Disruption Tolerant Networks (DTNs) require routing algorithms that are different from those designed for ad hoc networks. In DTNs, transport of data through the network is achieved through the physical movement of the participants in the network. We address two fundamental problems of routing in DTNs: routing algorithms with robust delivery rates, and management of networks where demand for routes does not match with the movement of peers. For the first problem, we propose the MV algorithm, which is based on observed meetings between peers and visits of peers to geographic locations. We show that our approach can achieve robust delivery rates: 83% of the maximum possible delivery rate, as compared to 64% for fifo buffer management. The advantage remains significant as the offered load of the system is increased an order of magnitude. For the second problem, we propose to augment available routes and capacity in a DTN through autonomous agents (e.g., autonomous blimps or mobile robots). We propose a controller that moves the agent to where network needs are not being met by the movement of peers. Our controller is able to increase delivery between fifteen and twenty-five percent. Our experiments shows that the introduction of even a few agents can dramatically increase the reliability of the message ferrying network. Moreover, our techniques are compatible and offer a robust method of approaching the problems of DTNs.

Lessons learned from three container-management systems over a decade.

Though widespread interest in software containers is a relatively recent phenomenon, at Google we have been managing Linux containers at scale for more than ten years and built three different container-management systems in that time. Each system was heavily influenced by its predecessors, even though they were developed for different reasons. This article describes the lessons we’ve learned from developing and operating them.

Abstract-Sampling-based motion planning discovers the implicit connectivity of a configuration space by selecting and connecting sets of configurations. The structure of every configuration space dictates a number of optimal sets of samples whose selection by a sampling-based planner results in a complete roadmap of the space. Though it is generally computationally impractical to develop complete knowledge of configuration space, each individual sample provides information about the configuration space. We propose a new utility-guided sampling strategy that accumulates this information into an approximate model of the configuration space. The model is an approximation of both the state (obstructed or free) of individual configurations and the connectivity of the configuration space. Our proposed sampler uses the approximate configuration space model to select samples that are maximally relevant to the planning task. The relevance of a sample is measured by its expected utility to the further coverage of the configuration space roadmap. The utility metric blends information from both configuration space state and connectivity. The planner incorporates the information obtained from each sample into its approximation and uses these improved models for subsequent sampling. Experimental results with an implementation of this approach to motion planning indicate that it is capable of significantly reducing the runtime required to construct a complete roadmap for configuration spaces with arbitrary degrees of freedom.

Robotic motion planning requires configuration space exploration. In high-dimensional configuration spaces, a complete exploration is computationally intractable. Practical motion planning algorithms for such high-dimensional spaces must expend computational resources in proportion to the local complexity of configuration space regions. We propose a novel motion planning approach that addresses this problem by building an incremental, approximate model of configuration space. The information contained in this model is used to direct computational resources to difficult regions, effectively addressing the narrow passage problem by adapting the sampling density to the complexity of that region. In addition, the expressiveness of the model permits predictive edge validations, which are performed based on the information contained in the model rather then by invoking a collision checker. Experimental results show that the exploitation of the information obtained through sampling and represented in a predictive model results in a significant decrease in the computational cost of motion planning.