Abstract
With wide penetration of smart robots in many application fields, Simultaneous Localization And Mapping (SLAM) has attracted great attention in the community. Yet the performance issue on multi-robot SLAM still remains challenging due to the contradiction of constrained on-device resources and intensive graphics computation. While traditional approaches resort to the powerful cloud servers to accelerate SLAM computing, we show by real-world measurements that the significant communication overhead prevents its practicability to real deployment. To tackle this challenge, in this paper, we promote the emerging edge computing paradigm into the SLAM execution optimization and propose ColaSLAM, a multi-robot collaborative laser SLAM system with robot-edge synergy. ColaSLAM manages a cluster of edge nodes to serve multiple robots and perform collaborative SLAM to generate a global geometric map in real-time. To orchestrate the map merging process from multi-robot sources, we further design an adaptive map fusion coordinator using the Tabu search heuristic. Extensive evaluation based on both simulation and prototype show ColaSLAM can achieve up to 40% processing latency reduction over the cloud approach.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
