Data-Efficient Collaborative Decentralized Thermal-Inertial Odometry
This work addresses data-efficient collaborative navigation for teams of flying robots, representing an incremental advance with specific gains in performance and communication efficiency.
The paper tackles the problem of decentralized state estimation for flying robots using thermal images and inertial measurements, achieving up to 46% improvement in trajectory estimation and up to 89% reduction in communication exchange compared to individual-agent approaches.
We propose a system solution to achieve data-efficient, decentralized state estimation for a team of flying robots using thermal images and inertial measurements. Each robot can fly independently, and exchange data when possible to refine its state estimate. Our system front-end applies an online photometric calibration to refine the thermal images so as to enhance feature tracking and place recognition. Our system back-end uses a covariance-intersection fusion strategy to neglect the cross-correlation between agents so as to lower memory usage and computational cost. The communication pipeline uses Vector of Locally Aggregated Descriptors (VLAD) to construct a request-response policy that requires low bandwidth usage. We test our collaborative method on both synthetic and real-world data. Our results show that the proposed method improves by up to 46 % trajectory estimation with respect to an individual-agent approach, while reducing up to 89 % the communication exchange. Datasets and code are released to the public, extending the already-public JPL xVIO library.