Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleJuly 2024
Emergence of integrated behaviors through direct optimization for homeostasis
AbstractHomeostasis is a self-regulatory process, wherein an organism maintains a specific internal physiological state. Homeostatic reinforcement learning (RL) is a framework recently proposed in computational neuroscience to explain animal behavior. ...
Highlights- We conducted a direct optimization of the simulated embodied agent for homeostasis.
- Agents obtained motor control for behavioral homeostasis in various environments.
- Interoception-dependent foraging emerged in an environment with ...
- abstractJuly 2022
Dual Robot Avatar: Real-time Multispace Experience using Telepresence Robots and Walk Sensation Feedback including Viewpoint Sharing for Immersive Virtual Tours
SIGGRAPH '22: ACM SIGGRAPH 2022 Emerging TechnologiesJuly 2022, Article No.: 3, Pages 1–2https://doi.org/10.1145/3532721.3535570Traveling to different places simultaneously is a dream for several people, but it is difficult to realize this aspiration because of our physical space limits. On one hand, virtual reality technologies can help alleviate such limits. According to the ...
- research-articleFebruary 2022
Imitation and mirror systems in robots through Deep Modality Blending Networks
Neural Networks (NENE), Volume 146, Issue CFeb 2022, Pages 22–35https://doi.org/10.1016/j.neunet.2021.11.004AbstractLearning to interact with the environment not only empowers the agent with manipulation capability but also generates information to facilitate building of action understanding and imitation capabilities. This seems to be a strategy ...
- research-articleDecember 2021
World model learning and inference
Neural Networks (NENE), Volume 144, Issue CDec 2021, Pages 573–590https://doi.org/10.1016/j.neunet.2021.09.011AbstractUnderstanding information processing in the brain—and creating general-purpose artificial intelligence—are long-standing aspirations of scientists and engineers worldwide. The distinctive features of human intelligence are high-level ...
- proceedingNovember 2020
HAI '20: Proceedings of the 8th International Conference on Human-Agent Interaction
It is our great pleasure to welcome you to the Eighth International Conference on Human-Agent Interaction HAI 2020 (Virtual Conference); hosted by the Western Sydney University (Australia) and supported by Chalmers University of Technology (Sweden).
The ...
-
- research-articleOctober 2020
Learning Timescales in Gated and Adaptive Continuous Time Recurrent Neural Networks
2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)Oct 2020, Pages 2662–2667https://doi.org/10.1109/SMC42975.2020.9282864Recurrent neural networks that can capture temporal characteristics on multiple timescales are a key architecture in machine learning solutions as well as in neurocognitive models. A crucial open question is how these architectures can adopt both multi-...
- research-articleFebruary 2020
A review on neural network models of schizophrenia and autism spectrum disorder
Neural Networks (NENE), Volume 122, Issue CFeb 2020, Pages 338–363https://doi.org/10.1016/j.neunet.2019.10.014AbstractThis survey presents the most relevant neural network models of autism spectrum disorder and schizophrenia, from the first connectionist models to recent deep neural network architectures. We analyzed and compared the most ...
- research-articleAugust 2019
Affordance-based altruistic robotic architecture for human–robot collaboration
Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems (SAGE-ADAP), Volume 27, Issue 4Aug 2019, Pages 223–241https://doi.org/10.1177/1059712318824697This article proposes a computational model for altruistic behavior, shows its implementation on a physical robot, and presents the results of human–robot interaction experiments conducted with the implemented system. Inspired from the sensorimotor ...
- research-articleOctober 2017
Active Perception based on Energy Minimization in Multimodal Human-robot Interaction
HAI '17: Proceedings of the 5th International Conference on Human Agent InteractionOctober 2017, Pages 103–110https://doi.org/10.1145/3125739.3125757Humans use various types of modalities to express own internal states. If a robot interacting with humans can pay attention to limited signals, it should select more informative ones to estimate the partners' states. We propose an active perception ...
- proceedingOctober 2017
HAI '17: Proceedings of the 5th International Conference on Human Agent Interaction
It is our great pleasure to welcome you to The Fifth International Conference on Human-Agent Interaction (HAI 2017) at the Excellence Center of Cognitive Interaction Technology (CITEC) in the medieval town of Bielefeld at the heart of the historically ...
- research-articleJune 2017
Efficient human-robot collaboration
International Journal of Robotics Research (RBRS), Volume 36, Issue 5-76 2017, Pages 563–579https://doi.org/10.1177/0278364916688253The promise of robots assisting humans in everyday tasks has led to a variety of research questions and challenges in human-robot collaboration. Here, we address the question of whether and when a robot should take initiative during joint human-robot ...
- research-articleDecember 2016
3D woven composite design using a flattening simulation
- Kotaro Morioka,
- Yutaka Ohtake,
- Hiromasa Suzuki,
- Yukie Nagai,
- Hiroyuki Hishida,
- Koichi Inagaki,
- Takeshi Nakamura,
- Fumiaki Watanabe
Computer-Aided Design (CADE), Volume 81, Issue CDecember 2016, Pages 24–38https://doi.org/10.1016/j.cad.2016.09.001Fiber composite materials have unique, advantageous mechanical properties that have made them highly desirable in a range of industries. In particular, 3D woven-fiber composites are highly resistant to delamination compared with laminated 2D woven-fiber ...
- research-articleNovember 2016
Panoramic view reconstruction for stereoscopic teleoperation of a humanoid robot
2016 IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids)Pages 242–248https://doi.org/10.1109/HUMANOIDS.2016.7803284In recent years, robots have become more commonplace as a method for humans to remotely conduct observations or interactions, with commercial applications ranging from customer service to assembly line work. Virtual and augmented reality have shown much ...
- research-articleOctober 2016
EmoSonics: Interactive Sound Interfaces for the Externalization of Emotions
AM '16: Proceedings of the Audio Mostly 2016October 2016, Pages 61–68https://doi.org/10.1145/2986416.2986437This paper presents a novel approach for using sound to externalize emotional states so that they become an object for communication and reflection both for the users themselves and for interaction with other users such as peers, parents or therapists. ...
- research-articleMarch 2016
Initiative in Robot Assistance during Collaborative Task Execution
HRI '16: The Eleventh ACM/IEEE International Conference on Human Robot InteractionMarch 2016, Pages 67–74Collaborative robots are quickly gaining momentum in real-world settings. This has motivated many new research questions in human-robot collaboration. In this paper, we address the questions of whether and when a robot should take initiative during ...
- proceedingMarch 2016
HRI '16: The Eleventh ACM/IEEE International Conference on Human Robot Interaction
We are excited to welcome you to the Eleventh Annual ACM/IEEE International Conference on Human-Robot Interaction (HRI 2016). The HRI Conference is a highly selective, single track, international meeting showcasing the best research in human-robot ...
- research-articleNovember 2015
Yet another gaze detector: An embodied calibration free system for the iCub robot
2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids)Pages 8–13https://doi.org/10.1109/HUMANOIDS.2015.7363515The recognition of gaze as for example mutual gaze plays an important role in social interaction. Previous research shows that already infants are capable of detecting mutual gaze. Such abilities are relevant for robots to learn from interaction, for ...
- research-articleAugust 2015
Gaze contingency in turn-taking for human robot interaction: Advantages and drawbacks
2015 24th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN)Pages 369–374https://doi.org/10.1109/ROMAN.2015.7333640It is generally accepted that a robot should exhibit a contingent behavior, adaptable to the needs of each individual user, to achieve a more natural and pleasant interaction. In this paper we have evaluated whether this general rule applies also when the ...
- research-articleJune 2015
Staged Development of Robot Skills: Behavior Formation, Affordance Learning and Imitation with Motionese
IEEE Transactions on Autonomous Mental Development (ITAMD), Volume 7, Issue 2June 2015, Pages 119–139https://doi.org/10.1109/TAMD.2015.2426192Inspired by infant development, we propose a three staged developmental framework for an anthropomorphic robot manipulator. In the first stage, the robot is initialized with a basic reach-and- enclose-on-contact movement capability, and discovers a set of ...