A Distributed and Fault Tolerant Robotic Localisation and Mapping in Network Edge

Of late, Cloud Robotics paradigm is being used to augment low-end robots with enhanced sensor data processing, storage and communication capabilities. In an era, where costly specialized hardware are being replaced by commodity hardware, software reliability within Cloud Robotic middleware will allow distributed execution on lightweight, low-cost robots and network edge devices. However, successful functioning of multi-robot systems in critical missions requires resilience in the middleware such that the overall functionity degrades gracefully during hardware or network failures. In the current work, reliable distributed execution capability is added to a well known robotic localization and mapping task such that data transfer between participating nodes is minimized and the application degrades gracefully in case of failure of participating robots. To ensure fault tolerance, an execution model based on the failure probabilities of individual robots and their components is proposed. A lightweight timeseries analysis scheme is presented enabling the robots to find their individual failure probabilities and use that to enhance system reliability in a distributed manner. Both the distribution and predictive recovery schemes are evaluated using standard datasets on virtual machines running robotic middleware.