System and method for offloading robotic functions to network edge augmented clouds

{
  "publication_number": "US11249488B2",
  "country": "US",
  "kind": "B2",
  "title": "System and method for offloading robotic functions to network edge augmented clouds",
  "abstract": "A system and method for offloading scalable robotic tasks in a mobile robotics framework. The system comprises a cluster of mobile robots and they are connected with a back-end cluster infrastructure. It receives scalable robotic tasks at a mobile robot of the cluster. The scalable robotics tasks include building a map of an unknown environment by using the mobile robot, navigating the environment using the map and localizing the mobile robot on the map. Therefore, the system estimate the map of an unknown environment and at the same time it localizes the mobile robot on the map. Further, the system analyzes the scalable robotics tasks based on computation, communication load and energy usage of each scalable robotic task. And finally the system priorities the scalable robotic tasks to minimize the execution time of the tasks and partitioning the SLAM with computation offloading in edge network and mobile cloud server setup.",
  "claims": [
    "1. A method for offloading one or more scalable robotic tasks in a mobile robotics framework, wherein the method comprising: receiving the one or more scalable robotic tasks at a mobile robot of a cluster of mobile robots, wherein the one or more scalable robotic tasks include building a map of an unknown environment by using the mobile robot, navigating the environment using the map and localizing the mobile robot on the map; notifying an edge network server about the one or more scalable robotics tasks by the mobile robot for load sharing; estimating the map of an unknown environment by using the mobile robot, wherein at the same time the mobile robot localizes itself on the map; analyzing, by the edge network server, the one or more scalable robotic tasks for offloading to one or more external resources based on computation, communication load and energy usage of each scalable robotic task, wherein the one or more scalable robotic tasks are prioritized to minimize the execution time of the one or more scalable robotic tasks of the mobile robot, wherein the one or more scalable robotic tasks are prioritized based on maximum number of tasks that can be assigned to the mobile robot, energy threshold (E thr) of the mobile robot, energy usage for task processing and data transfer by the mobile robot, and real-time response time required (T res) for the mobile robot to get location update, and wherein the tasks processing time and data transfer time between the one or more external resources and the mobile robot are same for each of the one or more scalable robotics tasks; partitioning, by the edge networks server, simultaneous localization and mapping (SLAM) between the mobile robot and the one or more external resources; offloading, by the edge networks server, the one or more scalable robotic tasks to one or more external resources based on the analysis, wherein the one or more external resources comprising a mobile cloud and an edge of a network; and executing computation of the one or more offloaded scalable robotic tasks at the one or more external resources comprising steps of: sending the one or more offloaded scalable robotic tasks from the mobile robot to the edge and from the edge to a back-end cloud infrastructure; sharing one or more location updates from the back-end cloud infrastructure to the edge and from the edge to the mobile robot; and updating results of the one or more scalable offloaded scalable robotic tasks from each of the one or more external resources and the edge network server to the mobile robot.",
    "2. The method claimed in claim 1, wherein the SLAM partitioning is to meet latency requirements, to achieve accurate mobile robot localization and to build the map of the unknown environment.",
    "3. A system for offloading one or more scalable robotic tasks in a mobile robotics framework, wherein the system comprising: a memory with a set of instructions; a cluster of mobile robots which are configured to connect with a back-end cloud infrastructure, wherein at a mobile robot of the cluster of mobile robots receives one or more scalable robotic tasks, and wherein the mobile robot notifies an edge network server about the one or more scalable robotics tasks for load sharing; and at least a processor, wherein the processor is communicatively coupled to the memory, and wherein the processor is configured to: analyze the one or more scalable robotic tasks for offloading to one or more external resources based on computation, communication load and energy usage of each scalable robotic task, wherein the one or more external resources comprising a mobile cloud and an edge of a network, and wherein the one or more scalable robotic tasks are prioritized to minimize the execution time of the one or more scalable robotic tasks of the mobile robot, wherein the one or more scalable robotic tasks are prioritized based on maximum number of tasks that can be assigned to the mobile robot, energy threshold (E thr) of the mobile robot, energy usage for task processing and data transfer by the mobile robot, and real-time response time required (T res) for the mobile robot to get location update, and wherein the tasks processing time and data transfer time between the one or more external resources and the mobile robot are same for each of the one or more scalable robotics tasks; offload the one or more scalable robotic tasks to one or more external resources based on the analysis, wherein a simultaneous localization and mapping (SLAM) is partitioned to meet latency requirements, to build a map of the unknown environment, to navigate the environment using the map and to localize the mobile robot on the map; and executing computation of the one or more offloaded scalable robotic tasks at the one or more external resources comprising steps of: sending the one or more offloaded scalable robotic tasks from the mobile robot to an edge and from the edge to a back-end cloud infrastructure; sharing one or more location updates from the back-end cloud infrastructure to the edge and from the edge to the mobile robot; and updating results of the one or more scalable offloaded scalable robotic tasks from each of the one or more external resources and the edge network server to the mobile robot.",
    "4. The system claimed in claim 3, wherein the system estimates the map of an unknown environment by using the mobile robot, wherein at the same time the mobile robot localizes itself on the map.",
    "5. A non-transitory computer readable medium storing instructions for offloading one or more scalable robotic tasks in a mobile robotics framework, the instructions comprise: receiving the one or more scalable robotic tasks at a mobile robot of a cluster of mobile robots, wherein the one or more scalable robotic tasks include building a map of an unknown environment by using the mobile robot, navigating the environment using the map and localizing the mobile robot on the map; notifying an edge network server about the one or more scalable robotics tasks by the mobile robot for load sharing; estimating the map of an unknown environment by using the mobile robot, wherein at the same time the mobile robot localizes itself on the map; analyzing, by the edge network server, the one or more scalable robotic tasks for offloading to one or more external resources based on computation, communication load and energy usage of each scalable robotic task, wherein the one or more scalable robotic tasks are prioritized to minimize the execution time of the one or more scalable robotic tasks of the mobile robot, wherein the one or more scalable robotic tasks are prioritized based on maximum number of tasks that can be assigned to the mobile robot, energy threshold (E thr) of the mobile robot, energy usage for task processing and data transfer by the mobile robot, and real-time response time required (T res) for the mobile robot to get location update, and wherein the tasks processing time and data transfer time between the one or more external resources and the mobile robot are same for each of the one or more scalable robotics tasks; partitioning, by the edge networks server, simultaneous localization and mapping (SLAM) between the mobile robot and the one or more external resources; offloading, by the edge networks server, the one or more scalable robotic tasks to one or more external resources based on the analysis, wherein the one or more external resources comprising a mobile cloud and an edge of a network; and executing computation of the one or more offloaded scalable robotic tasks at the one or more external resources comprising steps of: sending the one or more offloaded scalable robotic tasks from the mobile robot to the edge and from the edge to a back-end cloud infrastructure; sharing one or more location updates from the back-end cloud infrastructure to the edge and from the edge to the mobile robot; and updating results of the one or more scalable offloaded scalable robotic tasks from each of the one or more external resources and the edge network server to the mobile robot.",
    "6. The non-transitory computer readable medium claimed in claim 5, wherein the SLAM partitioning is to meet latency requirements, to achieve accurate mobile robot localization and to build the map of the unknown environment."
  ],
  "description_excerpt": "The embodiments herein generally relates to a system and method for offloading one or more scalable robotics tasks of a cluster of mobile robots and, more particularly, recommending a comprehensive framework for offloading computationally expensive simultaneous localization and mapping tasks for a mobile robot in cluster of mobile robots.\n\nMobile robots are generally constrained devices in terms of processing power, storage capacity and energy. Cloud robotics and robotic clusters are two prevalent approaches used to augment mobile robot's processing power performing complex robotic tasks including multi-robot simultaneous localization and mapping (SLAM), robotic vision etc. In cloud robotics, mobile robots use remote cloud server over the internet as resources for offloading intensive computation. Though computation offloading in cloud robotics rendered complex tasks such as map merging, cooperative navigation etc.\n\nCloud robotics in its current form assumes continuous connectivity to the back-end cloud infrastructure. However, in real world situations, especially in disaster scenarios, such assumptions does not hold. To handle the intermittent cloud connectivity and to meet the requirement of latency sensitive applications, there is a need to offload the computationally expensive simultaneous localization and mapping task for mobile robots. Whereas, performing such tasks by sharing computation load among the peer robots, forming a cluster, is not always feasible due to energy and processing power constraints in robots and non-availability of memory for complex tasks such as map merging, map storage etc.",
  "cpc": [
    "G05D 1/0274",
    "B25J 9/161",
    "B25J 9/1697",
    "G05B 19/418",
    "G05B 2219/33333",
    "G05B 2219/34019",
    "G05B 2219/40115",
    "G05D 1/0227",
    "G06Q 10/06311",
    "H04L 1/1854",
    "H04L 67/10",
    "H04L 67/1097",
    "H04L 67/12"
  ],
  "ipc": [
    "B25J 9/16",
    "G05B 19/418",
    "G05D 1/02",
    "G06Q 10/06"
  ],
  "assignees": [
    "Tata Consultancy Services Ltd"
  ],
  "inventors": [
    "Swarnava Dey",
    "Arijit Mukherjee"
  ],
  "filing_date": "2017-11-28",
  "publication_date": "2022-02-15",
  "grant_date": "2022-02-15",
  "priority_date": "2016-11-28",
  "application_number": "US-201715824758-A",
  "family_id": "60654640",
  "cited_by_count": 0,
  "citations": [
    "US9176562B2",
    "US20110288684A1",
    "US9031692B2",
    "US9026248B1",
    "US9427874B1",
    "US20160110625A1",
    "US20160244187A1",
    "US9679490B2"
  ]
}