Akshay Shetty

Akshay Shetty, Derek Knowles, Grace Xingxin Gao

Inter-robot communication enables multi-robot systems to coordinate and execute complex missions efficiently. Thus, maintaining connectivity of the communication network between robots is essential for many multi-robot systems. In this paper, we present a trajectory planner for connectivity maintenance of a multi-robot system. We first define a weighted undirected graph to represent the connectivity of the system. Unlike previous connectivity maintenance works, we explicitly account for robot motion and sensing uncertainties while formulating the graph edge weights. These uncertainties result in uncertain robot positions which directly affect the connectivity of the system. Next, the algebraic connectivity of the weighted undirected graph is maintained above a specified lower limit using a trajectory planner based on a distributed alternating direction method of multipliers (ADMM) framework. Here we derive an approximation for the Hessian matrices required within the ADMM optimization step to reduce the computational load. Finally, simulation results are presented to statistically validate the connectivity maintenance of our trajectory planner.

Akshay Shetty, Grace Xingxin Gao

We propose an image-based cross-view geolocalization method that estimates the global pose of a UAV with the aid of georeferenced satellite imagery. Our method consists of two Siamese neural networks that extract relevant features despite large differences in viewpoints. The input to our method is an aerial UAV image and nearby satellite images, and the output is the weighted global pose estimate of the UAV camera. We also present a framework to integrate our cross-view geolocalization output with visual odometry through a Kalman filter. We build a dataset of simulated UAV images and satellite imagery to train and test our networks. We show that our method performs better than previous camera pose estimation methods, and we demonstrate our networks ability to generalize well to test datasets with unseen images. Finally, we show that integrating our method with visual odometry significantly reduces trajectory estimation errors.