Sekou Remy

Robots on the Web

Today, the Internet has become a resource where human users expect to find answers. If Web information and services are so useful for human users, then why not share these resources with autonomous software and robotic systems? A significant barrier to realizing this goal is the mismatch in the design and operation of robotic systems when compared to Web-oriented paradigms such as service-oriented computing. In this article, we introduce both developmental and operational paradigms, whereas robots can be outfitted with Web-oriented software interfaces that give them access to universally standard Web resources.

Green web services: Models for energy-aware web services and applications

As the Web has evolved, web-based capabilities or web services have become a significant aspect of day-to-day routines for businesses and individuals, alike. Interactions with the Web and its services represent a significant portion of overall global power consumption. With the current national emphasis on sustainable resources and energy-efficiency, it is paramount that web processes be efficient in their use of energy. While many studies aim to reduce power consumption in network and computing hardware, our work focuses on models and frameworks to support energy-aware usage of web services (i.e. at the software and information technology (IT) process level). It will not be feasible to rely on measured power consumption when making web services usage decisions; instead predictive energy consumption models are more adequate for real-time decision support. In this paper, we introduce a model that isolates the power consumption of a particular web service within a regular server environment. The model assimilates key factors influencing the power consumption during web services executions such as server hardware characteristic, average CPU load, memory utilization, and hard drive access. Evaluative experiments demonstrate that our model can predict power consumption under varied domain-specific operations and conditions.

Visualize your robot with your eyes closed: A multi-modal interactive approach using environmental feedback

In this paper, we discuss an approach for enabling students with a visual impairment (VI) to validate the program sequence of a robotic system operating in the real world. We introduce a method that enables the person with VI to feel their robots movement as well as the environment in which the robot is traveling. The design includes a human-robot interaction framework that utilizes multi-modal feedback to transfer the environmental perception to a human user with VI. Haptic feedback and auditory feedback are selected as primary methods for user interaction. Using this multi-modal sensory feedback approach, participants are taught to program their own robot to accomplish varying navigation tasks. We discuss and analyze the implementation of the method as deployed during two summer camps for middle-school students with visual impairment.

Quantifying coherence when learning behaviors via teleoperation

Applications of robotics are quickly changing. Just as computer use evolved from research purposes to everyday functions, applications of robotics are making a transition to mainstream usage. With this change in applications comes a change in the user base of robotics, and there is a pronounced move to reduce the complexity of robotic control. The move to reduce complexity is linked to the separation of the role of robot designer and robot operator. For many target applications, the operator of the robot needs to be able to correct and augment its capabilities. One method to enable this is learning from human data, which has already been successfully applied to robotics. We assert that this learning process is only viable when the demonstrated human behavior is coherent. In this work we test the hypothesis that quantifying the coherence in the provided instruction can provide useful information about the progress of the learning process. We discuss results from the application of this method to reactive behaviors. Such behaviors permit the learning process to be computationally tractable in real-time. These results support the hypothesis that coherence is important for this type of learning and also show that this property can be used to provide an avenue for self regulation of the learning process.

Learning Approaches Applied to Human-Robot Interaction for Space Missions

Abstract Advances in space science and technology have enabled humanity to reach a stage where we are able to send manned and unrnanned vehicles to explore neazby planets. However, given key differences between terrestrial and space environrnents such as differences in atmospheric content and pressure, acceleration due to gravity among many others between our planet and those we wish to explore, it is not always easy or feasible to expect all mission related tasks to be accomplished by astronauts alone. The presence of robots that specialize in different tasks would greatly enhance our capabilities and enable better overall performance. In this paper we discuss a methodology for building a robotic system that can learn to perform tasks via interactive leazning. This learning functionality extends the ability for a robot agent to operate with similar competence as their human teacher- whether astronaut, mission designer, or engineer. We provide details on our approach and give representative examples of ap...

In situ interactive teaching of trustworthy robotic assistants

In this paper we discuss a method for transferring human knowledge to a robotic platform via teleoperation. The method combines unsupervised clustering and classification with interactive instruction to enable behavior capture in a transferable form. We discuss the approach in both simulation and robotic hardware platform to show the capability of the learning system. In this work we also present a definition and associated metric for trustworthiness, and relate this quantity to system performance. Improved performance and trustworthiness are motivations for our application of interactive learning, and we present results that indicate that these were indeed attained.

Improving the performance of ANN training with an unsupervised filtering method

Learning control strategies from examples has been identified as an important capability for many robotic systems. In this work we show how the learning process can be aided by autonomously filtering the training set provided to improve key properties of the learning process. Demonstrated with data gathered for manipulation tasks, the results herein show the improved performance when autonomous filtering is applied. The filtration method, with no prior knowledge of the task, was able to partition the training sets into sets almost equal to expertly labeled sets. In the case where the filter did not produce the same groupings as the expert user, the method still permitted a controller to be trained which demonstrated a success rate of 92%.

Exploring the relationship between degrees of self similarity and altered driving states

Combating the dangers of distracted driving is currently one of the major road safety concerns for our society. There is much being done to increase awareness on the issue and also to legislate punishment for drivers shoo get caught turning their focus away from the road, but these have not proven to fully address the issue. While cars are equipped with several other systems to keep their drivers and all nearby safe, there is a void when it comes to tools which can help keep drivers alerts, or at least to help identify the drivers distraction states. This work seeks to unmask distracted driving by monitoring the statistical self similarity of physiological, environmental and vehicular channels of data, through the application of Detrended Fluctuation Analysis (DFA). Combining the self similarity property for several but not all the channels in the considered data, a viable predictor was generated. Implemented in large part as a Self Organizing Map (SOM) construct, the predictor confirms that self similarity contains useful information. More work is required to uncover why this is the case, as well as just how good a predictor can be generated through extending this approach.

3D Simulations for Testing and Validating Robotic-Driven Applications for Exploring Lunar Poles

Due to the embodied nature of a robotic system, it is difficult to test the high level control software without the use of the physical robotic hardware. However, the availability of prototype robotic hardware and representative environments for software testing is often limited. This is particularly acute when the robot is to be deployed in remote planetary environments. The ability is needed to test and validate robotic control software within the design cycle, without requiring the time and effort of full field deployments. Currently, no single simulation system exists which provides both a high quality rendering environment and a means of constructing complex objects and environments. Presented here is a case study of developing a simulation system for testing an arctic robotic sensor node of possible use in the exploration of the lunar poles. In this work we focus on methods for developing visually faithful environments and local hazards, with emphasis on the resulting performance of vision-based robotic algorithms.