Robot Dreams 2015


Notes:

Richard Alan Peters (DBLP):

The links between behaviors are created by the SAN agent during task planning but may also be created by a dream agent during the dream state. The links are task dependent and different behaviors may be linked together depending on the assigned goal.

When the robot is tasked to achieve a goal the spreading activation network SAN agent constructs a sequence of behaviors that will take the robot from its current state to the goal state active map in the DBAM by back propagating from the goal state to the current state For each behavior added to the active map the SAN agent performs a search for behaviors that have a pre condition state close to the postcondition state of the added behavior and adds a link connecting the close behavior to the added behavior An activation term characterizing the link and based on the inverse vector space distance between the linked behaviors is also added to the added behavior The SAN agent may create several paths connecting the current state to the goal state.

A command context agent enables the robot to receive a goal defined task and to transition the robot between active mode dream mode and training mode.

During periods of mechanical inactivity when not performing or learning a task or when the current task does not use the full processing capabilities of the robot the robot may transition to a dream state While in the dream state the robot modifies or creates new behaviors based on its most recent activities and creates new scenarios behavior sequences never before executed by the robot for possible execution during future activity.

Each time the robot dreams the dream agent analyzes R t for the recent active period since the last dream state by identifying episode boundaries and episodes Each recent episode is first compared to existing behaviors in the DBAM to confirm if the recent episode is another instance of the existing behavior The comparison may be based on the average distance or end point distances between the recent episode and the existing behavior or any other like criteria If the episode is close to the behavior the behavior may be modified to account for the new episode.

If the episode is distinct from the existing behaviors the dream agent creates a new behavior based on the episode and finds and creates links to the nearest behaviors The default activation link to the nearest existing behaviors may be based in part on the number of episodes represented in the exemplar behavior such that a new behavior generated from a single episode may be assigned a smaller activation value than behaviors generated from many episodes The new behavior is added to the DBAM for possible future execution.

If a robot is limited to behavior sequences learned only through teleoperation or other known training techniques the robot may not be able to respond to a new situation In a preferred embodiment a dream agent is activated during periods of mechanical inactivity and creates new plausible behavior sequences that may allow the robot during its active state to react purposefully and positively to contingencies never before experienced The dream agent randomly selects a pairs of behaviors from the DBAM and computes the end point distances between the selected behaviors The endpoint distances are the distances between the pre condition state of one behavior and the post condition state of the other behavior The distance may be a vector distance or any appropriate measure known to one of skill in the art If the computed distance is less than a cut off distance the preceding behavior the behavior with the post condition state close to the succeeding behavior’s pre-condition state is modified to include a link to the succeeding behavior.

The robots of Pfeifer and Cohen must be trained to identify episodes that lead to the accomplishment of a task The training usually involves an external handler that observes and rewards robot behaviors that advance the robot through the completion of the task The robot either makes a random move or a best estimate move and receives positive or negative feedback from the handler depending on whether the move advances the robot toward the goal This move feed back cycle must be repeated for each step toward the goal The advantage of such a training program is that robot learns both actions that lead toward a goal and actions that do not accomplish a goal The disadvantage of such a system is that the training time is very long because in addition to learning how to accomplish a task the robot learns many more methods not accomplishing a task.

A more efficient method of learning a task is to teach the robot only the tasks required to accomplish a goal Instead allowing the robot to make random moves the robot is guided through the completion of the task by an external handler via teleoperation During teleoperation the handler controls all actions of the robot while the robot records the state sensor and actuator information of the robot during the teleoperation The task is repeated several times under slightly differ ent conditions to allow the formation of episode clusters for later analysis After one or more training trials the robot is placed in the dream state where the recorded state information is analyzed by the robot to identify episodes episode boundaries and to create exemplar episodes for each episode cluster.

  • Robot dream (dreams, dreaming, daydream, daydreams, reverie, reveries)
  • Robots dream (dreams, dreaming, daydream, daydreams, reverie, reveries)
  • Robotic dream (dreams, dreaming, daydream, daydreams, reverie, reveries)
  • Robotics dream (dreams, dreaming, daydream, daydreams, reverie, reveries)

Wikipedia:

References:

See also:

Computational Dreaming | Daydreaming Machines | Digital Poetry 2015 | Poetry Generation 2015 | Robopsychology


Robot dreams I Asimov – Science Fiction and Philosophy: From Time Travel to …, 2015 – books.google.com “Last night I dreamed,” said LVX?1, calmly. Susan Calvin said nothing, but her lined face, old with wisdom and experience, seemed to undergo a microscopic twitch.“Did you hear that?” said Linda Rash, nervously.“It’s as I told you.” She was small, dark?haired, and young. Her Cited by 30 Related articles All 3 versions

An Emotion and Temperament Model for Cognitive Mobile Robots LN Long, TD Kelley, ES Avery – 24th Conference on Behavior …, 2015 – scripts.cac.psu.edu … J. Adv. Robotic Syst. Vol. 3, No. 3, pp. 219-222. Kelley, Troy D., (2014), Robotic Dreams: A Computational Justification for the Post-Hoc Processing of Episodic Memories, Intl. Jnl. of Machine Consciousness, Vol. 6, No. 2, pp. 109- 123. … Cited by 1 Related articles All 11 versions

Dreaming of Robots: An Interview About Robots with Bruce Sterling A Marcus – HCI and User-Experience Design, 2015 – Springer … (AM+A). 19.1 Summary. In past times, not only today, human beings have dreamed of “human-machine” hybrids, which, or who, could help, hurt, collaborate with, and/or challenge us. 19.2 Robot Dreams: Past Tense. Aaron Marcus: … 19.3 Robot Dreams: Present Tense. AM: … Related articles

Robotic Dreams: A Computation Justification For The Post-Hoc Processing Of Episodic Memories. TD KELLEY – academia.edu 1. As part of the development of the Symbolic and Sub-symbolic Robotics Intelligence System (SS-RICS) we have implemented a memory store to allow a robot to retain knowledge from previous experiences. As part of the development of the event memory Related articles

HCI and User-Experience Design A Marcus – Springer … Sterling….. 151 19.1 Summary….. 151 19.2 Robot Dreams: Past Tense….. 152 19.3 Robot Dreams: Present Tense….. 155 … Cited by 1

Tradeoffs in Real-Time Robotic Task Design with Neuroevolution Learning for Imprecise Computation PC Huang, L Sentis, J Lehman, CL Fok… – Real-Time Systems …, 2015 – ieeexplore.ieee.org Page 1. Tradeoffs in Real-Time Robotic Task Design with Neuroevolution Learning for Imprecise Computation Pei-Chi Huang ? , Luis Sentis † , Joel Lehman ? , Chien-Liang Fok † , Aloysius K. Mok ? , Risto Miikkulainen ? … Related articles All 2 versions

Mind the gaps! EU and the makings of robot autonomy K Rommetveit, K Gunnarsdóttir, N van Dijk, M Smits – epinet.no Page 1. 1 This is a preprint draft copy, freely available for fair use, see http://en.wikipedia. org/wiki/Fair_use . This is a discussion paper / preprint draft, based on EPINET D8.4, 2012. Mind the gaps! EU and the makings of robot autonomy … Related articles All 2 versions

An Evaluation of Sociolinguistic Elicitation Methods Z Boyd, Z Elliott, J Fruehwald, L Hall-Lew, D Lawrence – research.ed.ac.uk … Figure 2 gives an example of the large amount of variation that might be seen across different lab tasks. Note that ‘Pear Story Narration’ [4] refers to the silent movie narration task, and ‘Robot Dreams’ [23] refers to the picture book narration task. … Robot Dreams. … Cited by 1 Related articles All 4 versions

The Multifunctionality of Dreaming and the Oblivious Avatar M Dresler – Open MIND, 2015 – open-mind.net Page 1. The Multifunctionality of Dreaming and the Oblivious Avatar A Commentary on Revonsuo & Colleagues Martin Dresler Sleep and dreaming do not serve a single biological function, but are multifunc- tional. Their functions … Related articles All 3 versions

Programmable DNA-mediated multitasking processor JJ Shu, QW Wang, KY Yong, F Shao… – The Journal of Physical …, 2015 – ACS Publications Cited by 1 Related articles All 8 versions

Warming Up the Strings T Prescott – Neil Gaiman in the 21st Century: Essays on the …, 2015 – books.google.com … Dream through London. They are not strictly the same entity. Except they are.“YOU: DREAM OF THE ENDLESS ARE AS/ALSO WE,” announces the Robot Dream who seems to be channeling Metropolis (24). Dream is late to … Related articles All 2 versions

“Beware the Cosmic String, My Son”: Highjacked Realities and Accidental Utopias in Shinichir? Watanabe’s Space Dandy LM Filimon – Caietele Echinox, 2015 – ceeol.com Page 1. Caietele Echinox, vol. 29, 2015: Utopia, Dystopia, Film 156 ABSTRACT Anime series in the dystopia sci-fi subgenre are essentially what Miller Jr. describes as “investigations into the nature of human identity and its relation … Related articles All 3 versions

Leveraging the creative arts in business ethics teaching RE Freeman, L Dunham, G Fairchild… – Journal of Business Ethics, 2015 – Springer … One small leverage point here to facilitate this awareness is through our readings of short fiction and writing exercises. For example, we might use Isaac Asimov’s Robot Dreams to illustrate how power is leveraged in the workplace. … Cited by 2 Related articles All 9 versions

[BOOK] Just ordinary robots: automation from love to war L Royakkers, R van Est – 2015 – books.google.com Page 1. Just Ordinary Robots Automation from Love to War Lambèr Royakkers Rinie van Est Page 2. Page 3. Just Ordinary Robots Automation from Love to War Page 4. OTHER TITLES FROM AUERBACH PUBLICATIONS AND … Cited by 1 Related articles All 7 versions

Narrative production skills of language minority learners and their English-only classmates in early adolescence PB GÁMEZ, NK LESAUX… – Applied …, 2015 – Cambridge Univ Press … Given our early adolescent sample and our goal of ensuring high interest in producing high-quality narratives, we used the graphic, wordless novel Robot Dreams (Varon, 2007). … To elicit oral narratives, we used the graphic, wordless novel Robot Dreams (Varon, 2007). … Cited by 1 Related articles

Sort Attack: Visualization and Gamification of Sorting Algorithm Learning A Yohannis, Y Prabowo – Games and Virtual Worlds for Serious …, 2015 – ieeexplore.ieee.org Page 1. Sort Attack: Visualization and Gamification of Sorting Algorithm Learning Alfa R. Yohannis, Yulius D. Prabowo Faculty of Computer Science and Communication Science Institut Teknologi dan Bisnis KALBIS Jakarta, Indonesia alfa.yohannis@kalbis.ac.id … Cited by 1 Related articles All 3 versions

My autobiography did this to me Y Kim – 2015 – scholarworks.calstate.edu … Anything. Why do I sometimes feel like such a drag whenever I try to be happy. Do robots dream too? If I can perform fellatio, then why must you reject me? I morph into a cyborg after heartbreak. I morph into a cyborg after heartbreak I morph into a cyborg after heartbreak … All 3 versions

[BOOK] Darth Paper Strikes Back: An Origami Yoda Book T Angleberger – 2015 – books.google.com Page 1. R2M THE BESE ING AMOR of TESTEAMCE CASE of 2/24//yoDA # TOMA ANGLEBERGER + WBACK AnoRichmyotr Book Page 2. Page 3. Page 4. * AAMULET BOOKS NEW YORK Page 5. #Enc. – AN cRGAMyoDA Hook. Page 6. … Cited by 2 Related articles

Usability in a visual interface of an intelligent teaching system L Sanchez-Guerrero, AL Laureano-Cruces… – E-Learn: World …, 2015 – learntechlib.org … References • Asimov I. (1990). Sueños de Robot, Original tiltle Robot Dream (1986), España: Plaza & Janes. • Avila P. (1999). Aprendizaje con Nuevas Tecnologías (Paradigma Emergente). Retrieved from: http://investigacion.ilce.edu.mx/panel_control/doc/c37aprendizaje.pdf. … Related articles All 2 versions

Grand challenges for modeling and simulation: simulation everywhere—from cyberinfrastructure to clouds to citizens SJE Taylor, A Khan, KL Morse, A Tolk, L Yilmaz… – …, 2015 – sim.sagepub.com Page 1. Methodology Simulation Simulation: Transactions of the Society for Modeling and Simulation International 1–18 © 2015 The Author(s) DOI: 10.1177/0037549715590594 sim.sagepub.com Grand challenges for modeling and simulation: simulation everywhere— … Cited by 4 Related articles All 3 versions

How Can Chaos Theory Help Us toward the Emergence of a New Civilization? B Marion – World Future Review, 2015 – wfr.sagepub.com … Funding The author(s) received no financial support for the research, authorship, and/or publication of this article. Suggested Reading Asimov, Isaac. “The Last Question.” In Robot Dream. New York: Ace Books, 1956. Diamond, Jared. Guns, Steel and Germs. … Related articles All 2 versions

Inefficiently Automated Law Enforcement W Hartzog, G Conti, J Nelson, LA Shay – Mich. St. L. Rev., 2015 – HeinOnline … Why else would 35. LISA SHAY ET AL., Do ROBOTS DREAM OF ELECTRIC LAWS?: AN EXPERIMENT IN THE LAW AS ALGORITHM 25 (2013), http://conferences.law.stanford. edu/werobot/wp-content/uploads/sites/29/2013/04/Shay-et-alLisa.pdf. 36. … Cited by 1 Related articles All 2 versions

Ironies of Automation Law: Tying Policy Knots with Fair Automation Practices Principles, The ML Jones – Vand. J. Ent. & Tech. L., 2015 – HeinOnline Page 1. The Ironies of Automation Law: Tying Policy Knots with Fair Automation Practices Principles Meg Leta Jones* ABSTRACT Rapid developments in sensors, computing, and robotics, including power, kinetics, control, telecommunication … Cited by 3 Related articles All 5 versions

[BOOK] Encyclopedia of the American Short Story AHP Werlock – 2015 – books.google.com Page 1. ENCYCLOPEDIA OF EAMERICAN SHCDRT STORY THIRD EDITION Abby HP. Wer|ock Page 2. Encyclopedia of the American Short Story, 2Volume Set, Third Edition Copyright©2013byAbby HP Werlock All rights reserved. … Related articles

All’s Fair in Love and Cold War AG Wabeke – 2015 – academia.edu … are conflicted by their own actions. Arguably, the most confrontational instance occurred in ‘Do Mail Robots Dream of Electric Sheep?’ (2015; season 3, episode 9), when Elizabeth is forced to kill an innocent older woman called Betty (Lois Smith). … Related articles

Surveillance Never Sleeps: Technologies of the New Real A Kroker, M Kroker – CTheory, 2015 – mmduvic.ca Surveillance Never Sleeps: Technologies of the New Real. Related articles All 6 versions

Operational architectonics methodology for EEG analysis: theory and results AA Fingelkurts, AA Fingelkurts – … Assessment Techniques: Theory and …, 2015 – Springer Cited by 9 Related articles All 5 versions

[BOOK] HCI and User-experience Design: Fast-forward to the Past, Present, and Future A Marcus – 2015 – books.google.com … Sterling….. 151 19.1 Summary….. 151 19.2 Robot Dreams: Past Tense….. 152 19.3 Robot Dreams: Present Tense….. 155 … Related articles

Chaos, A User’s Guide B Marion – brunomarion.com Page 1. i Page 2. CHAOS, A USER’S GUIDE ii Bruno Marion Chaos, A User’s Guide Solutions for developing ourselves, our communities and organizations in a chaotic world Page 3. CHAOS, A USERS GUIDE iii Copyright © 2014 by Bruno Marion All rights reserved. … Related articles

[BOOK] Philosophy of Technology: An Introduction for Technology and Business Students MJ Verkerk, J Hoogland, J van der Stoep, MJ de Vries – 2015 – books.google.com Page 1. – / L- – – – – A – /> – Z < \ – . – Ž ^ “P” – AND BUSINES / / NJ verke RK, JAN Hoog AND. DER i” Arc J. Devries / / / | Z CY . |- // Page 2. Philosophy of Technology deepens especially my appreciation for the work of the … Cited by 3 Related articles All 4 versions

[BOOK] Developing Strategic Writers Through Genre Instruction: Resources for Grades 3-5 ZA Philippakos, CA MacArthur, DL Coker – 2015 – books.google.com Page 1. Developing StrategicWriters through Genre InStruction £ezovyces £ow Gwades 3-5. Zoi A. Philippakos Charles A. MacArthur David L. Coker Jr. Page 2. ebook THE GUILFORD PRESS Page 3. Developing Strategic WriterS through genre inStruction Page 4. … Cited by 1 Related articles All 2 versions