Perturbation Training for Human-robot Teams PDF Download
Are you looking for read ebook online? Search for your book and save it on your Kindle device, PC, phones or tablets. Download Perturbation Training for Human-robot Teams PDF full book. Access full book title Perturbation Training for Human-robot Teams by Ramya Ramakrishnan. Download full books in PDF and EPUB format.
Author: Ramya Ramakrishnan Publisher: ISBN: Category : Languages : en Pages : 67
Book Description
Today, robots are often deployed to work separately from people. Combining the strengths of humans and robots, however, can potentially lead to a stronger joint team. To have fluid human-robot collaboration, these teams must train to achieve high team performance and flexibility on new tasks. This requires a computational model that supports the human in learning and adapting to new situations. In this work, we design and evaluate a computational learning model that enables a human-robot team to co-develop joint strategies for performing novel tasks requiring coordination. The joint strategies are learned through "perturbation training," a human team-training strategy that requires practicing variations of a given task to help the team generalize to new variants of that task. Our Adaptive Perturbation Training (AdaPT) algorithm is a hybrid of transfer learning and reinforcement learning techniques and extends the Policy Reuse in Q-Learning (PRQL) algorithm to learn more quickly in new task variants. We empirically validate this advantage of AdaPT over PRQL through computational simulations. We then augment our algorithm AdaPT with a co-learning framework and a computational bi-directional communication protocol so that the robot can work with a person in live interactions. These three features constitute our human-robot perturbation training model. We conducted human subject experiments to show proof-of-concept that our model enables a robot to draw from its library of prior experiences in a way that leads to high team performance. We compare our algorithm with a standard reinforcement learning algorithm Q-learning and find that AdaPT-trained teams achieved significantly higher reward on novel test tasks than Q-learning teams. This indicates that the robot's algorithm, rather than just the human's experience of perturbations, is key to achieving high team performance. We also show that our algorithm does not sacrifice performance on the base task after training on perturbations. Finally, we demonstrate that human-robot training in a simulation environment using AdaPT produced effective team performance with an embodied robot partner.
Author: Ramya Ramakrishnan Publisher: ISBN: Category : Languages : en Pages : 67
Book Description
Today, robots are often deployed to work separately from people. Combining the strengths of humans and robots, however, can potentially lead to a stronger joint team. To have fluid human-robot collaboration, these teams must train to achieve high team performance and flexibility on new tasks. This requires a computational model that supports the human in learning and adapting to new situations. In this work, we design and evaluate a computational learning model that enables a human-robot team to co-develop joint strategies for performing novel tasks requiring coordination. The joint strategies are learned through "perturbation training," a human team-training strategy that requires practicing variations of a given task to help the team generalize to new variants of that task. Our Adaptive Perturbation Training (AdaPT) algorithm is a hybrid of transfer learning and reinforcement learning techniques and extends the Policy Reuse in Q-Learning (PRQL) algorithm to learn more quickly in new task variants. We empirically validate this advantage of AdaPT over PRQL through computational simulations. We then augment our algorithm AdaPT with a co-learning framework and a computational bi-directional communication protocol so that the robot can work with a person in live interactions. These three features constitute our human-robot perturbation training model. We conducted human subject experiments to show proof-of-concept that our model enables a robot to draw from its library of prior experiences in a way that leads to high team performance. We compare our algorithm with a standard reinforcement learning algorithm Q-learning and find that AdaPT-trained teams achieved significantly higher reward on novel test tasks than Q-learning teams. This indicates that the robot's algorithm, rather than just the human's experience of perturbations, is key to achieving high team performance. We also show that our algorithm does not sacrifice performance on the base task after training on perturbations. Finally, we demonstrate that human-robot training in a simulation environment using AdaPT produced effective team performance with an embodied robot partner.
Author: Kevin A. Gluck Publisher: MIT Press ISBN: 0262349434 Category : Computers Languages : en Pages : 355
Book Description
Experts from a range of disciplines explore how humans and artificial agents can quickly learn completely new tasks through natural interactions with each other. Humans are not limited to a fixed set of innate or preprogrammed tasks. We learn quickly through language and other forms of natural interaction, and we improve our performance and teach others what we have learned. Understanding the mechanisms that underlie the acquisition of new tasks through natural interaction is an ongoing challenge. Advances in artificial intelligence, cognitive science, and robotics are leading us to future systems with human-like capabilities. A huge gap exists, however, between the highly specialized niche capabilities of current machine learning systems and the generality, flexibility, and in situ robustness of human instruction and learning. Drawing on expertise from multiple disciplines, this Strüngmann Forum Report explores how humans and artificial agents can quickly learn completely new tasks through natural interactions with each other. The contributors consider functional knowledge requirements, the ontology of interactive task learning, and the representation of task knowledge at multiple levels of abstraction. They explore natural forms of interactions among humans as well as the use of interaction to teach robots and software agents new tasks in complex, dynamic environments. They discuss research challenges and opportunities, including ethical considerations, and make proposals to further understanding of interactive task learning and create new capabilities in assistive robotics, healthcare, education, training, and gaming. Contributors Tony Belpaeme, Katrien Beuls, Maya Cakmak, Joyce Y. Chai, Franklin Chang, Ropafadzo Denga, Marc Destefano, Mark d'Inverno, Kenneth D. Forbus, Simon Garrod, Kevin A. Gluck, Wayne D. Gray, James Kirk, Kenneth R. Koedinger, Parisa Kordjamshidi, John E. Laird, Christian Lebiere, Stephen C. Levinson, Elena Lieven, John K. Lindstedt, Aaron Mininger, Tom Mitchell, Shiwali Mohan, Ana Paiva, Katerina Pastra, Peter Pirolli, Roussell Rahman, Charles Rich, Katharina J. Rohlfing, Paul S. Rosenbloom, Nele Russwinkel, Dario D. Salvucci, Matthew-Donald D. Sangster, Matthias Scheutz, Julie A. Shah, Candace L. Sidner, Catherine Sibert, Michael Spranger, Luc Steels, Suzanne Stevenson, Terrence C. Stewart, Arthur Still, Andrea Stocco, Niels Taatgen, Andrea L. Thomaz, J. Gregory Trafton, Han L. J. van der Maas, Paul Van Eecke, Kurt VanLehn, Anna-Lisa Vollmer, Janet Wiles, Robert E. Wray III, Matthew Yee-King
Author: Laura Major Publisher: Basic Books ISBN: 1541699106 Category : Technology & Engineering Languages : en Pages : 304
Book Description
The next generation of robots will be truly social, but can we make sure that they play well in the sandbox? Most robots are just tools. They do limited sets of tasks subject to constant human control. But a new type of robot is coming. These machines will operate on their own in busy, unpredictable public spaces. They'll ferry deliveries, manage emergency rooms, even grocery shop. Such systems could be truly collaborative, accomplishing tasks we don't do well without our having to stop and direct them. This makes them social entities, so, as robot designers Laura Major and Julie Shah argue, whether they make our lives better or worse is a matter of whether they know how to behave. What to Expect When You're Expecting Robots offers a vision for how robots can survive in the real world and how they will change our relationship to technology. From teaching them manners, to robot-proofing public spaces, to planning for their mistakes, this book answers every question you didn't know you needed to ask about the robots on the way.
Author: Ronald L. Boring Publisher: Springer ISBN: 331994391X Category : Technology & Engineering Languages : en Pages : 335
Book Description
This book brings together studies broadly addressing human error from different disciplines and perspectives. It discusses topics such as human performance; human variability and reliability analysis; medical, driver and pilot error, as well as automation error; root cause analyses; and the cognitive modeling of human error. In addition, it highlights cutting-edge applications in safety management, defense, security, transportation, process controls, and medicine, as well as more traditional fields of application. Based on the AHFE 2018 International Conference on Human Error, Reliability, Resilience, and Performance, held on July 21–25, 2018, in Orlando, Florida, USA, the book includes experimental papers, original reviews, and reports on case studies, as well as meta-analyses, technical guidelines, best practice and methodological papers. It offers a timely reference guide for researchers and practitioners dealing with human error in a diverse range of fields.
Author: Brian Christian Publisher: W. W. Norton & Company ISBN: 039363583X Category : Science Languages : en Pages : 459
Book Description
A jaw-dropping exploration of everything that goes wrong when we build AI systems and the movement to fix them. Today’s “machine-learning” systems, trained by data, are so effective that we’ve invited them to see and hear for us—and to make decisions on our behalf. But alarm bells are ringing. Recent years have seen an eruption of concern as the field of machine learning advances. When the systems we attempt to teach will not, in the end, do what we want or what we expect, ethical and potentially existential risks emerge. Researchers call this the alignment problem. Systems cull résumés until, years later, we discover that they have inherent gender biases. Algorithms decide bail and parole—and appear to assess Black and White defendants differently. We can no longer assume that our mortgage application, or even our medical tests, will be seen by human eyes. And as autonomous vehicles share our streets, we are increasingly putting our lives in their hands. The mathematical and computational models driving these changes range in complexity from something that can fit on a spreadsheet to a complex system that might credibly be called “artificial intelligence.” They are steadily replacing both human judgment and explicitly programmed software. In best-selling author Brian Christian’s riveting account, we meet the alignment problem’s “first-responders,” and learn their ambitious plan to solve it before our hands are completely off the wheel. In a masterful blend of history and on-the ground reporting, Christian traces the explosive growth in the field of machine learning and surveys its current, sprawling frontier. Readers encounter a discipline finding its legs amid exhilarating and sometimes terrifying progress. Whether they—and we—succeed or fail in solving the alignment problem will be a defining human story. The Alignment Problem offers an unflinching reckoning with humanity’s biases and blind spots, our own unstated assumptions and often contradictory goals. A dazzlingly interdisciplinary work, it takes a hard look not only at our technology but at our culture—and finds a story by turns harrowing and hopeful.
Author: Stefanos Z. Nikolaidis Publisher: ISBN: Category : Languages : en Pages : 79
Book Description
This thesis is focused on designing mechanisms for programming robots and training people to perform human-robot collaborative tasks, drawing upon insights from practices widely used in human teams. First, we design and evaluate human-robot cross-training, a strategy used and validated for effective human team training. Cross-training is an interactive planning method in which a human and a robot iteratively switch roles to learn a shared plan for a collaborative task. We present a computational formulation of the robot mental model, which encodes the sequence of robot actions towards task completion and the robot expectation over the preferred human actions, and show that it is quantitatively comparable to the human mental model that captures the interrole knowledge held by the human. Additionally, we propose a quantitative measure of human-robot mental model convergence, and an objective metric of mental model similarity. Based on this encoding, we formulate human-robot cross-training and evaluate it in human subject experiments (n = 36). We compare human-robot cross-training to standard reinforcement learning techniques, and show that cross-training provides statistically significant improvements in quantitative team performance measures. Additionally, significant differences emerge in the perceived robot performance and human trust. Finally, we discuss the objective measure of human-robot mental model convergence as a method to dynamically assess errors in human actions. This study supports the hypothesis that effective and fluent human-robot teaming may be best achieved by modeling effective practices for human teamwork. We also investigate the robustness of the learned policies to randomness in human behavior. We show that the learned policies are not robust to changes in the human behavior after the training phase. For this reason, we introduce a new framework that enables a robot to learn a robust policy to perform a collaborative task with a human.The human preference is modeled as a hidden variable in a Mixed Observability Markov Decision Process, which is inferred from joint-action demonstrations of a collaborative task. The framework automatically learns a user model from training data, and uses this model to plan an execution policy that is robust to changes in the human teammate's behavior. We compare the effectiveness of the proposed framework to previous techniques that plan in state-space, using data from the human subject experiments in which human and robot teams trained together to perform a place-and-drill task. Results demonstrate the robustness of the learned policy to increasing deviations in human behavior.
Author: Florian Jentsch Publisher: CRC Press ISBN: 1317119479 Category : Computers Languages : en Pages : 467
Book Description
Soldier-robot teams will be an important component of future battle spaces, creating a complex but potentially more survivable and effective combat force. The complexity of the battlefield of the future presents its own problems. The variety of robotic systems and the almost infinite number of possible military missions create a dilemma for researchers who wish to predict human-robot interactions (HRI) performance in future environments. Human-Robot Interactions in Future Military Operations provides an opportunity for scientists investigating military issues related to HRI to present their results cohesively within a single volume. The issues range from operators interacting with small ground robots and aerial vehicles to supervising large, near-autonomous vehicles capable of intelligent battlefield behaviors. The ability of the human to 'team' with intelligent unmanned systems in such environments is the focus of the volume. As such, chapters are written by recognized leaders within their disciplines and they discuss their research in the context of a broad-based approach. Therefore the book allows researchers from differing disciplines to be brought up to date on both theoretical and methodological issues surrounding human-robot interaction in military environments. The overall objective of this volume is to illuminate the challenges and potential solutions for military HRI through discussion of the many approaches that have been utilized in order to converge on a better understanding of this relatively complex concept. It should be noted that many of these issues will generalize to civilian applications as robotic technology matures. An important outcome is the focus on developing general human-robot teaming principles and guidelines to help both the human factors design and training community develop a better understanding of this nascent but revolutionary technology. Much of the research within the book is based on the Human Research and Engineering Directorate (HRED), U.S. Army Research Laboratory (ARL) 5-year Army Technology Objective (ATO) research program. The program addressed HRI and teaming for both aerial and ground robotic assets in conjunction with the U.S. Army Tank and Automotive Research and Development Center (TARDEC) and the Aviation and Missile Development Center (AMRDEC) The purpose of the program was to understand HRI issues in order to develop and evaluate technologies to improve HRI battlefield performance for Future Combat Systems (FCS). The work within this volume goes beyond the research results to encapsulate the ATO's findings and discuss them in a broader context in order to understand both their military and civilian implications. For this reason, scientists conducting related research have contributed additional chapters to widen the scope of the original research boundaries.
Author: Luefeng Chen Publisher: Springer Nature ISBN: 3030615774 Category : Technology & Engineering Languages : en Pages : 252
Book Description
This book focuses on the key technologies and scientific problems involved in emotional robot systems, such as multimodal emotion recognition (i.e., facial expression/speech/gesture and their multimodal emotion recognition) and emotion intention understanding, and presents the design and application examples of emotional HRI systems. Aiming at the development needs of emotional robots and emotional human–robot interaction (HRI) systems, this book introduces basic concepts, system architecture, and system functions of affective computing and emotional robot systems. With the professionalism of this book, it serves as a useful reference for engineers in affective computing, and graduate students interested in emotion recognition and intention understanding. This book offers the latest approaches to this active research area. It provides readers with the state-of-the-art methods of multimodal emotion recognition, intention understanding, and application examples of emotional HRI systems.
Author: Indranil Sur Publisher: ISBN: Category : Autonomous robots Languages : en Pages : 43
Book Description
To ensure system integrity, robots need to proactively avoid any unwanted physical perturbation that may cause damage to the underlying hardware. In this thesis work, we investigate a machine learning approach that allows robots to anticipate impending physical perturbations from perceptual cues. In contrast to other approaches that require knowledge about sources of perturbation to be encoded before deployment, our method is based on experiential learning. Robots learn to associate visual cues with subsequent physical perturbations and contacts. In turn, these extracted visual cues are then used to predict potential future perturbations acting on the robot. To this end, we introduce a novel deep network architecture which combines multiple sub-networks for dealing with robot dynamics and perceptual input from the environment. We present a self-supervised approach for training the system that does not require any labeling of training data. Extensive experiments in a human-robot interaction task show that a robot can learn to predict physical contact by a human interaction partner without any prior information or labeling. Furthermore, the network is able to successfully predict physical contact from either depth stream input or traditional video input or using both modalities as input.
Author: Ramya Ramakrishnan
Author: Ramya Ramakrishnan
Author: Kevin A. Gluck
Author: Laura Major
Author: Ronald L. Boring
Author: Wafa Johal
Author: Brian Christian
Author: Stefanos Z. Nikolaidis
Author: Florian Jentsch
Author: Luefeng Chen
Author: Indranil Sur