Organizational Unit:

Institute for Robotics and Intelligent Machines (IRIM)

Permanent Link

https://hdl.handle.net/1853/70657

Includes Organization(s)

Organizational Unit

Biorobotics and Human Modeling Lab

Organizational Unit

Humanoid Robotics Laboratory

Full item page

Publication Search Results

Now showing 1 - 10 of 70

A control theoretic perspective on learning in robotics

(Georgia Institute of Technology, 2015-12-16) O'Flaherty, Rowland Wilde

For robotic systems to continue to move towards ubiquity, robots need to be more autonomous. More autonomy dictates that robots need to be able to make better decisions. Control theory and machine learning are fields of robotics that focus on the decision making process. However, each of these fields implements decision making at different levels of abstraction and at different time scales. Control theory defines low-level decisions at high rates, while machine learning defines high-level decision at low rates. The objective of this research is to integrate tools from both machine leaning and control theory to solve higher dimensional, complex problems, and to optimize the decision making process. Throughout this research, multiple algorithms were created that use concepts from both control theory and machine learning, which provide new tools for robots to make better decisions. One algorithm enables a robot to learn how to optimally explore an unknown space, and autonomously decide when to explore for new information or exploit its current information. Another algorithm enables a robot to learn how to locomote with complex dynamics. These algorithms are evaluated both in simulation and on real robots. The results and analysis of these experiments are presented, which demonstrate the utility of the algorithms introduced in this work. Additionally, a new notion of “learnability” is introduced to define and determine when a given dynamical system has the ability to gain knowledge to optimize a given objective function.
Towards a terradynamics of legged locomotion on homogeneous and Heterogeneous granular media through robophysical approaches

(Georgia Institute of Technology, 2015-11-16) Qian, Feifei

The objective of this research is to discover principles of ambulatory locomotion on homogeneous and heterogeneous granular substrates and create models of animal and robot interaction within such environments. Since interaction with natural substrates is too complicated to model, we take a robophysics approach – we create a terrain generation system where properties of heterogeneous multi-component substrates can be systematically varied to emulate a wide range of natural terrain properties such as compaction, orientation, obstacle shape/size/distribution, and obstacle mobility within the substrate. A schematic of the proposed system is discussed in detail in the body of this dissertation. Control of such substrates will allow for the systematic exploration of parameters of substrate properties, particularly substrate stiffness and heterogeneities. With this terrain creation system, we systematically explore locomotor strategies of simplified laboratory robots when traversing over different terrain properties. A key feature of this proposed work is the ability to generate general interaction models of locomotor appendages with such complex substrates. These models will aid in the design and control of future robots with morphologies and control strategies that allow for effective navigation on a large diversity of terrains, expanding the scope of terramechanics from large tracked and treaded vehicles on homogeneous ground to arbitrarily shaped and actuated locomotors moving on complex heterogeneous terrestrial substrates.
Developing an engagement and social interaction model for a robotic educational agent

(Georgia Institute of Technology, 2015-11-16) Brown, LaVonda N.

Effective educational agents should accomplish four essential goals during a student's learning process: 1) monitor engagement, 2) re-engage when appropriate, 3) teach novel tasks, and 4) improve retention. In this dissertation, we focus on all of these objectives through use of a teaching device (computer, tablet, or virtual reality game) and a robotic educational agent. We begin by developing and validating an engagement model based on the interactions between the student and the teaching device. This model uses time, performance, and/or eye gaze to determine the student's level of engagement. We then create a framework for implementing verbal and nonverbal, or gestural, behaviors on a humanoid robot and evaluate its perception and effectiveness for social interaction. These verbal and nonverbal behaviors are applied throughout the learning scenario to re-engage the students when the engagement model deems it necessary. Finally, we describe and validate the entire educational system that uses the engagement model to activate the behavioral strategies embedded on the robot when learning a new task. We then follow-up this study to evaluate student retention when using this system. The outcome of this research is the development of an educational system that effectively monitors student engagement, applies behavioral strategies, teaches novel tasks, and improves student retention to achieve individualized learning.
Developing robots that impact human-robot trust in emergency evacuations

(Georgia Institute of Technology, 2015-11-10) Robinette, Paul

High-risk, time-critical situations require trust for humans to interact with other agents even if they have never interacted with the agents before. In the near future, robots will perform tasks to help people in such situations, thus robots must understand why a person makes a trust decision in order to effectively aid the person. High casualty rates in several emergency evacuations motivate our use of this scenario as an example of a high-risk, time-critical situation. Emergency guidance robots can be stored inside of buildings then activated to search for victims and guide evacuees to safety. In this dissertation, we determined the conditions under which evacuees would be likely to trust a robot in an emergency evacuation. We began by examining reports of real-world evacuations and considering how guidance robots can best help. We performed two simulations of evacuations and learned that robots could be helpful as long as at least 30% of evacuees trusted their guidance instructions. We then developed several methods for a robot to communicate directional information to evacuees. After performing three rounds of evaluation using virtually, remotely and physically present robots, we concluded that robots should communicate directional information by gesturing with two arms. Next, we studied the effect of situational risk and the robot's previous performance on a participant's decision to use the robot during an interaction. We found that higher risk scenarios caused participants to align their self-reported trust with their decisions in a trust situation. We also discovered that trust in a robot drops after a single error when interaction occurs in a virtual environment. After an exploratory study in trust repair, we have learned that a robot can repair broken trust during the emergency by apologizing for its prior mistake or giving additional information relevant to the situation. Apologizing immediately after the error had no effect. Robots have the potential to save lives in emergency scenarios, but could have an equally disastrous effect if participants overtrust them. To explore this concept, we created a virtual environment of an office as well as a real-world simulation of an emergency evacuation. In both, participants interacted with a robot during a non-emergency phase to experience its behavior and then chose whether to follow the robot’s instructions during an emergency phase or not. In the virtual environment, the emergency was communicated through text, but in the real-world simulation, artificial smoke and fire alarms were used to increase the urgency of the situation. In our virtual environment, we confirmed our previous results that prior robot behavior affected whether participants would trust the robot or not. To our surprise, all participants followed the robot in the real-world simulation of an emergency, despite half observing the same robot perform poorly in a navigation guidance task just minutes before. We performed additional exploratory studies investigating different failure modes. Even when the robot pointed to a dark room with no discernible exit the majority of people did not choose to exit the way they entered. The conclusions of this dissertation are based on the results of fifteen experiments with a total of 2,168 participants (2,071 participants in virtual or remote studies conducted over the internet and 97 participants in physical studies on campus). We have found that most human evacuees will trust an emergency guidance robot that uses understandable information conveyance modalities and exhibits efficient guidance behavior in an evacuation scenario. In interactions with a virtual robot, this trust can be lost because of a single error made by the robot, but a similar effect was not found with real-world robots. This dissertation presents data indicating that victims in emergency situations may overtrust a robot, even when they have recently witnessed the robot malfunction. This work thus demonstrates concerns which are important to both the HRI and rescue robot communities.
Spatio-temporal multi-robot routing

(Georgia Institute of Technology, 2015-04-02) Chopra, Smriti

We analyze spatio-temporal routing under various constraints specific to multi-robot applications. Spatio-temporal routing requires multiple robots to visit spatial locations at specified time instants, while optimizing certain criteria like the total distance traveled, or the total energy consumed. Such a spatio-temporal concept is intuitively demonstrable through music (e.g. a musician routes multiple fingers to play a series of notes on an instrument at specified time instants). As such, we showcase much of our work on routing through this medium. Particular to robotic applications, we analyze constraints like maximum velocities that the robots cannot exceed, and information-exchange networks that must remain connected. Furthermore, we consider a notion of heterogeneity where robots and spatial locations are associated with multiple skills, and a robot can visit a location only if it has at least one skill in common with the skill set of that location. To extend the scope of our work, we analyze spatio-temporal routing in the context of a distributed framework, and a dynamic environment.
Characterizing and facilitating human interactions with swarms of mobile robots

(Georgia Institute of Technology, 2015-02-20) De la Croix, Jean-Pierre

Since humans and robots often share workspaces and interact with each other to complete tasks cooperatively, as is the case, for example, in automated warehouses and assembly lines, much of the focus has been centered on supporting human interactions with one or a few robots. As the number of robots involved in a task grows large, scalable abstractions are needed to support interactions with larger numbers of robots. Consequently, there has been a growing effort to understand human-swarm interactions (HSIs) and devise abstractions that are amenable to having humans interact with swarms of robots easily and effectively. In this dissertation, we investigate what it means to impose a control structure on a swarm of robots for the purpose of supporting a specific HSI, when such a control structure is suitable for allowing a user to solve a particular task with a swarm of robots, how one can evaluate attention and effort required to interact with a swarm of robots through a particular control structure, how well attention and effort scale as the number of robots in the swarm increases, why some swarms of robots are easier to interact with than others under the same type of control structure, how to select an appropriate swarm size, and how to design new input controllers for interacting with swarm of mobile robots. Consequently, this dissertation provides a comprehensive framework for characterizing, understanding, and designing the control structures of new abstractions that will be amenable to humans interacting with swarms of networked mobile robots, as well as, a number of examples of such old and new abstractions investigated under this framework.
Graceful connections in dynamical systems – an approach to gait transitions in robotics

(Georgia Institute of Technology, 2014-12-12) Memon, Abdul Basit

Gaits have become an integral part of the design method of robots heading to complex terrains. But research into optimal ways to transition between different gaits is still lacking, and is the primary motivation behind this research. An essential characteristic of gaits is periodicity, and considering that a novel notion of graceful transition is proposed: a graceful transition is one that has maximally persisting periodicity. This particular notion of persistence in the characteristic behavior can be generalized. Therefore, a comprehensive framework for the general problem of connecting any two trajectories of a dynamical system, with an underlying characteristic behavior, over a finite time interval and in a manner that the behavior persists maximally during the transition, is developed and presented. This transition is called the Gluskabi Raccordation, and the characteristic behavior is defined by a kernel representation. Along with establishing this framework, the kernel representations for some interesting characteristic behaviors are also identified. The problem of finding the Gluskabi Raccordations is then solved for different combinations of characteristic behaviors and dynamical systems, and compact widely applicable results are obtained. Lastly, the problem of finding graceful gait transitions is treated within this newly established broader framework, and these graceful gait transitions are obtained for the case of a two-piece worm model.
Using multiple agents in uncertainty minimization of ablating target sources

(Georgia Institute of Technology, 2014-09-05) Coogle, Richard A.

The objective of this research effort is to provide an efficient methodology for a multi-agent robotic system to observe moving targets that are generated from an ablation process. An ablation process is a process where a larger mass is reduced in volume as a result of erosion; this erosion results in smaller, independent masses. An example of such a process is the natural process that gives rise to icebergs, which are generated through an ablation process referred to as ice calving. Ships that operate in polar regions continue to face the threat of floating ice sheets and icebergs generated from the ice ablation process. Although systems have been implemented to track these threats with varying degrees of success, many of these techniques require that the operations are conducted outside of some boundary where the icebergs are known not to drift. Since instances where polar operations must be conducted within such a boundary line do exist (e.g., resource exploration), methods for situational awareness of icebergs for these operations are necessary. In this research, efficacy of these methods is correlated to the initial acquisition time of observing newly ablated targets, as it provides for the ability to enact early countermeasures. To address the research objective, the iceberg tracking problem is defined such that it is re-cast within a class of robotic, multiagent target-observation problems. From this new definition, the primary contributions of this research are obtained: 1) A definition of the iceberg observation problem that extends an existing robotic observation problem to the requirements for the observation of floating ice masses; 2) A method for modeling the activity regions on an ablating source to extract ideal search regions to quickly acquire newly ablated targets; 3) A method for extracting metrics for this model that can be used to assess performance of observation algorithms and perform resource allocation. A robot controller is developed that implements the algorithms that result from these contributions and comparisons are made to existing target acquisition techniques.
Characterization of lymphatic pump function in response to mechanical loading

(Georgia Institute of Technology, 2014-04-28) Kornuta, Jeffrey Alan

The lymphatic system is crucial for normal physiologic function, performing such basic functions as maintaining tissue fluid balance, trafficking immune cells, draining interstitial proteins, as well as transporting fat from the intestine to the blood. To perform these functions properly, downstream vessels (known as collecting lymphatics) actively pump like the heart to dynamically propel lymph from the interstitial spaces of the body to the blood vasculature. However, despite the fact that lymphatics are so important, there exists very little knowledge regarding the details of this active pumping. Specifically, it is known that external mechanical loading such as fluid shear stress and circumferential stress due to transmural pressure affect pumping response; however, anything other than simple, static relationships remain unknown. Because mechanical environment has been implicated in lymphatic diseases such as lymphedema, understanding these dynamic relationships between lymphatic pumping and mechanical loading during normal function are crucial to grasp before these pathologies can be unraveled. For this reason, this thesis describes several tools developed to study lymphatic function in response to the unique mechanical loads these vessels experience both in vitro and ex vivo. Moreover, this work investigates how shear stress sensitivity is affected by transmural pressure and how the presence of dynamic shear independently affects lymphatic contractile function.
Robot learners: interactive instance-based learning with social robots

(Georgia Institute of Technology, 2014-04-11) Park, Hae Won

On one hand, academic and industrial researchers have been developing and deploying robots that are used as educational tutors, mediators, and motivational tools. On the other hand, an increasing amount of interest has been placed on non-expert users being able to program robots intuitively, which has led to promising research efforts in the fields of machine learning and human-robot interaction. This dissertation focuses on bridging the gap between the two subfields of robotics to provide personalized experience for the users during educational, entertainment, and therapeutic sessions with social robots. In order to make the interaction continuously engaging, the workspace shared between the user and the robot should provide personalized contexts for interaction while the robot learns to participate in new tasks that arise. This dissertation aims to solve the task-learning problem using an instance-based framework that stores human demonstrations as task instances. These instances are retrieved when confronted with a similar task in which the system generates predictions of task behaviors based on prior solutions. The main issues associated with the instance-based approach, i.e., knowledge encoding and acquisition, are addressed in this dissertation research using interactive methods of machine learning. This approach, further referred to as interactive instance-based learning (IIBL), utilizes the keywords people use to convey task knowledge to others to formulate task instances. The key features suggested by the human teacher are extracted during the demonstrations of the task. Regression approaches have been developed in this dissertation to model similarities between cases for instance retrieval including multivariate linear regression and sensitivity analysis using neural networks. The learning performance of the IIBL methods were then evaluated while participants engaged in various block stacking and inserting scenarios and tasks on a touchscreen tablet with a humanoid robot Darwin. In regard to end-users programming robots, the main benefit of the IIBL framework is that the approach fully utilizes the explanatory behavior of the instance-based method which makes the learning process transparent to the human teacher. Such an environment not only encourages the user to produce better demonstrations, but also prompts the user to intervene at the moment a new instance is needed. It was shown through user studies that participants naturally adapt their teaching behavior to the robot learner's progress and adjust the timing and the number of demonstrations. It was also observed that the human-robot teaching and learning scenarios facilitate the emergence of various social behaviors from participants. Encouraging social interaction is often an objective of the task especially with children with cognitive disabilities, and a pilot study with children with autism spectrum disorder revealed promising results comparable to the typically developing group. Finally, this dissertation investigated the necessity of renewable context for prolonged interaction with robot companions. Providing personalized tasks that match each individual's preferences and developmental stages enhances the quality of the user experience with robot learners. Confronted with the limitations of the physical workspace, this research proposes utilizing commercially available touchscreen smart devices as a shared platform for engaging the user in educational, entertainment, and therapeutic tasks with the robot learners. To summarize, this dissertation attempts to defend the thesis statement that a robot learner that utilizes an IIBL approach improves the performance and efficiency of general task learning, and when combined with the state-of-the-art mobile technology that provides personalized context for interaction, enhances the user's experience for prolonged engagement of the task.