International Business Machines Corporation

Saraswathi Sailaja Perumalla

Sarbajit Kumar Rakshit

Venkata Vara Prasad Karri

Shanthan Chamala

Partho Ghosh

Gautam Zalpuri

Venkata Ratnam Alubelli

Rachana Vishwanathula

Akash U Dhoot

Subha Kiran Patnaikuni

Abhijit Deshmukh

Sri Harsha Varada

Krishna Reddy Venkata Batchu

Sirisha Akella

Narendra Reddy Tippala

Sampath Kumar Pulupula Venkata

Pavan Kumar Penugonda

Sowjanya Rao

Divya Mantha

Vamsi Vasireddy

Sweta Agarwal

Neela Vauhini Komaragiri

Ravi Sankar Parvathina

Raghupatruni Nagesh

Omkar Nath Bag

Aditi Chakraborty

Sudheesh S Kairali

Sathya Santhar

Hemant Kumar Sivaswamy

Abhishek Jain

Girish Dhanakshirur

Mahesh Malatesh Chitragar

Nitika Sharma

Sreekanth L Kakaraparthy

Sudhir Alluri

Ramprasad Bhat

Geetha Karna

Vidya Chandrashekar

Amit Kumar Senapaty

Ram Kumar Vadlamani

Sunita Rani Nayak

Khader Saheb Shaik

Sekhar Reddy Dandu Reddy

Archana Ponnada

Pavan K Manda

Dan Craig

Danana Sandhya

Gunendar Kumar Premchand

Deepak Rai

Sreedhar Rao Bachu

Gowri Pruthvi

Ryan Jackson

Lalitha Komarapuri

Praveen Kumar M Kuntumalla

Dilip Kumar Ronanki

Sripathi S Mithra

Venkatrama Siva Kumar Vemuri

Vani Thangaraju

Jyotsna Kasa

Venkataramana Bora

Amit Sharma

Malathy Desikan

Maithree Challapalli

Swetha Sukeerthi Chettupalli

Sheema Farheen

Sairam Telukuntla

Nagesh Raghupatruni

Ashwini Padubidri Chandrase

A method, computer program product, and computer system for network topology optimization. A graph convolutional network (GCN) model is trained using training network topology datasets as input. Each training network topology dataset includes: (i) a specified network topology and an associated optimal network topology and an optimality function value for the optimal network topology, (ii) relative weights of optimality parameters including performance, availability, and scalability, and (iii) an identification of an optimality function of the optimality parameters weighted by the relative weights. The specified network topology includes components, relationships between the components, and metadata pertaining to the components. Each output node in an output layer of the GCN model includes an optimality function value for a different candidate network topology. One of the output nodes identifies an optimum network topology relative to the specified network topology as being the candidate network topology having a highest optimality function value.

Cloud topology optimization using a graph convolutional network model

A convertible robot including a plurality of modules connected one to another by one of a plurality of joints, wherein the plurality of modules has a first end and a second end that is adapted to allow for removable attachment to the first end. The convertible robot also includes a coupling that reversibly converts the plurality of modules between one configuration and at least one other configuration. One configuration is a snake-arm configuration in which the plurality of modules are in an elongated arrangement. Another configuration is a drone configuration in which the first and second ends of the plurality of modules are attached and in a loop-shaped arrangement.

Snake-arm robot capable of converting to a drone

A method, computer system, and a computer program product for generating a communication mode suggestion are provided. A first computer may receive a communication request from a first user to communicate with a second user. The first computer inputs the received communication request to a first machine learning model. The first machine learning model was trained with historical usage of the second user for communication of responses across multiple communication platforms. The trained first machine learning model generates the communication mode suggestion in response to receiving the received communication request as an input. The first computer transmits the communication mode suggestion for presentation to the first user.

Artificial intelligence for communication mode suggestion

The present disclosure includes digitizing user symptoms. A processor may receive user provided data from one or more data collection devices. A processor may access a historical database. The historical database may include historical user provided data. A processor may generate a user data packet based, at least in part on, the user provided data and the historical database. A processor may display the user data packet to one or more authorized user and one or more other correlating information.

Digitizing disease symptoms

One embodiment of the invention provides a method for proactive preparation of an intelligent ecosystem of Internet of Things (IoT) devices based on a virtual reality (VR) interaction. The method comprises identifying a plurality of machine devices in a physical environment, and identifying a plurality of IoT devices within proximity of the machine devices. The method further comprises providing a VR environment for display on a VR headset of a user. The VR environment comprises a VR model of the physical environment. The method further comprises receiving, as input, VR interaction data indicative of one or more VR interactions of the user in the VR environment. The method further comprises determining, based on the VR interaction data, which of the machine devices the one or more VR interactions involve, and proactively awakening at least one of the IoT devices based on the determining.

Proactive preparation of an intelligent ecosystem in a mapped physical surrounding based on a virtual reality (VR) interaction

According to one embodiment, a method, computer system, and computer program product for contextual route guidance is provided. The embodiment may include receiving user information related to a current travel route. The embodiment may further include identifying current status information associated with a transportation hub through IoT-collected data. The embodiment may also include generating a navigation path for a user to reach a destination within the transportation hub based on the received user information and the identified current status information. The embodiment may further include presenting the navigation path to the user.

Creating a time bounded and goal driven network for passenger guidance

A computer-implemented method, according to one approach, includes identifying machines involved in performance of a manufacturing process at a manufacturing location, and identifying a workflow sequence of execution of the machines. Conditions associated with remote operators using virtual reality (VR) devices to remotely control the machines to perform the workflow sequence of execution at the manufacturing location are received. The method further includes determining, for each of the VR devices, an extent of a VR collaborative environment to display. The extents are determined based on the conditions, thereby reducing latency in performance of the workflow sequence of execution at the manufacturing location. The method further includes outputting the extents to the VR devices.

Determination of extents of a virtual reality (VR) environment to display on a VR device

A method, computer system, and a computer program product for automated management of a meeting are provided. A first computer may receive a meeting agenda for a first meeting. The first computer may access live content from the first meeting. The first computer may generate a meeting suggestion based on the meeting agenda and on the accessed live content. The first computer may transmit the meeting suggestion to a second computer.

Artificial intelligence for meeting management

Systems, methods and/or computer program products for improving autonomous vehicle operation by enabling communication between the autonomous vehicles and BCI systems publishing signals from nearby pedestrians. Wearable BCI devices worn by pedestrians analyze brainwave signals and classify the brainwave signals in order to filter out signals that are unrelated to crossing the street or the directionality of travel by the pedestrian. BCI devices publish, or broadcast brain wave signals related to crossing the street or directionality of travel to the surrounding area where autonomous vehicle receive and process the brainwave signals being published. The autonomous vehicles predict movements of nearby pedestrians based on the intended direction of travel signified by the collected brainwave signals, and the autonomous vehicles select driving actions in response to the anticipated movements of nearby pedestrians.

Brain-computer interface enabled communication between autonomous vehicles and pedestrians

A method, computer system, and a computer program product for robot assistance are provided. A computer identifies a position of a first robot in an environment and a range of movement of an arm of the first robot. The computer generates an alignment plan for moving a first conveyor to be aligned with the first robot so that the first conveyor is engageable with the arm of the first robot within the range of movement of the arm. The first conveyor and the first robot include respective supports that are separate from each other. The computer transmits the alignment plan for execution so that the first conveyor is moved according to the alignment plan.

Dynamic changing of conveyor profile based on range of robot

A device's display can be moved based on sensor data to protect the display. The display can be moved via springs and/or electromagnets. The display can be moved into a safe recessed position, allowing a frame to absorb impacts that might otherwise damage the display. The display can also be moved back out of the recessed position.

Retractable displays

An approach for routing one or more packages and delivering the one or more packages to one or more autonomous vehicles is disclosed. The approach receives shipment request from the one or more vendors, receives package status (e.g., status that the one or more packages is ready to be routed, dimension and weight of the one or more packages) of the one or more packages from the one or more vendors, receives vehicle status (e.g., size and available storage space in the vehicles, location and transit time of the vehicles) from the one or more autonomous vehicles. The approach receives the status of the delivery units (e.g., available automated delivery unit, current path and time of completion). The approach determines an optimal routing path for the one or more packages based on the shipment request, package status and vehicle status and outputs the optimal routing path.

Autonomous loading and unloading of packages relating to a vehicle

Computer technology for performing dynamic code branching of self-adapted code upon successful execution of a contextual scenario by artificial intelligence (AI) enabled edge device (for example, an autonomous vehicle or an industrial robotic device). predicting a second contextual scenario where the AI enabled edge device can perform a predetermined activity, and proactively deploying self-adapted code on the AI enabled edge device.

Scenario aware dynamic code branching of self-evolving code

Provided are techniques for performing edge processing by selecting edge devices based on security levels. A security policy is identified for a job to determine a security level for the data. A number of the edge devices that are to be included in a participating group to execute the job is identified. A subset of edge devices that meet the security level are identified by comparing security data of each of the edge devices with the security level. In response to determining that the subset of edge devices includes that number of edge devices, the edge devices from the subset are added to the participating group. The job is executed using the edge devices in the participating group and the one or more cloud nodes, while maintaining the security level in processing the data and in communications across the edge devices and the one or more cloud nodes.

Perform edge processing by selecting edge devices based on security levels

An embodiment for augmented reality (AR)-based visualization of an accidental situation in a multi-machine environment is provided. The embodiment may include receiving real-time and historical data relating to an activity. The embodiment may also include identifying a context of the activity and at least one property of one or more objects associated with the activity. The embodiment may further include identifying one or more items of safety equipment used by a user. The embodiment may also include assigning a compatibility score to the user. The embodiment may further include in response to determining the compatibility score is not adequate, executing a digital twin simulation of an avatar of the user. The embodiment may also include creating a visual animation of a resultant state of the avatar of the user consistent with the executed digital twin simulation. The embodiment may further include displaying the visual animation to the user.

AR-based visualization of accidental situation in multi-machine environment

Growing community of inventors

Visakhapatnam, India

Saraswathi Sailaja Perumalla