An intelligent light bulb is provided as well as a method, devices and computer program product of configuring such an intelligent light bulb. The intelligent light bulb comprises an LED lighting element and a programmable controller. The programmable controller comprises a memory module having stored therein firmware including instructions for controlling operations of the LED lighting element, where the memory module including a passive memory on which at least a portion of the firmware is stored. The passive memory component of the memory module is responsive to a signal carrying firmware update information received over a wireless communication link from a device external to the intelligent light bulb for causing a firmware update process to be performed to modify the instructions of the firmware based on the update information carried by the signal. The programmable controller also includes a processing unit in communication with the memory module for operating the LED lighting element at least in part in accordance with the instructions of the firmware. Advantageously, the proposed intelligent light bulb can be configured using the signal carrying the firmware update information. In some embodiments, this may allow modifications of certain operating characteristic of the intelligent light bulb to be performed after manufacturing, including modifications pertaining to light color emitted and/or manner of operating the light bulb.

Some embodiments provide a system comprising: multiple self-propelled motorized transport units; a wireless communication network; and a central computer comprising: a transceiver, a control circuit and a memory storing computer instructions that when executed by the control circuit cause the control circuit to: receive a request from a customer requesting location information for a requested item; identify the requested item is a category of items, and identify category location information; communicate routing instructions to the motorized transport unit based on the category location information causing the motorized transport unit to initiate physical movement; and communicate to the motorized transport unit a species clarification inquiry instruction configured to cause the motorized transport unit, while implementing routing instructions to move toward the category location, to present a clarification inquiry to the customer seeking clarification in narrowing the identified category to one or more products categorized within the identified category.

An encoder includes a base portion, a rotation portion that is provided to be rotatable about a rotation axis with respect to the base portion, a mark that is disposed around the rotation axis on the rotation portion, an imaging element that is disposed in the base portion and images the marks, a storage portion that stores a reference image, and a determination portion that performs template matching on the mark imaged by the imaging element by using the reference image, so as to determine a rotation state of the rotation portion with respect to the base portion.

Techniques described herein relate to using reduced-dimensionality embeddings generated from robot sensor data to identify predetermined semantic labels that guide robot interaction with objects. In various implementations, obtaining, from one or more sensors of a robot, sensor data that includes data indicative of an object observed in an environment in which the robot operates. The sensor data may be processed utilizing a first trained machine learning model to generate a first embedded feature vector that maps the data indicative of the object to an embedding space. Nearest neighbor(s) of the first embedded feature vector may be identified in the embedding space. Semantic label(s) may be identified based on the nearest neighbor(s). A given grasp option may be selected from enumerated grasp options previously associated with the semantic label(s). The robot may be operated to interact with the object based on the pose and using the given grasp option.

Methods and apparatuses are provided for use in monitor power levels at a shopping facility, comprising: central control system separate and distinct from a plurality of self-propelled motorized transport units, wherein the central control system comprises: a transceiver configured to wirelessly receive communications from the plurality of motorized transport units; a control circuit coupled with the transceiver; and a memory coupled to the control circuit and storing computer instructions that cause the control circuit to: identify available stored power levels at each of the plurality of motorized transport units; identify an available recharge station, of a plurality of recharge stations distributed throughout the shopping facility, at least relative to a location of the first motorized transport unit intended to be subjected to recharging; and wirelessly communicate one or more instructions to cause the first motorized transport unit to cooperate with an available recharge station.

The present application relates to a method of determining an action associated with an apparatus. The method comprises obtaining (100) data representing a visual code and a visual symbol; comparing (120) the visual code with a reference code, and comparing (130) the visual symbol with a reference symbol, to obtain comparison results; and determining (140) the action in response to the comparison results.

Systems and methods are provided to address incorrectly placed items. Some systems comprise: a plurality of motorized transport units that are each configured to perform multiple different tasks at a retail shopping facility; and a central computer system configured to instruct various ones of the plurality of motorized transport units to implement at least one of the multiple different tasks relative to the retail shopping facility, receive and analyze input data detected and provided by the motorized transport units while the motorized transport units perform the at least one of the tasks, and detect and categorize each item of multiple items that are incorrectly placed within the retail shopping facility according to one of multiple different predefined categories.

Techniques described herein relate to using reduced-dimensionality embeddings generated from robot sensor data to identify predetermined semantic labels that guide robot interaction with objects. In various implementations, sensor data obtained from one or more sensors of a robot includes data indicative of an object observed in an environment in which the robot operates. The sensor data is processed utilizing a first trained machine learning model to generate a first embedded feature vector that maps the data indicative of the object to an embedding space. Nearest neighbor(s) of the first embedded feature vector is identified in the embedding space. Semantic label(s) are identified based on the nearest neighbor(s). A given grasp option is selected from enumerated grasp options previously associated with the semantic label(s). The robot is operated to interact with the object based on the pose and using the given grasp option.

Systems and methods of associating data to an item being transported by a conveying system are disclosed. The item and data associated with the item are received at a first zone of the conveying system. The data is stored in a first computer-readable storage medium associated with the first zone. The item is transported to a second zone of the conveying system, and the data stored in the first computer-readable storage medium is transferred to a second computer-readable storage medium associated with the second zone.

Methods and apparatuses are provided for use in monitoring product placement within a shopping facility. Some embodiments provide an apparatus configured to determine product placement conditions within a shopping facility, comprising: a transceiver configured to wirelessly receive communications; a product monitoring control circuit coupled with the transceiver; a memory coupled with the control circuit and storing computer instructions that when executed by the control circuit cause the control circuit to: obtain a composite three-dimensional (3D) scan mapping corresponding to at least a select area of the shopping facility and based on a series of 3D scan data; evaluate the 3D scan mapping to identify multiple product depth distances; and identify, from the evaluation of the 3D scan mapping, when one or more of the multiple product depth distances is greater than a predefined depth distance threshold from the reference offset distance of the product support structure.