Ali Sekmen

Assessment of adaptive human-robot interactions

One of the overarching goals of robotics research is that robots ultimately coexist with people in human societies as an integral part of them. In order to achieve this goal, robots need to be accepted by people as natural partners within the society. It is therefore essential for robots to have adaptive learning mechanisms that can intelligently update a human model for effective human-robot interaction (HRI). This might be critical in interactions with elderly and disabled people in their daily activities. This research has developed and evaluated an intelligent HRI system that enables a mobile robot to learn adaptively about the behaviors and preferences of the people with whom it interacts. Various learning algorithms have been compared and a Bayesian learning mechanism has been implemented by estimating and updating a parameter set that models behaviors and preferences of people. Every time a user interacts with the robot, the model is updated. The robot then uses the model to predict future actions of its user. A variety of HRI modalities including speech recognition, sound source localization, simple natural language understanding, face detection, face recognition, and attention gaining/losing systems, along with a navigation system, have been integrated with the learning system. The integrated system has been successfully implemented on a Pioneer 3-AT mobile robot. The system has also been evaluated using 25 subjects who interacted with the robot using adaptive and non-adaptive interfaces. This study showed that adaptive interaction is preferred over non-adaptive interaction by the participants at a statistically significant level.

Vision-based mobile robot learning and navigation

This research develops a vision-based learning mechanism for semi-autonomous mobile robot navigation. Laser-based localization, vision-based object detection and recognition, and route-based navigation techniques for a mobile robot have been integrated. Initially, the robot can localize itself in an indoor environment with its laser range finder. Then, a user can teleoperate the robot and point the objects of interest via a graphical user interface. In addition, the robot can automatically detect potential objects of interest. The objects are automatically recognized by the object recognition system using neural networks. If the robot cannot recognize an object, it asks the user to identify it. The user can ask the robot to navigate back autonomously to an object recognized or identified before. The human and robot can interact vocally via an integrated speech recognition and synthesis software component. The completed system has been successfully tested on a Pioneer 3-AT mobile robot.

Dynamic multiobjective optimization of war resource allocation using adaptive genetic algorithms

Genetic algorithms (GA) are often well suited for multiobjective optimization problems. The major objective of this research is to optimize the war resource allocations of sorties, for a given war scenario, using genetic algorithms. The war is simulated using THUNDER software. THUNDER software is a stochastic, two-sided, analytical simulation of campaign-level military operations. The simulation is subject to internal unknown noises similar to real war cases. Due to these noises and discreteness in the simulation, as well as in real wars, an adaptive GA approach has been applied to solve this multiobjective optimization problem. Transforming this multiobjective optimization problem to a form suitable for direct implementation of GA was a major accomplishment of this research. A suitable fitness function was chosen after careful research and testing on the GA. Furthermore, the GA parameters were adaptively set to yield smoother and faster fitness convergence. Two fuzzy logic mechanisms were used to adapt the GA parameters. In the first mechanism, the mutation and crossover rates were changed adaptively. In the second mechanism, the fitness function coefficients are changed dynamically in each run. Testing results showed that the adaptive GA outperforms the conventional GA search in this multiobjective optimization problem and was effectively able to allocate forces for war scenarios.

Genetic algorithms applied to real time multiobjective optimization problems

Genetic algorithms (GAs) are often well-suited for multi-objective optimization problems. In this work, multiple objectives pertaining to the THUNDER software (a very large military campaign simulation model) were used to optimize the war results obtained from the software. It is a stochastic, two-sided, analytical Monte-Carlo simulation of military operations. The simulation is subject to internal unknown noises. Due to these noises and to the discreteness in the simulation program, a GA approach has been applied to this multi-objective optimization problem. This method is capable of searching for multiple solutions concurrently in a single run. Transforming this problem to a form that is suitable for the direct implementation of GA was the major challenge that was achieved. Three different kinds of fitness assignment methods were implemented, and the best one was chosen. The THUNDER software may be considered as a black box, since very little information about its internal dynamics was known. The problem with the THUNDER software is its expensive running time. In order to optimize the time involved with the THUNDER software, autocorrelation techniques were used to reduce the number of THUNDER runs. Furthermore, the GA parameters were set optimally to yield smoother and faster fitness convergence. From these results, the GA was shown to perform well for this multi-objective optimization problem and was effectively able to allocate force power for the THUNDER software.

Human–robot interaction via voice-controllable intelligent user interface

An understanding of how humans and robots can successfully interact to accomplish specific tasks is crucial in creating more sophisticated robots that may eventually become an integral part of human societies. A social robot needs to be able to learn the preferences and capabilities of the people with whom it interacts so that it can adapt its behaviors for more efficient and friendly interaction. Advances in human– computer interaction technologies have been widely used in improving human–robot interaction (HRI). It is now possible to interact with robots via natural communication means such as speech. In this paper, an innovative approach for HRI via voice-controllable intelligent user interfaces is described. The design and implementation of such interfaces are described. The traditional approaches for human–robot user interface design are explained and the advantages of the proposed approach are presented. The designed intelligent user interface, which learns user preferences and capabilities in time, can be controlled with voice. The system was successfully implemented and tested on a Pioneer 3-AT mobile robot. 20 participants, who were assessed on spatial reasoning ability, directed the robot in spatial navigation tasks to evaluate the effectiveness of the voice control in HRI. Time to complete the task, number of steps, and errors were collected. Results indicated that spatial reasoning ability and voice-control were reliable predictors of efficiency of robot teleoperation. 75% of the subjects with high spatial reasoning ability preferred using voice-control over manual control. The effect of spatial reasoning ability in teleoperation with voice-control was lower compared to that of manual control.

Nearness to Local Subspace Algorithm for Subspace and Motion Segmentation

This letter presents a clustering algorithm for high dimensional data that comes from a union of lower dimensional subspaces of equal and known dimensions. The algorithm estimates a local subspace for each data point, and computes the distances between the local subspaces and the points to convert the problem to a one-dimensional data clustering problem. The algorithm is reliable in the presence of noise, and applied to the Hopkins 155 Dataset, it generates the best results to date for motion segmentation. The two motion, three motion, and overall segmentation rates for the video sequences are 99.43%, 98.69%, and 99.24%, respectively.

Evolutionary approach to multi-objective problems using adaptive genetic algorithms

The paper describes an adaptive genetic algorithm used to achieve multi-objectives such as minimizing the territory losses and maximizing enemy air losses by finding the optimum distribution of aircraft fighting in a war scenario simulated by the THUNDER software. The adaptive genetic algorithm changes the mutation and crossover adaptively to provide fast convergence to the optimum possible solutions. According to the population of the fitness values obtained for each generation, three distribution properties (the mean, the variance and the best fitness value) are determined and used as input to a fuzzy-logic system for modifying the mutation and crossover rates to obtain the individuals of the next generation. This enables fast and smooth convergence to the best possible solutions.

Real-time multiple moving targets detection from airborne IR imagery by dynamic Gabor filter and dynamic Gaussian detector

This paper presents a robust approach to detect multiple moving targets from aerial infrared (IR) image sequences. The proposed novel method is based on dynamic Gabor filter and dynamic Gaussian detector. First, the motion induced by the airborne platform is modeled by parametric affine transformation and the IR video is stabilized by eliminating the background motion. A set of feature points are extracted and they are categorized into inliers and outliers. The inliers are used to estimate affine transformation parameters, and the outliers are used to localize moving targets. Then, a dynamic Gabor filter is employed to enhance the difference images for more accurate detection and localization of moving targets. The Gabor filters orientation is dynamically changed according to the orientation of optical flows. Next, the specular highlights generated by the dynamic Gabor filter are detected. The outliers and specular highlights are fused to indentify the moving targets. If a specular highlight lies in an outlier cluster, it corresponds to a target; otherwise, the dynamic Gaussian detector is employed to determine whether the specular highlight corresponds to a target. The detection speed is approximate 2 frames per second, which meets the real-time requirement of many target tracking systems.

Towards socially acceptable robots

Robots are integrating more and more into our lives, However, to become an integral part of daily life, they should be socially accepted by humans. Evidently, the acceptance rate will increase as human-robot interaction gets closer to human-human interaction. The article describes the development of a Web based information filtering system, which enables a humanoid robot to initiate interaction with a human by generating human-like daily conversations.

Human-robot interaction over the Internet

Describes two Java-based Internet control mechanisms, manual control and autonomous navigation, for a mobile robot to allow users to explore the robots environment. In the manual control, a user sends control commands to the robot over the Internet to make the robot explore its environment. In the autonomous navigation mode, the user only needs to specify the target point and the rest of the task is taken care of by the robot. In both cases, the real time video images, the robot trajectory, and a status report of the robot are sent to the user over the Internet. In addition, sonar readings are transmitted over the Internet in the manual control to provide more detailed information to the user. The mobile robot was successfully controlled from several locations in the USA.