Collaborative inference helps robots to complete large tasks with mutual collaboration in edge-assisted multi-robot systems. It is challenging to provide trusted edge collaborative inference in the presence of malicious nodes. In this article, we propose a blockchain-based collaborative edge knowledge inference (BCEI) framework for edge-assisted multi-robot systems. First, we formulate the inference process at the edge as the collaborative knowledge graph construction and sharing model. Second, to guarantee the trust of knowledge sharing, an efficient knowledge-based blockchain consensus method is presented. Finally, we conduct a case study on the emergency rescue application to evaluate the proposed framework. The experiment results demonstrate the efficiency of the proposed framework in terms of latency and accuracy.
ASJC Scopus subject areas
- Computer Science Applications
- Computer Networks and Communications
- Electrical and Electronic Engineering