles in a storage bin and a robot implementing the method are provided. The robot senses a loaded state of articles received in the storage bin in real time or at regular intervals and includes the storage bin and storage bin sensors disposed outside the storage bin. The storage bin sensors are arranged at a non-parallel angle relative to a side surface of the storage bin.

A method for specifying a cleaning area to a cleaning robot without an in-built map provides a hand-held mobile device capturing a two-dimensional code label arranged on a top of a cleaning robot parked on a charging base, and obtaining a positional relationship between the mobile device and the cleaning robot through the captured image. The cleaning robot is controlled to enter a cleaning mode under the guidance of the mobile device. With captured images, a user can specify an area within the environment for cleaning, and through a touch display screen can control the cleaning robot to go to the specified cleaning area for cleaning. The mobile device and the cleaning robot employing the method are also disclosed.

Various technologies described herein pertain to generating an occupancy grid movie for utilization in motion planning for the autonomous vehicle. The occupancy grid movie can be generated for a given time and can include time-stepped occupancy grids for future times that are at predefined time intervals from the given time. The time-stepped occupancy grids include cells corresponding to regions in an environment surrounding the autonomous vehicle. Probabilities can be assigned to the cells specifying likelihoods that the regions corresponding to the cells are occupied at the future times. Moreover, cached query objects that respectively specify indices of cells of a grid occupied by a representation of an autonomous vehicle at corresponding orientations are described herein. An occupancy grid for the environment surrounding the autonomous vehicle can be queried to determine whether cells of the occupancy grid are occupied utilizing a cached query object from the cache query objects.