Amazon Technologies, Inc.

X Development LLC

Munaf Assaf

Gabriel Aaron Cohen

Benjamin Holson

Nicholas Chuanji Liao

Jessica Kitchens

Peter McGowin Kelly

Jonathan Ota

May Wing-Sze Cheng

Simon Lucien Fillat

Dhanik Shah

A user interacts with an autonomous mobile device (AMD) using a voice user interface. The voice user interface allows a user to instruct the AMD to move, stop, go to a specified location, and so forth. The commands may include, but are not limited to: stop, stop moving, move, turn, go to, stay here, go away, and so forth. In one implementation, if the AMD is instructed by the user to go away, the AMD may move out of sight of the user from a first region to another region, such as another room. The AMD will avoid traversing the first region until a timer expires or a command to enter the first region is given.

System for user interactions with an autonomous mobile device

A robot operating in an environment provides cues to users. These cues provide information to the user as to operation of the robot. Some cues may involve physical movement of at least a portion of the robot. For example, as the robot passes a user, the robot may tilt a display head up and down to simulate a nodding motion. The cues may comprise one or more motions of one or more parts of the robot. The cues may also comprise visual output, such as graphics, pictures, text, and so forth, being presented on a display device of the robot, or changing the color or brightness of a light. In some implementations, the cues may include audio output, such as sounds.

Non-verbal cuing by autonomous mobile device

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selective human-robot interaction. In some implementations, sensor data describing an environment of a robot is received, and a person in the environment of the robot is detected based on the sensor data. Scores indicative of properties of the detected person are generated based on the sensor data and processed using a machine learning model. Processing the scores can produce one or more outputs indicative of a likelihood that the detected person will perform a predetermined action in response to communication from the robot. Based on the one or more outputs of the machine learning model, the robot initiates communication with the detected person.

Selective human-robot interaction

The subject matter of this specification generally relates to object recognition for robots. In some implementations, a method includes navigating a robot through an area to identify objects located in the area. The robot detects the presence of the objects in the area using one or more sensors. A determination is made that an object detected by the robot is not recognized by the robot. In response to determining that the object is not recognized by the robot, a user interface that includes data describing the object that is not recognized is provided. The user interface can be configured to receive user input that identifies the object. In response to interaction with the user interface, data identifying the object is received. A database for the robot is updated with the data identifying the object.

Object recognition tool

Growing community of inventors

San Francisco, CA, United States of America

Munaf Assaf