Abstract: Various aspects related to methods, systems, and computer readable media for scalable software deployment on autonomous mobile robots are described herein. A mobile robotics system can include a storage component configured to store a containerized software package, a server in operative communication with the storage component, and, an autonomous mobile robot (AMR) in operative communication with the server. The containerized software installation package is configured to direct the AMR to maneuver to perform at least one robotic task, monitor computational resource usage of resources of the AMR associated with the at least one robotic task, and, responsive to a determination that computational resource usage at the AMR is or will be above a threshold, sending a request to the server to perform a portion of processing tasks such that resource usage at the AMR is reduced to below the threshold or maintained below the threshold.

Abstract: Various aspects related to methods, systems, and computer readable media for vision-based obstacle detection on autonomous mobile robots are described herein. A computer-implemented method can include receiving, from an imaging device of an autonomous mobile robot (AMR), at least one image of a physical environment that includes a floorspace, compressing, at a processor, the at least one image to a fixed image size to obtain an encoded image, providing the encoded image to a trained machine learning model, the trained machine learning model configured to return a pixel classification for each pixel of the encoded image that indicates whether the pixel corresponds to unobstructed floorspace or obstructed floorspace, determining at least a portion of a navigation route based on the pixel classification, and directing the AMR to traverse the portion of the navigation route.

Abstract: A method, system, and apparatus in the form of a robotic platform. When implemented as described, the method and system provide a highly flexible open platform for efficient and agile code development for robotic platforms through a cloud-based API. The method and system also allow developers to test new robotic platform programming immediately via the Internet and observe the results in real time, even for geographically remote robotic telepresence systems.