Time filter

Source Type

Deal S.V.,Deal Corporation | Hoffman R.R.,Institute for Human and Machine Cognition
IEEE Intelligent Systems | Year: 2010

This essay focuses on the forces and constraints of procurement versus the goals of human centering, especially the creation of intelligent technologies that are usable, useful, and understandable. The procurement process tends to de-emphasize these goals and focus on adherence to rules and regulations. As a result, software system development processes are misaligned with the challenges faced by development teams. This misalignment between "actual world problems" and normative documentation repeatedly results in failed systems. A real-life practitioner's account illustrates this point by describing how a group of individuals, acting on their own initiative and at their own risk, short-circuited the rules and constraints of the procurement process to turn a procurement process failure into a success. © 2010 IEEE.


Anyone who grew up with "The Jetsons" would agree that Rosie is the perfect robotic maid with her reliable attitude, superb cleaning abilities and wit, so it's no wonder that researchers keep on trying to find ways to construct humanoid robots that have similar functionalities. Rosie may have been an outdated model when she was first introduced but she can give newer robot models a run for their money. "The Jetsons" is set in futuristic 2062 and follows the Jetson family who live in Orbit City. Of course, the entire cartoon show has imagined the future as an era of great technology, with flying cars and a comfortable home life where every chore can be passed on to robotic assistants. Rosie was given the spotlight in the show's pilot and in the eighth episode in 1962. She also made appearances in 1985 and 1987 when the show was picked up for a second and third season. It's easy to see why Rosie became a hit character despite being the only non-organic member of the Jetsons' household because, even if her original purpose is for house chores, her witty comebacks and other antics combined with somewhat expressive "facial" features made her memorable. With only 46 years until the Jetsons' time, the clock is ticking for researchers who plan to build a robot maid like Rosie. There are some honorable mentions that were unveiled but they still pale in comparison to the two-dimensional robot maid. In 2010, the Interaction and Robotics Research Center of the Korea Institute of Science and Technology (KIST) unveiled a bipedal humanoid robot designed to interact with humans through image and voice recognition. Mahru Z has also been given three-dimensional vision to enable it to visually interpret the task at hand and execute it successfully. "It recognizes people, can turn on microwave ovens, washing machines and toasters, and also pick up sandwiches, cups and whatever else it senses as objects," You Bum-Jae, head of the Cognitive Robotics Center at KIST, explained. KIST demonstrated Mahru Z's ability in 2010 when they showed Mahru Z, along with its other metallic friend, Mahru M, preparing and serving coffee and toast. Check out the video demonstration below. Both robots focus on network-based intelligence by using network infrastructure and the main concern of researchers is to improve human-robot interaction. Mahru Z may have successfully served the researcher toast and coffee at his command but, with the time it took before the food reached the table, it's safe to say that Mahru Z is on the slow side and is still a long way off from becoming the future Rosie. The Florida Institute for Human and Machine Cognition is responsible for building Atlas, one of the most advanced humanoid robots to date. Before we get into details, though, check out Atlas doing some recently learned skills: household chores. In the video above, we can see that Atlas has learned how to operate a vacuum cleaner, put aside large items, use a broom to clean up a mess and have a little fun on the job by flying a paper airplane. The robot is definitely closer to Rosie in the cleaning aspect but before you dream of having your own Atlas, you should know that cleaning up is just an added skill programmed recently. Atlas' main objective is actually to be used in emergency and rescue missions and to do tasks in areas where humans cannot possibly go for safety reasons. Atlas was developed with support, funding and oversight from the United States Defense Advanced Research Projects Agency (DARPA). Atlas won second place in the DARPA Robotics Challenge where it completed eight disaster response-related tasks in 50 minutes and 26 seconds. Rosie may be charming and very handy but the idea of having robots taking care of everything in the house may still be a fantasy for now. Sure, people would love to just sit back and relax once they reach home but, no matter how cool the concept of having a robot maid or butler tending to your personal needs is, there is still much to be improved with our current technology to be able to achieve this. For now, we just have to be satisfied with the Roomba.


Hoffman R.R.,Institute for Human and Machine Cognition | Woods D.D.,Ohio State University
IEEE Intelligent Systems | Year: 2011

Macrocognitive work systems are complex adaptive systems designed to support near-continuous interdependencies among humans and intelligent machines to carry out joint cognitive work that includes functions such as sensemaking, replanning, mental projection to the future, and coordination. The effort to identify empirical laws and use them to construct a formal theory led the authors to the identification of fundamental trade-offs that place performance limits on all macrocognitive work systems. This article presents five trade-offs that define these limits. It also illustrates how empirical regularities about the performance of human work systems emerge from the trade-offs. © 2006 IEEE.


News Article | December 2, 2016
Site: www.technologyreview.com

By testing the ground beneath its feet, it can work out how to make its move. Robots have a track record of falling over. But a new technique allows a humanoid robot to feel its way over rough ground better than ever. In a video found by TechCrunch, researchers from the Institute for Human and Machine Cognition Robotics Lab in Pensacola, Florida, show off a new set of control algorithms that allow the Boston Dynamics robot known as Atlas to cross an uneven path of cinder blocks. It looks eerily human-like as it moves its foot to explore the ground in front of it, strides, then corrects itself by swinging its torso and arms. In fact, that’s exactly what it’s been programmed to do. In a paper describing how the technique works, the researchers explain that “the robot explores the new contact surface by attempting to shift the center of pressure around the foot.” Then, an “available foothold is inferred by the way in which the foot rotates about contact edges ... during exploration.” The robot uses that information to work out how it should hold its foot as it takes a step, then it moves and uses upper body angular momentum—including arm waving—to maintain and regain balance. In testing, it’s able to walk over rough surfaces that feature edges or even corners of cinder blocks. The researchers say that their work is “an important step in the effort of making legged robots useful in real-world scenarios.” Of course, like humans, it won’t always get it right. But researchers have already started working out how to ensure that robots fall safely—so when they do take a tumble, it’s shouldn’t fracture their circuit boards.


News Article | December 2, 2016
Site: www.technologyreview.com

By testing the ground beneath its feet, it can work out how to make its move. Robots have a track record of falling over. But a new technique allows a humanoid robot to feel its way over rough ground better than ever. In a video found by TechCrunch, researchers from the Institute for Human and Machine Cognition Robotics Lab in Pensacola, Florida, show off a new set of control algorithms that allow the Boston Dynamics robot known as Atlas to cross an uneven path of cinder blocks. It looks eerily human-like as it moves its foot to explore the ground in front of it, strides, then corrects itself by swinging its torso and arms. In fact, that’s exactly what it’s been programmed to do. In a paper describing how the technique works, the researchers explain that “the robot explores the new contact surface by attempting to shift the center of pressure around the foot.” Then, an “available foothold is inferred by the way in which the foot rotates about contact edges ... during exploration.” The robot uses that information to work out how it should hold its foot as it takes a step, then it moves and uses upper body angular momentum—including arm waving—to maintain and regain balance. In testing, it’s able to walk over rough surfaces that feature edges or even corners of cinder blocks. The researchers say that their work is “an important step in the effort of making legged robots useful in real-world scenarios.” Of course, like humans, it won’t always get it right. But researchers have already started working out how to ensure that robots fall safely—so when they do take a tumble, it’s shouldn’t fracture their circuit boards.


Boston Dynamics has already developed a robot that can maintain its balance in uneven terrain involving a four-legged robot called BigDog. Now, the company through a third-party technology has just achieved the same feat but this time it involves a humanoid robot. The new development is attributed to an algorithm developed by the Institute for Human and Machine Cognition Robotics Lab in Florida, which allows humanoid robots advanced control techniques in order to maintain balance. The robotic project is part of the IHMC's entry to the DARPA Robotics Challenge, a competition seeking to advance robotics in the area of disaster response. The technology has enabled the bipedal robot called Atlas to balance itself not just on an uneven surface but on one that is constituted by different shapes and sizes . "While great strides have recently been made in robotics, robots still cannot get to the same places that people can," the IHMC said. "Our humanoid projects are focused on enabling our bipedal humanoids handle rough terrain without requiring onboard sensors to build a model of the terrain." The researchers addressed the challenge of bipedal walking by having the robot explore the surface first. "After a step is taken, the robot explores the new contact surface by attempting to shift the center of pressure around the foot," the researchers stated in a published paper detailing the walking technique. "The available foothold is inferred by the way in which the foot rotates about contact edges and/or by the achieved center of pressure locations on the foot during exploration." The video below demonstrates how the robot walks and balances itself atop cinder blocks. It initially looks easy but the efficacy and even grace by which Atlas navigates the surface is astounding given two factors. First, the robot weighs 330 pounds, so that act of balancing itself via the workings of gears and bolts on its joints and the effect of gravity on such weight makes the feat quite impressive, indeed. Second, there is the fact that the robot has no prior knowledge of the surface. It is effectively navigating the path for the first time and it was achieved without toppling over. The DARPA competition that the IHMC is participating in does not require the robot to be humanoid as long as it will be compatible with human operators and useful in disaster relief operations. IHMC researchers, however, decided to use Atlas because his human-like form is best suited for environments built for humans. © 2017 Tech Times, All rights reserved. Do not reproduce without permission.


Kerle N.,University of Twente | Hoffman R.R.,Institute for Human and Machine Cognition
Natural Hazards and Earth System Science | Year: 2013

Remote sensing is increasingly used to assess disaster damage, traditionally by professional image analysts. A recent alternative is crowdsourcing by volunteers experienced in remote sensing, using internet-based mapping portals. We identify a range of problems in current approaches, including how volunteers can best be instructed for the task, ensuring that instructions are accurately understood and translate into valid results, or how the mapping scheme must be adapted for different map user needs. The volunteers, the mapping organizers, and the map users all perform complex cognitive tasks, yet little is known about the actual information needs of the users. We also identify problematic assumptions about the capabilities of the volunteers, principally related to the ability to perform the mapping, and to understand mapping instructions unambiguously. We propose that any robust scheme for collaborative damage mapping must rely on Cognitive Systems Engineering and its principal method, Cognitive Task Analysis (CTA), to understand the information and decision requirements of the map and image users, and how the volunteers can be optimally instructed and their mapping contributions merged into suitable map products. We recommend an iterative approach involving map users, remote sensing specialists, cognitive systems engineers and instructional designers, as well as experimental psychologists. © 2013 Author(s).


Atkinson D.J.,Institute for Human and Machine Cognition
ACM/IEEE International Conference on Human-Robot Interaction | Year: 2015

Well-justified human evaluations of autonomous robot trustworthiness require evidence from a variety of sources, including observation of robot behavior. Displays of affect by a robot that reflect important internal states not otherwise overtly visible could provide useful evidence for evaluation of robot agent trustworthiness. As an analogy, the human limbic system, sometimes described as an ancient sub-cognitive system, drives human display of affect in a manner that is largely independent of purposeful behavior arising from cognition. Such displays of affect and corresponding attributions of emotion provide important social information that aids understanding and prediction of human behavior. Could an "artificial limbic system" provide similar useful insight into a robot's internal state? The value of affect signals for evaluation of robot trustworthiness depends on three crucial factors that require investigation: 1) Correlation of affective signals to trust-related, measurable attributes of robot agent internal state, 2) Fidelity in portrayal of emotion by the robot agent such that affective signals evoke human anthropomorphic social recognition, and 3) Correct human interpretation of the affective signals for justifiable modulation of beliefs about the robot agent. This paper discusses these three factors as principles to guide robotic simulation of emotion for increasing human ability to make reasonable assessments of robot trustworthiness and appropriate reliance. © 2015 Author.


Atkinson D.J.,Institute for Human and Machine Cognition
AAAI Spring Symposium - Technical Report | Year: 2015

The central thesis of this paper is that the technology of intelligent, autonomous machines gives rise to novel fault modes that are not seen in other types of automation. As a consequence, autonomous systems provide new vectors for cyber-attack with the potential consequence of subversion, degraded behavior or outright failure of the autonomous system. While we can only pursue the analogy so far. maladaptive behavior and the other symptoms of these fault modes in some cases may resemble those found in humans. The term "psychopathology" is applied to fault modes of the human mind, but as yet we have no equivalent area of study for intelligent, autonomous machines. This area requires further study in order to document and explain the symptoms of unique faults in intelligent systems, whether they occur in nominal conditions or as a result of an outside, purposeful attack. By analyzing algorithms, architectures and what can go wrong with autonomous machines, we may a) gain insight into mechanisms of intelligence: b) learn how to design out. work around or otherwise mitigate these new failure modes; c) identify potential new cyber-security risks: d) increase the trustworthiness of machine intelligence. Vigilancc and attention management mechanisms are identified as specific areas of risk. Copyright © 2015, AAAI Press.


Hoffman R.,Institute for Human and Machine Cognition
Journal of Cognitive Engineering and Decision Making | Year: 2015

Core elements of Endsley's models of situation awareness can be found in the history of the psychology of attention. History affords cautionary tales about the fuzzy nature of all attention constructs, the trap of reification, and the benefits of mindfulness in the modeling of cognitive phenomena. © 2015 Human Factors and Ergonomics Society.

Loading Institute for Human and Machine Cognition collaborators
Loading Institute for Human and Machine Cognition collaborators