Search

We consider the problem of optimal unsignalized intersection management, wherein we seek to obtain safe and optimal trajectories, for a set of robots that arrive randomly and continually. This problem involves repeatedly solving a mixed integer program (with robot acceleration trajectories as decision variables) with different parameters, for which the computation time using a naive optimization algorithm scales exponentially with the number of robots and lanes. Hence, such an approach is not suitable for real-time implementation. In this paper, we propose a solution framework that combines learning and sequential optimization. In particular, we propose an algorithm for learning a shared policy that given the traffic state information, determines the crossing order of the robots. Then, we optimize the trajectories of the robots sequentially according to that crossing order. This approach inherently guarantees safety at all times. We validate the performance of this approach using extensive simulations and compare our approach against 5 different heuristics from the literature in 9 different simulation settings. Our approach, on average, significantly outperforms the heuristics from the literature in various metrics like objective function, weighted average of crossing times and computation time. For example, in some scenarios, we have observed that our approach offers up to 150% improvement in objective value over the first come first serve heuristic. Even on untrained scenarios, our approach shows a consistent improvement (in objective value) of more than 30% over all heuristics under consideration. We also show through simulations that the computation time for our approach scales linearly with the number of robots (assuming all other factors are constant). We further implement the learnt policies on physical robots with a few modifications to the solution framework to address real-world challenges and establish its real-time implementability.

As cyber–physical networks become increasingly equipped with embedded capabilities, they are made vulnerable to malicious attacks with the increased number of access points available to attackers. A particularly pernicious attack is spoofing, in which a malicious agent spawns multiple identities and can compromise otherwise attack–resilient algorithms that rely on assumed network robustness structures. We generalize a class of resilient consensus strategies, known as weighted mean-subsequence-reduced (W-MSR) consensus, to further provide spoof resilience by incorporating a physical layer authentication. By comparing the physical fingerprints of received signals, legitimate agents can identify and isolate malicious agents that attempt spoofing attacks. A key technical contribution is to quantify worst case misclassification probability using distributionally robust Chebyshev bounds computed via semidefinite programming when the physical fingerprints of received signals are stochastic. Numerical simulations and experimental results illustrate the effectiveness of the proposed methods. Our framework is applicable to a variety of problems involving multirobot systems coordinating via wireless communication. [ABSTRACT FROM AUTHOR]

Underwater mobile sensor networks such as Autonomous Underwater Vehicles (AUVs) or robots are envisioned to enable applications for oceanographic data collection, environmental and pollution monitoring, offshore exploration, and distributed tactical surveillance. These applications require running compute- and data-intensive algorithms that go beyond the capabilities of the individual AUVs that are involved in a mission. To execute these task-parallel algorithms in resource- and time-constrained environments, dynamic and reliable collaboration between local networked robots (e.g., AUVs) and remote public Clouds is needed. To this end, the heterogeneous sensing, computing, communication, and storage capabilities of local and remote resources are exploited to form a “loosely coupled” mobile Cloud, and a novel resource provisioning engine that dynamically takes decisions on “what” and “where” the tasks should be executed in the mobile Cloud is introduced. Comparison of benefits of collaboration between local and Cloud resources with purely local and centralized approaches are presented through exhaustive computer simulations. [ABSTRACT FROM PUBLISHER]