Amazon Technologies, Inc.

Armada Systems Inc.

Microsoft Technology Licensing, LLC

Pragyana K Mishra

Dushyant Goyal

Gur Kimchi

Darren Ernest Canavor

Hilliard Bruce Siegel

Tye Michael Brady

Anish Swaminathan

Janardhan Prabhakara

Ethan Zane Evans

Pradeep Nair

James Christopher Curlander

Naveen Sudhakaran Nair

Eyal Ofek

Javier Alonso Lopez

Prakash Bulusu

Debanjan Mukherjee

Jon Stuart Battles

Jules Cook Graybill

Danny Guan

David L Alspaugh

Jonathan Blair Norwood

Nagareddy S Reddy

Roopesh Ranjan

Nikolaos Chatzipanagiotis

Larry Felser

Dipan M Shah

Wesley Scott Lauka

Ryan Scott Russell

Thomas Matthew Ryle

Udit Madan

Allan Scott Bathurst

Alan Kipust

Chinmay Hemant Bhagwat

Ivan Barrientos

Sina Ehsani

Venkata Bhanu Teja Pallakonda

Raghuram Satyanarayana Rao

Brian C Beckman

Nishant Dani

Rajeev Prasad

Cole Brooking

Kancheng Cao

Jonathan Robert Dughi

Avneesh Sud

Mikhail Parakhin

Mohammed Khalilia

Jason Michael Long

Ayman Malek Abdel Hamid Kaheel

Pengpeng Wang

Kun Li

David Joseph Rendleman

Chris Vasquez

Dan Wright

Grant Gordon

Arash Motamedi

Kenny Xie

Graton Marshal Randal Gathright

Sumit Amar

Manjula Ananthnarayanan Iyer

Billy P Chen

Marshall Friend Tappen

Yonatan Wexler

Sanjeev Kumar

Erik Resch Parker

Gregory Johnson

Nagendra V Kolluru

Ayman Mahfouz

Amitava Das

Wenbin Ouyang

Daniel Hafner Cavalcanti

Rohan Gurappagouda Patil

Han Wu

Rohit K Gupta

Neeharika Adabala

Nathalie Majcherczyk

Shantanu Thakar

Ben Lloyd Shapiro

Kevin Tseng

Chirag Natvarlal Mandaviya

Alexiy Buynitsky

Mohit Chandak

John Weresh

Kevin Kuang-Hui Tseng

Chittaranjan Tripathy

Venketaram Ramachandran

Aniruddha Loya

Douglas Wong

Ayman Omar Farahat

Yanatan Wexler

Jai Chakrapani

Nikhil Raina

Anil Padia

Shivani Matta

Shikha Aggarwal

Chitti Babu Namballa

Techniques and apparatus for adaptively controlling an end-effector of a robotic arm are provided. The end-effector includes at least one articulated finger having multiple facets arranged on a surface of the at least one articulated finger. The robotic arm is moved to engage an item using the at least one articulated finger. At least one of an amount of force or an amount of torque applied to the multiple facets on the surface of the at least one articulated finger is determined while the item is engaged using the at least one articulated finger. At least one of a position and orientation of the at least one articulated finger is adaptively controlled, based on at least one of the determined amount of force or the amount of torque.

Faceted finger for guided haptic feedback

Artificial intelligence agents generate media content for broadcasting to devices of listeners over one or more networks. An agent is trained based on episodes of previously aired media programs to identify topics of the episodes and media entities played during such episodes. Words or phrases spoken by human creators during such episodes are identified and modeled. The agent selects a topic of an episode of a media program and selects media entities that are consistent with those typically played during the media programs. The agent also identifies sets of words that are consistent with the topic, and transmits audio data including the selected media entities and sets of words spoken in voices having linguistic styles, a prosody or acoustic characteristics of the human creators to devices of listeners of the media program.

Using artificial creators to generate media content

A method can include receiving monitoring information associated with a machine learning (ML) or artificial intelligence (AI) workload implemented by an edge compute unit of a plurality of edge compute units. Status information corresponding to a plurality of connected edge assets can be received, the plurality of edge compute units and connected edge assets included in a fleet of edge devices. A remote fleet management graphical user interface (GUI) can display a portion of the monitoring or status information for a subset of the fleet of edge devices, based on a user selection input, and can receive a user configuration input indicative of an updated configuration associated with at least one edge compute unit of the fleet. A cloud computing environment can transmit control information corresponding to the updated configuration to the at least one edge compute unit.

Cloud-based fleet and asset management for edge computing of machine learning and artificial intelligence workloads

Disclosed are systems and methods to control a robotic device using natural language commands. A natural language command may be received by a system. The system may convert the command into low-level machine controls and logic for implementation by a robotic device to achieve a desired action. In some instances, an API module may include mapping data to associate high-level commands with low-level machine controls. A language model may process the natural language command (input), high-level commands, and/or other information, such as system state, sensor observation data, parameters, etc., to determine one or more commands to execute by a robotic device and possibly logic for execution by the robotic device. The robotic device may receive the low-level machine controls and logic to cause the robotic device to perform the requested actions.

Robotic control using natural language commands

Disclosed are systems and methods to track an object in a scene even when the object is partially or wholly obscured by an artifact, such as another object. As the tracked object moves through the scene, frames of video are processed and used to refine and tune a diffusion model that predicts an appearance of the tracked object in future frames of the video as well as the appearance of artifacts in the frames of the video. Frames of the video may then be enhanced to illustrate the tracked object as if the tracked object were visible through the artifact.

Object tracking through artifacts

A process can include obtaining a plurality of data points each associated with a respective edge device of a fleet of edge devices, each respective edge device associated with an edge site location or edge device asset group. The plurality of data points are stored to a fleet map data catalog and a filtering selection for viewing a filtered subset of the fleet map data catalog is received, indicating a selected geographic view area and selected edge device types from a plurality of edge device types. Data points corresponding to the filtered subset are obtained from the fleet map data catalog using the filtering selection. A fleet map GUI view is generated using the data points corresponding to the filtered subset, the fleet map GUI view comprising a converged geographic map of the selected geographic view area, with data points are rendered at corresponding locations within the converged geographic map.

Fleet and asset management and interfaces thereof associated with edge computing deployments

Systems and techniques are provided for processing streaming data. For example, a process can include obtaining, by an edge device, a plurality of data streams corresponding to objects, activities, or events registered in an edge environment associated with the edge device. One or more machine learning networks implemented on the edge device can generate a plurality of features and/or embeddings corresponding to each respective data stream of the plurality of data streams. The edge device can determine a subset of salient content from the plurality of data streams, based on analyzing the plurality of features and/or embeddings generated for each respective data stream. The edge device can generate index information corresponding to the determined subset of salient content. The subset of salient content and the generated index information can be stored locally at the edge device for search and retrieval based on local queries received at the edge device.

Real-time search and retrieval of streaming sensor data

Disclosed are systems and methods that convert digital video data, such as two-dimensional digital video data, into a natural language text description describing the subject matter represented in the video. For example, the disclosed implementations may process video data in real-time, near real-time, or after the video data is created and generate a text-based video narrative describing the subject matter of the video. In addition, the disclosed implementations may also support a question and answer session in which a user may submit queries about the subject matter of one or more videos and the disclosed implementations will present natural language responses based on the subject matter of the video and any corresponding context.

Video to narration

A process can include transmitting a pre-trained machine learning model to an edge compute unit associated with a request. The edge compute unit can perform inference using the pre-trained machine learning model and one or more sensor data streams obtained at an edge location. One or more batch uploads of information can be received, associated with inference performed by the edge compute unit and using the pre-trained machine learning model. One or more updated machine learning models can be generated, based on using the batch uploads of information from the edge compute unit to retrain or finetune the pre-trained machine learning model. The one or more updated machine learning models can be transmitted to the edge compute unit, wherein transmission of the updated machine learning model is responsive to receiving the one or more batch uploads of information.

Fleet and asset management for edge computing of machine learning and artificial intelligence workloads deployed from cloud to edge

An apparatus can be configured to receive monitoring information associated with a machine learning (ML) or artificial intelligence (AI) workload implemented by an edge compute unit of a plurality of edge compute units. Status information corresponding to a plurality of connected edge assets can be received, the plurality of edge compute units and connected edge assets included in a fleet of edge devices. A remote fleet management graphical user interface (GUI) can display a portion of the monitoring or status information for a subset of the fleet of edge devices, based on a user selection input, and can receive a user configuration input indicative of an updated configuration for at least one workload corresponding to a pre-trained ML or AI model deployed on the at least one edge compute unit. A cloud computing environment can transmit control information corresponding to the updated configuration to the at least one edge compute unit.

Computing units provided at local sites or edge locations are programmed to execute conversational tools that generate pertinent, domain-specific responses to queries received from workers at such sites or locations. The conversational tools are large language models that are trained with domain-specific knowledge documents. Data representing queries are received from workers at such sites or locations and provided as inputs to the conversational tools along with text representing nearest knowledge documents from a knowledge base associated with the domain, as well as contextual data. Responses identified based on outputs received from the conversational tools in response to the inputs are provided to the workers that generated the queries. Where subsequent queries are received from the workers, responses to the subsequent queries are identified based on the subsequent queries, nearest knowledge documents, contextual data, and conversational histories including previously received queries and responses to such queries.

Edge computing units for operating conversational tools at local sites

Disclosed implementations include systems, methods, and apparatus that process multiple, disparate streams of data, determine correlations and relationships between the data and provide natural language responses that provide insights for events or activities that have occurred and foresights for events or activities that are forecasted to occur. The disclosed implementations include a model that understands data statistics and provides both insights and foresights that are backed with statistical support that can be presented to and understood by operators. Still further, the disclosed implementations are capable of operating at edge locations that may be frequently or permanently disconnected from conventional or cloud based systems.

Natural language statistical model with alerts

Time series data to statistical natural language interaction

A physical space may contain sliding doors in various places such as between rooms, as closet doors, on furniture, and so forth. An autonomous mobile device (AMD) capable of non-holonomic motion may selectively contact a portion of the sliding door and apply a force to open or close the door. The AMD moves to an initial pose relative to the door, with a portion of the AMD coming into contact with the door. The AMD then rotates and translates, relative to the door, applying a force to the door. Sensor data, such as linear acceleration, rotation, drive wheel torque, and so forth is used as input to determine the next movement in a series of motions, resulting in continued contact and force application. As the end of travel for this motion is reached, the AMD may separate from the door, reposition, and continue to apply a force to the door.

System to manipulate sliding obstacles with non-holonomic autonomous mobile device

A process can include receiving monitoring information associated with a machine learning (ML) or artificial intelligence (AI) workload implemented by an edge compute unit of a plurality of edge compute units. Status information corresponding to a plurality of connected edge assets can be received, the plurality of edge compute units and connected edge assets included in a fleet of edge devices. A remote fleet management graphical user interface (GUI) can display a portion of the monitoring or status information for a subset of the fleet of edge devices, based on a user selection input, and can receive a user configuration input indicative of an updated configuration for at least one workload corresponding to a pre-trained ML or AI model deployed on the at least one edge compute unit. A cloud computing environment can transmit control information corresponding to the updated configuration to the at least one edge compute unit.

Growing community of inventors

Seattle, WA, United States of America

Pragyana K Mishra