Abstract not found

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.

Abstract not found

Abstract — Cabled robotic systems have been used for a diverse set of applications such as environmental sensing, search and rescue, sports and entertainment and air vehicle simulators. In this paper, we introduce a new cabled robot- Networked Info Mechanical System for Planar actuation (NIMS-PL), with energy profiling capabilities. Accurate energy measurements supported by NIMS-PL enable path planning that optimizes the robot’s path subject to an upper bound on energy consumption. We performed extensive empirical validation of the optimized path planning approach in simulation using an environmental sensing application as an example. We also validated the simulation results using NIMS-PL, demonstrating significant improvements in the sensing task when accounting with accurate energy measurements as opposed to Euclidean distance, which is typically used for modeling energy spent in path traversal. I.

In active learning, it is typically assumed that all instances require the same amount of effort to label and that the cost of labeling an instance is independent of other selected instances. In spatially distributed data such as hyperspectral imagery for land-cover classification, the act of labeling a point (i.e., determining the land-type) may involve physically traveling to a location and determining ground truth. In this case, both assumptions about label acquisition costs made by traditional active learning are broken, since costs will depend on physical locations and accessibility of all the visited points. This paper formulates and analyzes the novel problem of performing active learning on spatial data where label acquisition costs are proportional to distance traveled. 1

This paper deals with a multiple vehicle routing problem in which profit is maximized subject to competition. This problem will be referred to as the multiple vehicle routing problem with profits and competition (MVRPPC). The MVRPPC differs from traditional multivehicle routing problems in three ways: (1) competition is incorporated into the process, (2) the objective is to maximize profits rather than minimize costs, and (3) it is assumed that trucks leave and return to their home bases empty, thus any freight picked up in a tour must be delivered in that same tour (which represents the case of for-hire carriers). The solution method takes a “cluster first, route second ” approach in which the clustering phase combines a geometric clustering with a generalized assignment problem (GAP). The routing is performed using a tabu search. To get an idea of how well the tabu search performs, an alternative method for routing was developed which consisted of a mixed integer program (MIP) based on the flow formulation of the traveling salesman problem. The solution approach was applied to a series of problems of varying size and complexity with the routing performed by both the tabu search and the MIP formulations. A comparison of the tabu search and MIP solutions indicated that the tabu search solutions were practically the same than the corresponding MIP solutions, with tabu search objective function values which were no more than 0.70 % of the MIP values. As an illustration of the potential uses of the methodologies developed, the paper analyzes the role of the degree of market transparency on the geographic segmentation of the market. Thorson, Holguín-Veras and Mitchell 3

Examining methods for maximising ship classifications in maritime surveillance

Supervised learners can be used to automatically classify many types of spatially distributed data. For example, land cover classification by hyperspectral image data analysis is an important remote sensing task where a supervised learner is trained on a large set of labeled data. However, while gathering unlabeled samples may be relatively easy, labeling large amounts of data can be very costly. Acting learning is one approach to reduce the amount of labeled data required to build a supervised learner that performs well. However, most active learning approaches assume that the cost of acquiring labels for all points is uniform. For spatially distributed data that requires physical access to spatial locations in order to assign labels, label acquisition costs become proportional to distance traveled in order to label a point. In this paper, we present results for applying a novel active learning method which takes variable label acquisition costs into account on two hyperspectral datasets. Index Terms — hyperspectral data, remote sensing, classification, active learning, spatial information 1.

Pareto Local Search (PLS) is a generalization of the local search algorithms to handle more than one objective. In this paper, two variants of PLS are examined on the multiobjective 0/1 knapsack problems, compared with three well-known multiobjective EA algorithms, namely SPEA, SPEA2 and NSGA2. Furthermore, A Guided Local Search (GLS) based multiobjective optimization algorithm is proposed, the Guided Pareto Local Search (GPLS). GPLS shows the ability of GLS to set on top of PLS not only to help PLS to escape Pareto local optimal set, but also to enhance its convergence toward and spread over the true Pareto front. Experimental results have shown that PLS can produce results with a very good quality, and proven the effectiveness of the GPLS.

Abstract not found