Vision-based collaborative simultaneous localization and mapping system and method

Multi-Platform Collaborative SLAM System Using Non-Static Feature-Based Rendezvous Detection

This technology is a vision-based collaborative simultaneous localization and mapping (SLAM) system. To identify rendezvous situations between multiple platforms and fuse individual SLAM maps, it uses an optimization algorithm at a ground station to compare and calculate the movement of non-static features extracted from each platform, along with the similarity of pose and map information between platforms, to perform inter-platform matching.

Existing collaborative SLAM systems have faced significant limitations in sensor configuration and operation, as they often require visual markers for platform identification or demand precise distance information.

This technology proposes a method that tracks and manages non-static features—which are typically discarded in images collected by monocular cameras—without the need for separate markers. By formulating the detection of inter-platform rendezvous as an optimization problem, it enables the fusion of individual maps and pose data at a ground station, allowing for collaborative mapping among multiple robots with a simple sensor setup. It can be applied to multi-drone exploration, collaborative mapping in disaster zones, and indoor autonomous navigation. Since it is implemented using only a monocular camera without markers or expensive sensors, it significantly reduces system construction costs.

‍

‍

Key Features:

• A step where each of the multiple platforms estimates camera pose and creates an individual map based on camera input images using a single SLAM method.
• A step of extracting and managing non-static features from camera input images to be used for rendezvous determination.
• A step of transmitting camera pose, individual maps, and non-static features as platform data to a ground station.
• A step where the ground station determines whether a rendezvous situation has occurred based on the platform data and fuses individual maps into an integrated map.

‍

This invention was developed with support from the multi-ministry project for the development of autonomous driving assistance robots for foldable wheelchairs.