AI problems such as autonomous robotic exploration, automatic diagnosis and activity recognition have in common the need for choosing among a set of informative but possibly expensive observations. When monitoring spatial phenomena with sensor networks or mobile robots, for example, we need to decide which locations to observe in order to most effectively decrease the uncertainty, at minimum cost. These problems usually are NP-hard. Many observation selection objectives satisfy submodularity, an intuitive diminishing returns property – adding a sensor to a small deployment helps more than adding it to a large deployment. In this paper, we survey recent advances in systematically exploiting this submodularity property to efficiently achieve near-optimal observation selections, under complex constraints. We illustrate the effectiveness of our approaches on problems of monitoring environmental phenomena and water distribution networks.

In many sensing applications, including environmental monitoring, measurement systems must cover a large space with only limited sensing resources. One approach to achieve required sensing coverage is to use robots to convey sensors within this space.Planning the motion of these robots – coordinating their paths in order to maximize the amount of information collected while placing bounds on their resources (e.g., path length or energy capacity) – is a NP-hard problem. In this paper, we present an efficient path planning algorithm that coordinates multiple robots, each having a resource constraint, to maximize the “informativeness ” of their visited locations. In particular, we use a Gaussian Process to model the underlying phenomenon, and use the mutual information between the visited locations and remainder of the space to characterize the amount of information collected. We provide strong theoretical approximation guarantees for our algorithm by exploiting the submodularity property of mutual information. In addition, we improve the efficiency of our approach by extending the algorithm using branch and bound and a region-based decomposition of the space. We provide an extensive empirical analysis of our algorithm, comparing with existing heuristics on datasets from several real world sensing applications.

In many applications, one has to actively select among a set of expensive observations before making an informed decision. For example, in environmental monitoring, we want to select locations to measure in order to most effectively predict spatial phenomena. Often, we want to select observations which are robust against a number of possible objective functions. Examples include minimizing the maximum posterior variance in Gaussian Process regression, robust experimental design, and sensor placement for outbreak detection. In this paper, we present the Submodular Saturation algorithm, a simple and efficient algorithm with strong theoretical approximation guarantees for cases where the possible objective functions exhibit submodularity, an intuitive diminishing returns property. Moreover, we prove that better approximation algorithms do not exist unless NP-complete problems admit efficient algorithms. We show how our algorithm can be extended to handle complex cost functions (incorporating non-unit observation cost or communication and path costs). We also show how the algorithm can be used to near-optimally trade off expected-case (e.g., the Mean Square Prediction Error in Gaussian Process regression) and worst-case (e.g., maximum predictive variance) performance. We show that many important machine learning problems fit our robust submodular observation selection formalism, and provide extensive empirical evaluation on several real-world problems. For Gaussian Process regression, our algorithm compares favorably with state-of-the-art heuristics described in the geostatistics literature, while being simpler, faster and providing theoretical guarantees. For robust experimental design, our algorithm performs favorably compared to SDP-based algorithms.

In this paper, we describe a novel, computationally efficient algorithm that facilitates the autonomous acquisition of readings from sensor networks (deciding when and which sensor to acquire readings from at any time), and which can, with minimal domain knowledge, perform a range of information processing tasks including modelling the accuracy of the sensor readings, predicting the value of missing sensor readings, and predicting how the monitored environmental variables will evolve into the future. Our motivating scenario is the need to provide situational awareness support to first responders at the scene of a large scale incident, and to this end, we describe a novel iterative formulation of a multi-output Gaussian process that can build and exploit a probabilistic model of the environmental variables being measured (including the correlations and delays that exist between them). We validate our approach using data collected from a network of weather sensors located on the south coast of England. 1

A great opportunity exists to fuse information from populations of privately-held sensors to create useful sensing applications. For example, GPS devices, embedded in cellphones and automobiles, might one day be employed as distributed networks of velocity sensors for traffic monitoring and routing. Unfortunately, privacy and resource considerations limit access to such data streams. We describe principles of community sensing that offer mechanisms for sharing data from privately held sensors. The methods take into account the likely availability of sensors, the contextsensitive value of sensor information, based on models of phenomena and demand, and sensor owners’ preferences about privacy and resource usage. We present efficient and well-characterized approximations of optimal sensing policies. We provide details on key principles of community sensing and highlight their use within a case study for road traffic monitoring.

The need for efficient monitoring of spatio-temporal dynamics in large environmental applications, such as the water quality monitoring in rivers and lakes, motivates the use of robotic sensors in order to achieve sufficient spatial coverage. Typically, these robots have bounded resources, such as limited battery or limited amounts of time to obtain measurements. Thus, careful coordination of their paths is required in order to maximize the amount of information collected, while respecting the resource constraints. In this paper, we present an efficient approach for near-optimally solving the NP-hard optimization problem of planning such informative paths. In particular, we first develop eSIP (efficient Single-robot Informative Path planning), an approximation algorithm for optimizing the path of a single robot. Hereby, we use a Gaussian Process to model the underlying phenomenon, and use the mutual information between the visited locations and remainder of the space to quantify the amount of information collected. We prove that the mutual information collected using paths obtained by using eSIP is close to the information obtained by an optimal solution. We then provide a general technique, sequential allocation, which can be used to extend any single robot planning algorithm, such as eSIP, for the multi-robot problem. This procedure approximately generalizes any guarantees for the single-robot problem to the multi-robot case. We extensively evaluate the effectiveness of our approach on several experiments performed in-field for two important environmental sensing applications, lake and river monitoring, and simulation experiments performed using several real world sensor network data sets. 1.

The circular sensing model has been widely used to estimate performance of sensing applications in existing analysis and simulations. While this model provides valuable high-level guidelines, the quantitative results obtained may not reflect the true performance of these applications, due to the existence of obstacles and sensing irregularity introduced by insufficient hardware calibration. In this project, we design and implement two Sensing Area Modeling (SAM) techniques useful in the real world. They complement each other in the design space. P-SAM provides accurate sensing area models for individual nodes using controlled or monitored events, while V-SAM provides continuous sensing similarity models using natural events in an environment. With these two models, we pioneer an investigation of the impact of sensing irregularity on application performance, such as coverage scheduling. We evaluate SAM extensively in realworld settings, using three testbeds consisting of 40 MICAz motes and 14 XSM motes. To study the performance at scale, we also provide an extensive 1,400-node simulation. Evaluation results reveal several serious issues concerning circular models, and demonstrate significant improvements in several applications when SAM is used instead.

This paper introduces an adaptive sampling algorithm for a mobile sensor network to estimate a scalar field. The sensor network consists of static nodes and one mobile robot. The static nodes are able to take sensor readings continuously in place, while the mobile robot is able to move and sample at multiple locations. The measurements from the robot and the static nodes are used to reconstruct an underlying scalar field. The algorithm presented in this paper accepts the measurements made by the static nodes as inputs and computes a path for the mobile robot which minimizes the integrated mean square error of the reconstructed field subject to the constraint that the robot has limited energy. We assume that the field does not change when robot is taking samples. In addition to simulations, we have validated the algorithm on a robotic boat and a system of static buoys operating in a lake over several km of traversed distance while reconstructing the temperature field of the lake surface.

This tutorial presents a detailed study of sensor faults that occur in deployed sensor networks and a systematic approach to model these faults. We begin by reviewing the fault detection literature for sensor networks. We draw from current literature, our own experience, and data collected from scientific deployments to develop a set of commonly used features useful in detecting and diagnosing sensor faults. We use this feature set to systematically define commonly observed faults, and provide examples of each of these faults from sensor data collected at recent deployments. Categories and Subject Descriptors: B.8.1 [Reliability, Testing, and Fault-Tolerance]: Fault

In recent years, a fundamental problem structure has emerged as very useful in a variety of machine learning applications: Submodularity is an intuitive diminishing returns property, stating that adding an element to a smaller set helps more than adding it to a larger set. Similarly to convexity, submodularity allows one to efficiently find provably (near-) optimal solutions for large problems. We present SFO, a toolbox for use in MATLAB or Octave that implements algorithms for minimization and maximization of submodular functions. A tutorial script illustrates the application of submodularity to machine learning and AI problems such as feature selection, clustering, inference and optimized information gathering.