An official website of the United States government
Interactive object understanding, or what we can do to objects and how is a long-standing goal of computer vision. In this paper, we tackle this problem through observation of human hands in in-the-wild egocentric videos. We demonstrate that observation of what human hands interact with and how can provide both the relevant data and the necessary supervision. Attending to hands, readily localizes and stabilizes active objects for learning and reveals places where interactions with objects occur. Analyzing the hands shows what we can do to objects and how. We apply these basic principles on the EPIC-KITCHENS dataset, and successfully learn state-sensitive features, and object affordances (regions of interaction and afforded grasps), purely by observing hands in egocentric videos.
more »
« less
Interactive Vignettes: Enabling Large-Scale Interactive HRI Research
We propose the use of interactive vignettes as an alternative to traditional text- and video-based vignettes for conducting large-scale Human-Robot Interaction (HRI) studies. Interactive vignettes maintain the advantages of traditional vignettes while offering additional affordances for participant interaction and data collection through interactive elements. We discuss the core affordances of interactive vignettes, including explorability, responsiveness, and non-linearity, and look into how these affordances can enable HRI research with more complex scenarios. To demonstrate the strength of the approach, we present a case study of our own research project with N=87 participants and show the data we collect through interactive vignettes. We suggest that the use of interactive vignettes can benefit HRI researchers in learning how participants interact with, respond to, and perceive a robot’s behavior in pre-defined scenarios.
more »
« less
- PAR ID:
- 10318058
- Date Published:
- Journal Name:
- 2021 30th IEEE International Conference on Robot & Human Interactive Communication (RO-MAN)
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
We examined how Idea Wall, a collaboration spatially manipulable interactive note tool, supports collaborative scientific reasoning among students. Through a design-based research approach, the study also aims to identify potential improvements to the tool that can better support collaborative interactions. The Idea Wall has the ability to facilitate spatial manipulation and interactive note-taking supported student engagement and collaboration. This paper contributes to the growing body of research on the use of interactive tools to enhance scientific reasoning skills in collaborative learning environments. By researching the affordances and challenges of the tool, this study provides valuable insights into the design considerations and potential improvements of such tools in building new norms of collaborative discussion for a knowledge community.more » « less
-
Human-robot interaction is now an established discipline. Dozens of HRI courses exist at universities worldwide, and some institutions even offer degrees in HRI. However, although many students are being taught HRI, there is no agreed-upon curriculum for an introductory HRI course. In this workshop, we aim to reach community consensus on what should be covered in such a course. Through interactive activities like panels, breakout discussions, and syllabus design, workshop participants will explore the many topics and pedagogical approaches for teaching HRI. They will then distill their findings into a single example introductory HRI curriculum. Output from this workshop will include a short paper explaining this curriculum and an example syllabus that can be used and adapted by HRI educators.more » « less
-
Human emotions are expressed through multiple modalities, including verbal and non-verbal information. Moreover, the affective states of human users can be the indicator for the level of engagement and successful interaction, suitable for the robot to use as a rewarding factor to optimize robotic behaviors through interaction. This study demonstrates a multimodal human-robot interaction (HRI) framework with reinforcement learning to enhance the robotic interaction policy and personalize emotional interaction for a human user. The goal is to apply this framework in social scenarios that can let the robots generate a more natural and engaging HRI framework.more » « less
-
Students in introductory college physics often have wide ranges of preparation, making it challenging to deliver effective instruction for all. While numerous educational products and strategies have been shown to be broadly effective, there is a need for research-based online materials that support personalized learning and focus specifically on improving problem-solving abilities. Building from our Interactive Video Vignettes (IVVs), we are developing freely available Interactive Video-Enhanced Tutorials (IVETs). These combine videos of real instructors who guide students through an expert-like problem-solving process using a series of required questions that motivate students to interact with the material. Research on the effectiveness of the IVETs is underway and preliminary results are encouraging.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/RO-MAN50785.2021.9515376
