Abstract: Techniques described in this application are directed to facilitating delivery of an item through improved notifications. One or more geographical boundaries may assist with detection of status identifiers corresponding with delivery of the item at various points of time.

Abstract: Techniques described in this application are directed to facilitating delivery of an item by analyzing continuous data streams. These data streams may identify potential delivery issues with and respect to user device location information and geographical boundaries. The delivery issues may be resolved proactively.

Abstract: Techniques described in this application are directed to facilitating delivery of an item through detection of locations of various user devices and geographical boundaries. Location detection may be compared with one or more threshold values at various points of time. Potential delivery issues may be identified and resolved proactively through the comparison of locations with these thresholds.

Abstract: Provided is a light projection system that can be used to indicate a robot's path of travel, a robot including the light projection system, and methods for projecting light to indicate a robot's path of travel. The light projection system can by mounted to the body of the robot, and can be configured to project light onto the ground in front of the robot. The light projection system can be configured to project different illumination patterns that can indicate whether the robot is moving forward, turning, accelerating, and/or slowing down, among other examples.

Abstract: Provided are systems, methods, and computer-program products for generating a personalized item list. In various examples, a server computer on a network can receive a request that includes a user identifier. The computer can use the user identifier to look up a data model associated with the user identifier. The computer can further determine a geolocation, and use the geolocation to determine a list of items associated with an eatery at or near the geolocation. The computer can input the item list into the data model, for the data model to output a probability for each item, the probability indicating a likelihood that the user will select the item. The probabilities can be used to generate a personalized item list, which can be output onto the network for receipt by a computing device.