As robots become more prevalent in our everyday lives, both in our workplaces and in our homes, it becomes increasingly likely that people who are not experts in robotics will be asked to interface with robotic devices. It is therefore important to develop robotic controls that are intuitive and easy for novices to use. Robotic hands, in particular, are very useful, but their high dimensionality makes creating intuitive human-machine interfaces for them complex. In this dissertation, we study the control of non-anthropomorphic robotic hands by non-roboticists in two contexts: collaborative manipulation and assistive robotics. In the field of collaborative manipulation, the human and the robot work side by side as independent agents. Teleoperation allows the human to assist the robot when autonomous grasping is not able to deal sufficiently well with corner cases or cannot operate fast enough. Using the teleoperator’s hand as an input device can provide an intuitive control method, but finding a mapping between a human hand and a non-anthropomorphic robot hand can be difficult, due to the hands’ dissimilar kinematics. In this dissertation, we seek to create a mapping between the human hand and a fully actuated, non-anthropomorphic robot hand that is intuitive enough to enable effective real-time teleoperation, even for novice users. We propose a low-dimensional and continuous teleoperation subspace which can be used as an intermediary for mapping between different hand pose spaces. We first propose the general concept of the subspace, its properties and the variables needed to map from the human hand to a robot hand. We then propose three ways to populate the teleoperation subspace mapping. Two of our mappings use a dataglove to harvest information about the user's hand. We define the mapping between joint space and teleoperation subspace with an empirical definition, which requires a person to define hand motions in an intuitive, hand-specific way, and with an algorithmic definition, which is kinematically independent, and uses objects to define the subspace. Our third mapping for the teleoperation subspace uses forearm electromyography (EMG) as a control input. Assistive orthotics is another area of robotics where human-machine interfaces are critical, since, in this field, the robot is attached to the hand of the human user. In this case, the goal is for the robot to assist the human with movements they would not otherwise be able to achieve. Orthotics can improve the quality of life of people who do not have full use of their hands. Human-machine interfaces for assistive hand orthotics that use EMG signals from the affected forearm as input are intuitive and repeated use can strengthen the muscles of the user's affected arm. In this dissertation, we seek to create an EMG based control for an orthotic device used by people who have had a stroke. We would like our control to enable functional motions when used in conjunction with a orthosis and to be robust to changes in the input signal. We propose a control for a wearable hand orthosis which uses an easy to don, commodity forearm EMG band. We develop an supervised algorithm to detect a user’s intent to open and close their hand, and pair this algorithm with a training protocol which makes our intent detection robust to changes in the input signal. We show that this algorithm, when used in conjunction with an orthosis over several weeks, can improve distal function in users. Additionally, we propose two semi-supervised intent detection algorithms designed to keep our control robust to changes in the input data while reducing the length and frequency of our training protocol.

Artificial Intelligence (AI) promises to deeply alter the structure of organizations and work. This dissertation explores how firms and their human workers interact with the diffusion of automation and related technologies in the workplace, and how this informs our general understanding of organizations. I use three experiments to examine the consequences and implications of human-machine interaction in organizations. Chapter 1 studies the introduction of AI agents and human new hires into "laboratory firms" as they engage in a coordination-based game. Chapter 2 focuses on the sources of AI bias and offers practical solutions managers can adopt to limit bias. Finally, Chapter 3 studies how organizations can enjoy the benefits of AI and ensure that human collaborators remain engaged and exert effort. Overall, my dissertation develops an organizational and team perspective on the impact of workplace automation. Successful human/AI collaboration requires going beyond the technical capabilities of AI and developing a human-centered approach that incorporates firm strategies, behavioral responses, and managerial choices.

Decision making in a parallel human/computer system is considered. In this type of system, those tasks for which the computer identical to has the decision making responsibility tasks for which the human are has responsibility. For optimal system performance, it is crucial that the human and computer avoid redundant actions. The traditional method of avoiding redundancies is to have the human engage in an. explicit dialogue with the computer. This method adds an additional task for the human. An alternative method which does not increase workload is to provide the computer with a model of human decision making. If this model is accurate, the computer could predict the actions of the human and avoid those actions which are redundant. The mathematical development of such a predictive model is presented. The model suggested has two stages. The first stage uses discriminant analysis to describe human event detection behavior. The output from the first stage of the model is a vector of "event detected" probabilities, each entry in the vector representing a different system task. The second stage of the model uses dynamic programming to determine the optimal action at a specific point in time. The output from this stage of the model is the appropriate action for the human to take. Two experiments were presented to validate the first and second stage of the model, respectively. The experimental situation depicted a sheet metal plant in which the subjects were to monitor machines for failures. The first stage of the model predicted over 80% of the actions correctly, while the entire model predicted nearly 85% correctly. In the third experiment, the computer was implemented as a parallel decision maker. A significant improvement in performance was observed when the computer based decisions on a model of human decision making vs. when the model was ignored. A modeling approach is suggested as a reasonable alternative to explicit human/computer systems. communication in the design of Further research is suggested to determine the situations in which model based communication would be preferable to dialogue based communication. / Ph. D.

Little research effort has been devoted to human interaction with telephone information systems. This study investigated the effects of system parameters and user characteristics on human behavior in an interactive telephone-based information system. The research method utilized a centraI-composite design to study four variables at five levels each. The four factors manipulated were: synthesized speech rate, time available for user input, subject age, and background music level. Subjects searched a fictitious department store database for 16 specific store items and transcribed 16 information messages which were spoken by a computer speech synthesizer. Subjective ratings of certain features of the system were solicited from the subjects and performance measures were also collected from the subjects on an on-line basis. Performance was evaluated by calculating regression equations relating the dependent measures and the independent variables. A response surface was plotted, and optimal settings for the Information system were also calculated. Two seconds was found to be an optimal time for users to enter their selection. The computer synthesized speech rate should be set close to 120-150 words per minute. Background music or noise level should be kept below 50 dB(A); sound level above 50 dB(A) seriously affected user's ability to understand synthetic speech. Younger subjects (age 14 - 22) performed better in this study than older subjects (age 36- 62). / Master of Science / incomplete_metadata

This study examined the effects of five dichotomous variables on human performance using a computer-based telephone information system. The five variables were: speech rate (120 or 240 words per minute), length of input time-out (two or ten seconds), feedback (available or not available), wallet guide - a graphical representation of the information (available or not available), and the database structure (8x2 or 2x6). The research methodology implemented a one-half fraction of a 2⁵ factorial design, requiring only 16 of the 32 possible treatment combinations. Two tasks were included in this study: a search task and a transcription task. The search task consisted of each subject accessing an information system through a touch-tone telephone. The subject listened to the computer as it used synthesized speech to list available menu options. The search task continued until the subject found the target item. The transcription task consisted of listening to and typing an information message for each target item. The experiment ended when 16 target items were found. Four dependent measures were used to evaluate user performance. The search task was evaluated with three measures: user added time (the amount of additional time the subject required to complete the search in excess of the minimum search time imposed by the system design); invalid key presses (the number of times undefined keys on the touch tone telephone were pressed during the search); and user added key presses (the number of additional, valid key presses the subject required to complete the search in excess of the minimum number of key presses required to complete the search). Only one measure was used to evaluate user performance of the transcription task: transcription accuracy score (the number of words that each subject transcribed correctly). The results show four of the five variables (speech rate, database structure, input time-out, and wallet guide) to have a significant effect on human performance. The following interactions were found to have a significant effect on at least one of the dependent measures: database structure by input timeout, database structure by wallet guide, input timeout by wallet guide, and speech rate by wallet guide. Twelve subjective ratings were also analyzed. The results show at least one of the 12 subjective ratings was significantly affected by speech rate, input time-out, or the database structure. Perhaps the most important finding of this research is that complicated auditory information structures can be accessed easily if a wallet guide is provided. In addition to decreasing search time, a wallet guide reduces the number of search errors users make. / Master of Science

Thesis: B.S., Massachusetts Institute of Technology, Department of Mechanical Engineering, 1981 / Lacks leaf 38. / by Eric Brian Shain. / B.S. / B.S. Massachusetts Institute of Technology, Department of Mechanical Engineering

The work presented in this thesis provides new perspectives and approaches for problems that arise in the analysis of neural data. Particular emphasis is placed on parameter fitting and automated analysis problems that would arise naturally in closed-loop experiments. Part one focuses on two brain-computer interface problems. First, we provide a framework for understanding co-adaptation, the setting in which decoder updating and user learning occur simultaneously. We also provide a new perspective on intention-based parameter fitting and tools to extend this approach to higher dimensional decoders. Part two focuses on event inference, which refers to the decomposition of observed timeseries data into interpretable events. We present application of event inference methods on voltage-clamp recordings as well as calcium imaging, and describe extensions to allow for combining data across modalities or trials.

Haptic devices allow a human to interact physically with a remote or virtual environment by providing tactile feedback to the user. In general haptic devices can be classified in two groups according to the energetic nature of their actuators. Devices using electric motors, pneumatic or hydraulic cylinders or other similar actuators that can add energy to the system are considered "active." Devices using brakes, clutches or other passive actuators are considered "passive" haptic devices. The research presented here focuses on the use of passive haptic devices used during teleoperation, the remote control of a "slave" device by the haptic "master" device. An actuation scheme as well as three different control methods is developed for providing the user with haptic feedback. As a final step, the effectiveness of the controllers is compared to that of a commercially available active haptic device. Twenty subjects provide data that shows the usefulness of the passive device in three typical teleoperation tasks.

Thesis (Ph.D)--Industrial and Systems Engineering, Georgia Institute of Technology, 2010. / Committee Chair: Kemp, Charles; Committee Member: Glass, Jonathan; Committee Member: Griffin, Paul; Committee Member: Howard, Ayanna; Committee Member: Thomaz, Andrea. Part of the SMARTech Electronic Thesis and Dissertation Collection.

The ways people express their opinions and sentiments have radically changed in the past few years thanks to the advent of social networks, web communities, blogs, wikis and other online collaborative media. The distillation of knowledge from this huge amount of unstructured information can be a key factor for marketers who want to create an image or identity in the minds of their customers for their product, brand, or organisation. These online social data, however, remain hardly accessible to computers, as they are specifically meant for human consumption. The automatic analysis of online opinions, in fact, involves a deep understanding of natural language text by machines, from which we are still very far. Hitherto, online information retrieval has been mainly based on algorithms relying on the textual representation of web-pages. Such algorithms are very good at retrieving texts, splitting them into parts, checking the spelling and counting their words. But when it comes to interpreting sentences and extracting meaningful information, their capabilities are known to be very limited. Existing approaches to opinion mining and sentiment analysis, in particular, can be grouped into three main categories: keyword spotting, in which text is classified into categories based on the presence of fairly unambiguous affect words; lexical affinity, which assigns arbitrary words a probabilistic affinity for a particular emotion; statistical methods, which calculate the valence of affective keywords and word co-occurrence frequencies on the base of a large training corpus. Early works aimed to classify entire documents as containing overall positive or negative polarity, or rating scores of reviews. Such systems were mainly based on supervised approaches relying on manually labelled samples, such as movie or product reviews where the opinionist’s overall positive or negative attitude was explicitly indicated. However, opinions and sentiments do not occur only at document level, nor they are limited to a single valence or target. Contrary or complementary attitudes toward the same topic or multiple topics can be present across the span of a document. In more recent works, text analysis granularity has been taken down to segment and sentence level, e.g., by using presence of opinion-bearing lexical items (single words or n-grams) to detect subjective sentences, or by exploiting association rule mining for a feature-based analysis of product reviews. These approaches, however, are still far from being able to infer the cognitive and affective information associated with natural language as they mainly rely on knowledge bases that are still too limited to efficiently process text at sentence level. In this thesis, common sense computing techniques are further developed and applied to bridge the semantic gap between word-level natural language data and the concept-level opinions conveyed by these. In particular, the ensemble application of graph mining and multi-dimensionality reduction techniques on two common sense knowledge bases was exploited to develop a novel intelligent engine for open-domain opinion mining and sentiment analysis. The proposed approach, termed sentic computing, performs a clause-level semantic analysis of text, which allows the inference of both the conceptual and emotional information associated with natural language opinions and, hence, a more efficient passage from (unstructured) textual information to (structured) machine-processable data. The engine was tested on three different resources, namely a Twitter hashtag repository, a LiveJournal database and a PatientOpinion dataset, and its performance compared both with results obtained using standard sentiment analysis techniques and using different state-of-the-art knowledge bases such as Princeton’s WordNet, MIT’s ConceptNet and Microsoft’s Probase. Differently from most currently available opinion mining services, the developed engine does not base its analysis on a limited set of affect words and their co-occurrence frequencies, but rather on common sense concepts and the cognitive and affective valence conveyed by these. This allows the engine to be domain-independent and, hence, to be embedded in any opinion mining system for the development of intelligent applications in multiple fields such as Social Web, HCI and e-health. Looking ahead, the combined novel use of different knowledge bases and of common sense reasoning techniques for opinion mining proposed in this work, will, eventually, pave the way for development of more bio-inspired approaches to the design of natural language processing systems capable of handling knowledge, retrieving it when necessary, making analogies and learning from experience.