Bridging Cooperative Sensing and Route Planning of Autonomous Vehicles

Autonomous Vehicles (AV) are used to solve the problem of data gathering in large scale sensor deployments with disconnected clusters of sensors networks. Our take is that an efficient strategy for data collection with AVs should leverage i) cooperation amongst sensors in communication range of each other forming a sensor cluster, ii) advanced coding and data storage techniques for easing the cooperation process, and iii) AV route-planning that is both content-and cooperation-aware. Our work formulates the problem of efficient data gathering as a cooperative route-optimization problem with communication constraints. We also analyze (network) coded data transmission and storage for simplifying cooperation amongst sensors as well as data collection by the AV. Given the complexity of the problem, we focus on heuristic techniques, such as particle swarm optimization, to calculate the AV's route and the times for communication with each sensor and/or cluster of sensors. We analyze two extreme cases, i.e., networks with and without intra-cluster cooperation, and provide numerical results to illustrate that the performance gap between them increases with the number of nodes. We show that cooperation in a 100 sensor deployment can increase the amount of data collected by up to a factor of 3 with respect to path planning without cooperation.