Edge Cloud SLAM Offloading for Intermittent Robot Connectivity
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Mobile robots face challenges in offloading computationally expensive simultaneous localization and mapping tasks due to processing power, energy, and memory constraints, especially in scenarios with intermittent cloud connectivity and latency-sensitive applications, where current cloud robotics and robotic clusters are inadequate.
Innovation Solution
A dynamic offloading system and method that analyzes scalable robotic tasks based on computation, communication load, and energy usage to prioritize and offload tasks to external resources like a mobile cloud and edge network, partitioning SLAM execution to meet latency requirements and achieve accurate robot localization and map building.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If computationally expensive SLAM tasks are performed on mobile robots using cloud robotics, then complex tasks such as map merging and cooperative navigation can be executed, but continuous connectivity to back-end cloud infrastructure is assumed which does not hold in real world situations especially in disaster scenarios
Solution Approach 1:
The patent segments the SLAM computation into two parts: local processing on the mobile robot for basic localization and mapping, and cloud processing for computationally expensive tasks like map merging. This segmentation allows the system to operate independently when cloud connectivity is unavailable while still benefiting from cloud resources when available.
Solution Approach 2:
The patent implements dynamic task offloading that adapts to changing connectivity conditions. The system dynamically decides which tasks to execute locally and which to offload to the cloud based on real-time assessment of connectivity status, computational requirements, and energy constraints, making the system flexible and adaptive to intermittent connectivity.
2Productivity
If computationally expensive SLAM tasks are performed by sharing computation load among peer robots forming a cluster, then complex tasks can be distributed, but energy and processing power constraints in robots and non-availability of memory for complex tasks such as map merging and map storage are not addressed
Solution Approach 1:
The patent extracts the most computationally expensive tasks (map merging, cooperative navigation) from the mobile robot and offloads them to the cloud. This extraction allows the robot to maintain cluster productivity while avoiding the energy and memory constraints that would otherwise prevent execution of these complex tasks.
Solution Approach 2:
The cloud infrastructure acts as an intermediary that provides additional computational resources for the robotic cluster. Instead of requiring each robot to have sufficient local resources to handle all tasks, the cloud mediates by providing supplementary processing power and storage capacity for complex operations.
3Ease of operation
If static offloading strategies are used, then implementation is simpler, but the results demonstrate the efficacy of the proposed dynamic offloading framework over static offloading strategies
Solution Approach 1:
The patent implements a feedback mechanism where the system continuously monitors task execution time, energy consumption, and connectivity status. Based on this feedback, the offloading decisions are dynamically adjusted to optimize performance. The system learns from past execution patterns and adapts its offloading strategy accordingly.
Solution Approach 2:
The patent transitions from static to dynamic offloading where the offloading decisions are made in real-time based on current system state. This dynamic approach considers varying computational loads, changing connectivity conditions, and energy availability, resulting in optimized execution time and resource utilization compared to fixed static strategies.
Data Source
AI summary
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.