Sanem Sariel

Naval Mine Countermeasure Missions

Undersea operations using autonomous underwater vehicles (AUVs) provide a different and in some ways a more challenging problem than tasks for unmanned aerial vehicles and unmanned ground vehicles. In particular, in undersea operations, communication windows are restricted, and bandwidth is limited. Consequently, coordination among agents is correspondingly more difficult. In traditional approaches, a central planner initially assigns subtasks to a set of AUVs to achieve the team goal. However, those initial task assignments may become inefficient during real-time execution because of the real-world issues such as failures. Therefore, initial task allocations are usually subject to change if efficiency is a high concern. Reallocations are needed and should be performed in a distributed manner. To provide such flexibility, we propose a distributed auction-based cooperation framework, distributed and efficient multirobot-cooperation framework (DEMiR-CF), which is an online dynamic task allocation (reallocation) system that aims to achieve a team goal while using resources effectively. DEMiR-CF, with integrated task scheduling and execution capabilities, can also respond to and recover from real-time contingencies such as communication failures, delays, range limitations, and robot failures.

A Distributed Multi-robot Cooperation Framework for Real Time Task Achievement

In this paper, we propose a general framework, DEMiR-CF, for a multi-robot team to achieve a complex mission including inter-related tasks that require diverse capabilities and/or simultaneous executions. Our framework integrates a distributed task allocation scheme, cooperation mechanisms and precaution routines for multi-robot team execution. Its performance has been demonstrated in NavalMine Countermeasures, Multi-robotMulti-Target Exploration and Object Construction domains. The framework not only ensures near-optimal solutions for task achievement but also efficiently responds to real time contingencies.

Incremental multi-robot task selection for resource constrained and interrelated tasks

When the tasks of a mission are interrelated and subject to several resource constraints, more efforts are needed to coordinate robots towards achieving the mission than independent tasks. In this work, we formulate the Coordinated Task Selection Problem (CTSP) to form the basis of an efficient dynamic task selection scheme for allocation of interrelated tasks of a complex mission to the members of a multi-robot team. Since processing times of tasks are not exactly known in advance, the incremental task selection scheme for the eligible tasks prevents redundant efforts as, instead of scheduling all of the tasks, they are allocated to robots as needed. This approach results in globally efficient solutions through mechanisms that form priority based rough schedules and select the most suitable tasks from these schedules. Since our method is targeted at real world task execution, communication requirements are kept limited. Empirical evaluations of the proposed approach are performed on the Webots simulator and the real robots. The results validate that the proposed approach is scalable, efficient and suitable to the real world safe mission achievement.

Content-based access to art paintings

This paper introduces ArtHistorian, a content-based classification and indexing system that represents the visual content of art paintings by a six-dimensional feature set. The introduced feature set is robust to scale changes and can handle variations in lighting conditions. A nonlinear SVM classifier included in the system learns the characteristics of fundamental art movements and painting styles. A hybrid classifier that combines PCA representation of paintings with the SVM classification is also exploited. It is shown that ArtHistorian is capable of classifying art paintings based on painters as well as art movements with an accuracy of greater than 90% and its false alarm ratio is very small. The developed system enables the user to run content-based queries and to retrieve from painting databases created in XML format.

Empirical Evaluation of Auction-Based Coordination of AUVs in a Realistic Simulated Mine Countermeasure Task

In this work, we evaluate performance of our distributed cooperation framework, DEMiR-CF, for Naval Mine Countermeasure missions on the US NAVY’s ALWSE-MC simulator against different contingencies that may arise run time. Our cooperation framework integrates a distributed task allocation scheme, coordination mechanisms and precaution routines for multirobot team execution. Its performance has been demonstrated in Multi-robot Multi-target exploration and Object Construction domains. Marine applications provide additional challenges such as noisy communication, position uncertainty and the likelihood of robot failures. There is a high probability that the initial assignments are subject to change during run time, in these kinds of environments. Our framework ensures robust execution and efficient completion of missions against several different types of failures. Preliminary results for MCM missions are promising in the sense of mission completion, and AUV paths are close to optimal in the presence of uncertainties.

A Gene Based Adaptive Mutation Strategy for Genetic Algorithms

In this study, a new mechanism that adapts the mutation rate for each locus on the chromosomes, based on feedback obtained from the current population is proposed. Through tests using the one-max problem, it is shown that the proposed scheme improves convergence rate. Further tests are performed using the 4-Peaks and multiple knapsack test problems to compare the performance of the proposed approach with other similar parameter control approaches. A convergence control scheme that provides acceptable perform- ance is chosen to maintain sufficient diversity in the population and implemented for all tested methods to provide fair comparisons. The effects of using a convergence control mechanism are not within the scope of this paper and will be explored in a future study. As a result of the tests, promising results which promote further experimentation are obtained.

A novel search strategy for autonomous search and rescue robots

In this work, a novel search strategy for autonomous search and rescue robots, that is highly suitable for the environments when the aid of human rescuers or search dogs is completely impossible, is proposed. The work area for a robot running this planning strategy can be small voids or possibly dangerous environments. The main goal of the proposed planning strategy is to find victims under very tight time constraints. The exploration strategy is designed to improve the success of the main goal of the robot using specialized sensors when available. The secondary goals of the strategy are avoiding obstacles for preventing further collapses, avoiding cycles in the search, and handling errors. The conducted experiments show that the proposed strategies are complete and promising for the main goal of a SR robot. The number of steps to find the reachable victims is considerably smaller than that of the greedy mapping method.

Learning Behaviors of and Interactions Among Objects Through Spatio–Temporal Reasoning

In this paper, we introduce an automated reasoning system for learning object behaviors and interactions through the observation of event sequences. We use an existing system to learn the models of objects and further extend it to model more complex behaviors. Furthermore, we propose a spatio-temporal reasoning based learning method for reasoning about interactions among objects. Experience gained through learning is to be used for achieving goals by these objects. We take The Incredible Machine game (TIM) as the main testbed to analyze our system. Tutorials of the game are used to train the system. We analyze the results of our reasoning system on four different input types: a knowledge base of relations; spatial information; temporal information; and spatio-temporal information from the environment. Our analysis reveals that if a knowledge base about relations is provided, most of the interactions can be learned. We have also demonstrated that our learning method which incorporates both spatial and temporal information gives close results to that of the knowledge-based approach. This is promising as gathering spatio-temporal information does not require prior knowledge about relations. Our second analysis of the spatio-temporal reasoning method in the Electric Box computer game domain verifies the success of our approach.

Cognitive robots learning failure contexts through real-world experimentation

Learning is essential for cognitive robots as humans to gain experience and to adapt to the real world. We propose an experiential learning method for robots to build their experience online and to transfer knowledge among appropriate contexts. Experience gained through learning is used as a guide to future decisions of the robot for both efficiency and robustness. We use Inductive Logic Programming (ILP) learning paradigm to frame hypotheses represented in first-order logic that are useful for further reasoning and planning processes. Furthermore, incorporation of background knowledge is also possible to generalize the framed hypotheses. Partially specified world states can also be easily represented by these hypotheses. All these advantages of ILP make this approach superior to the other supervised learning methods. We have analyzed the performance of the learning method on our autonomous mobile robot and on our robot arm both building their experience on action executions online. It has been observed in both domains that our experience-based learning and learning-based guidance methods frame sound hypotheses that are useful for constraining and guiding the future tasks of the robots. This learning paradigm is promising especially for the contexts where abstraction is useful for efficient transfer of knowledge.

Robots Avoid Potential Failures through Experience-based Probabilistic Planning

Robots should avoid potential failure situations to safely execute their actions and to improve their performances. For this purpose, they need to build and use their experience online. We propose online learning-guided planning methods to address this problem. Our method includes an experiential learning process using Inductive Logic Programming (ILP) and a probabilistic planning framework that uses the experience gained by learning for improving task execution performance. We analyze our solution on a case study with an autonomous mobile robot in a multi-object manipulation domain where the objective is maximizing the number of collected objects while avoiding potential failures using experience. Our results indicate that the robot using our adaptive planning strategy ensures safety in task execution and reduces the number of potential failures.