Learning to Navigate using Visual Sensor Networks

We consider the problem of navigating a mobile robot towards a target in an unknown environment that is endowed with visual sensors, where neither the robot nor the sensors have access to global positioning information and only use first-person-view images. While prior work in sensor network based navigation uses explicit mapping and planning techniques, and are often aided by external positioning systems, we propose a vision-only based learning approach that leverages a Graph Neural Network (GNN) to encode and communicate relevant viewpoint information to the mobile robot. During navigation, the robot is guided by a model that we train through imitation learning to approximate optimal motion primitives, thereby predicting the effective cost-to-go (to the target). In our experiments, we first demonstrate generalizability to previously unseen environments with various sensor layouts. Our results show that by using communication between the sensors and the robot, we achieve up to $2.0\times$ improvement in SPL (Success weighted by Path Length) when compared to the communication-free baseline. This is done without requiring a global map, positioning data, nor pre-calibration of the sensor network. Second, we perform a zero-shot transfer of our model from simulation to the real world. To this end, we train a `translator' model that translates between {latent encodings of} real and simulated images so that the navigation policy (which is trained entirely in simulation) can be used directly on the real robot, without additional fine-tuning. Physical experiments demonstrate the feasibility of our approach in various cluttered environments.