A Fog Robotics Approach to Deep Robot Learning: Application to Object Recognition and Grasp Planning in Surface Decluttering
This addresses privacy, security, and latency issues for industrial, automotive, and service robots, but is incremental as it builds on existing cloud and edge computing paradigms.
The paper tackles the challenge of centralized Cloud Robotics by proposing a Fog Robotics approach that distributes resources between Cloud and Edge for deep robot learning, applied to surface decluttering, resulting in a 4× reduction in inference cycle time and successful decluttering of 86% of objects over 213 attempts.
The growing demand of industrial, automotive and service robots presents a challenge to the centralized Cloud Robotics model in terms of privacy, security, latency, bandwidth, and reliability. In this paper, we present a `Fog Robotics' approach to deep robot learning that distributes compute, storage and networking resources between the Cloud and the Edge in a federated manner. Deep models are trained on non-private (public) synthetic images in the Cloud; the models are adapted to the private real images of the environment at the Edge within a trusted network and subsequently, deployed as a service for low-latency and secure inference/prediction for other robots in the network. We apply this approach to surface decluttering, where a mobile robot picks and sorts objects from a cluttered floor by learning a deep object recognition and a grasp planning model. Experiments suggest that Fog Robotics can improve performance by sim-to-real domain adaptation in comparison to exclusively using Cloud or Edge resources, while reducing the inference cycle time by 4\times to successfully declutter 86% of objects over 213 attempts.