Relative POSe Estimation for Intelligent Drones and rObots in GPS-deNied Environments (POSEIDON)
This project combines onboard odometry with inter-robot distance measurements to help robots and drones determine their relative positions and collaborate without external positioning infrastructure.
The adoption of autonomous mobile robots is rapidly advancing in sectors like logistics, manufacturing, warehousing, agriculture, and industrial inspection. Effective localization systems are essential for their safe operation. Outdoor localization uses GPS (RTK), while indoor localization relies on infrastructure like UWB anchors, QR codes, or cameras. These systems are costly but justified in environments with many robots.
Decreasing robot costs and rising labor expenses are driving their use in smaller-scale applications, such as logistics or crop manipulation in GPS-denied environments like warehouses and greenhouses. In these cases, the cost of installing localization systems is disproportionately high.
Approaches without installation of infrastructure (anchorless) have been promoted for these environments to enable collaboration using only onboard sensors. The Poseidon project aims to evaluate performance using field data, considering factors like metal structures and crops, to assess technological and economic feasibility. This innovation enables the deployment of robotic platforms in both smaller-scale and larger environments with fewer robots.
Downloads
GitHub - y2d2/POSEIDON_FAIR_enrichment
Contacts
Bram Vanderborght - bram.vanderborght@vub.be
Researcher
Yuri Durodie - yuri.durodie@vub.be
Research group
VUB-Brubotics