Theodoros Theodoridis

BioSleeve: a natural EMG-based interface for HRI

This paper presents the BioSleeve, a new gesture-based human interface for natural robot control. Detailed activity of the users hand and arm is acquired via surface electromyography sensors and an inertial measurement unit that are embedded in a forearm sleeve. The BioSleeves accompanying software decodes the sensor signals, classifies gesture type, and maps the result to output commands to an external robot. The current BioSleeve system can reliably decode as many as sixteen discrete hand gestures and estimate the continuous orientation of the forearm. The gestures are used in several modes: for supervisory point-to-goal commands, virtual joystick for teleoperation, and high degree-of-freedom (DOF) mimicked manipulation. We report results from three control applications: a manipulation robot, a small ground vehicle, and a 5-DOF hand.

Toward Intelligent Security Robots: A Survey

In this paper, a survey is being conducted on the investigation of a four-class taxonomy related to security robots that appeared over the past three decades. The survey emphasizes on state-of-the-art mobile technologies that have been developed for crime-fighting robots, capable of crafting critical situations with confrontation strategies. Throughout this investigation, 60 projects are being examined with respect to faculties and sensor apparatus being used. A statistical analysis, which is carried on the historical developments of the most attractive frameworks, reveals the popularity of the four security robot categories and their chronological progress over the past 30 years. The categories being evaluated regard teleoperated, distributed, surveillance, and law-enforcement robot architectures. In the survey, an attempt is made to explain the importance of intelligent methodologies, and their emergent effects in security tasks. The major findings of this analysis illustrate the minor contribution of intelligent architectures in crime-fighting robots, and what constitutes an intelligent security robot.

Ubiquitous robotics in physical human action recognition: A comparison between dynamic ANNs and GP

Two different classifier representations based on dynamic artificial neural networks (ANNs) and genetic programming (GP) are being compared on a human action recognition task by an ubiquitous mobile robot. The classification methodologies used, process time series generated by an indoor ubiquitous 3D tracker which generates spatial points based on 23 reflectable markers attached on a human body. This investigation focuses mainly on class discrimination of normal and aggressive action recognition performed by an architecture which implements an interconnection between an ubiquitous 3D sensory tracker system and a mobile robot to perceive, process, and classify physical human actions. The 3D tracker and the robot are used as a perception-to-action architecture to process physical activities generated by human subjects. Both classifiers process the activity time series to eventually generate surveillance assessment reports by generating evaluation statistics indicating the classification accuracy of the actions recognized.

Maximum margin decision surfaces for increased generalisation in evolutionary decision tree learning

Decision tree learning is one of the most widely used and practical methods for inductive inference. We present a novel method that increases the generalisation of genetically-induced classification trees, which employ linear discriminants as the partitioning function at each internal node. Genetic Programming is employed to search the space of oblique decision trees. At the end of the evolutionary run, a (1+1) Evolution Strategy is used to geometrically optimise the boundaries in the decision space, which are represented by the linear discriminant functions. The evolutionary optimisation concerns maximising the decision-surface margin that is defined to be the smallest distance between the decision-surface and any of the samples. Initial empirical results of the application of our method to a series of datasets from the UCI repository suggest that model generalisation benefits from the margin maximisation, and that the new method is a very competent approach to pattern classification as compared to other learning algorithms.

Kinect Enabled Monte Carlo Localisation for a Robotic Wheelchair

Proximity sensors and 2D vision methods have shown to work robustly in particle filter-based Monte Carlo Localisation (MCL). It would be interesting however to examine whether modern 3D vision sensors would be equally efficient for localising a robotic wheelchair with MCL. In this work, we introduce a visual Region Locator Descriptor, acquired from a 3D map using the Kinect sensor to conduct localisation. The descriptor segments the Kinect’s depth map into a grid of 36 regions, where the depth of each column-cell is being used as a distance range for the measurement model of a particle filter. The experimental work concentrated on a comparison of three different localization cases. (a) an odometry model without MCL, (b) with MCL and sonar sensors only, (c) with MCL and the Kinect sensor only. The comparative study demonstrated the efficiency of a modern 3D depth sensor, such as the Kinect, which can be used reliably for wheelchair localisation.

Action classification of 3D human models using dynamic ANNs for mobile robot surveillance

This paper presents an alternative approach on physical human action classification implemented by mobile robots. In contrast with other action recognition methods, this research indicates the best configuration topology of a number of dynamic neural networks to be used in 3D time series classification by showing several comparison performances. In this action recognition investigation we demonstrate high level network granularity on dynamic classification and class discrimination of normal and aggressive action recognition. An interconnection between an ubiquitous 3D sensory tracker system and a mobile robot is set to create a perception to action architecture capable to perceive, process, and classify physical human actions. The robot is used as a process-to-action unit to process the 3D data taken by the tracker and to eventually generate surveillance assessment reports pointing towards action-class matchings as well as generating evaluation statistics which signify the quality of the actions recognized.

Variable stiffness Mckibben muscles with hydraulic and pneumatic operating modes

Abstract McKibben muscles have been shown to have improved stiffness characteristics when operating hydraulically. However when operating pneumatically, they are compliant and so have potential for safer physical human–robot interaction. This paper presents a method for rapidly switching between pneumatic and hydraulic modes of operation without the need to remove all hydraulic fluid from the actuator. A compliant and potentially safe pneumatic mode is demonstrated and compared with a much stiffer hydraulic mode. The paper also explores a combined pneumatic/hydraulic mode of operation which allows both the position of the joint and the speed at which it reacts to a disturbance force to be controlled.

Learning environment models in car racing using stateful Genetic Programming

For computational intelligence to be useful in creating game agent AI we need to focus on methods that allow the creation and maintenance of models for the environment, which the artificial agents inhabit. Maintaining a model allows an agent to plan its actions more effectively by combining immediate sensory information along with a memories that have been acquired while operating in that environment. To this end, we propose a way to build environment models for non-player characters in car racing games using stateful Genetic Programming. A method is presented, where general-purpose 2-dimensional data-structures are used to build a model of the racing track. Results demonstrate that model-building behaviour can be cooperatively coevolved with car-controlling behaviour in modular programs that make use of these models in order to navigate successfully around a racing track.

A gaussian groundplan projection area model for evolving probabilistic classifiers

In this paper, an investigation of evolvable probabilistic classifiers is conducted, along with a thorough comparison between a classical Gaussian distance model, and the induction of Gaussian-to-circle projection model. The newly introduced model refers to a distance fitness measure, based on the projection of Gaussian distributions with geometric circles. The projection architecture aims to model and classify physical aggressive behaviours, by using biomechanical primitives. The primitives are being used to model the dynamics of the aggressive activities, by evolving biomechanical classifiers, which can discriminate between three behaviours and six actions. Both evolutionary models have shown strong discrimination performances on recognising the individual actions of each behaviour. From the comparison, the proposed model outperformed the classical one with three ensemble programs.

Evolving aggressive biomechanical models with genetic programming

A repertory of nine biomechanical aggressive activities is investigated in this paper, in our effort to instigate a new paradigm at aggregating descriptive mathematical models with evolutionary, symbolic program representations. Such representations are based on shared biomechanical primitives inspired from kinematics, dynamics, and energetics. Our intension is twofold, initially to study the nature of aggressive biomechanical models and then to classify their physical activities by evolving expression-trees with biomechanical synthesis. The methodology targets on evolving expression programs using the Gaussian Ground-plan Projection Area model, to discriminate among three aggressive behaviours and recognise the individual actions involved. For the n-class problem, three programs have been evolved, each for an aggressive behaviour such as the arm-Launch, the legLaunch, and the bodyLaunch behaviour, so that to be able to examine separately the evolvable characteristics induced. The proposed approach has evidently shown strong classification and discrimination performances.