An official website of the United States government
An Evaluation of Robot-directed Prompts to Facilitate Interactions with Learners with Autism Spectrum Disorder
In Proc. of the 48th Annual Convention of the Association for Behavior Analysis International (ABAI 2022), Boston, Massachusetts, May 28-30, 2022.
more »
« less
- Award ID(s):
- 1838808
- PAR ID:
- 10355840
- Date Published:
- Journal Name:
- 48th Annual Convention of the Association for Behavior Analysis International (ABAI 2022)
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
Avidan, S.; Brostow, G.; Cissé, M.; Farinella, G.M.; Hassner, T. (Ed.)Wen, S., Wang, H., Metaxas, D. (2022). Social ODE: Multi-agent Trajectory Forecasting with Neural Ordinary Differential Equations. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13682. Springer, Cham. https://doi.org/10.1007/978-3-031-20047-2_13 Multi-agent trajectory forecasting has recently attracted a lot of attention due to its widespread applications including autonomous driving. Most previous methods use RNNs or Transformers to model agent dynamics in the temporal dimension and social pooling or GNNs to model interactions with other agents; these approaches usually fail to learn the underlying continuous temporal dynamics and agent interactions explicitly. To address these problems, we propose Social ODE which explicitly models temporal agent dynamics and agent interactions. Our approach leverages Neural ODEs to model continuous temporal dynamics, and incorporates distance, interaction intensity, and aggressiveness estimation into agent interaction modeling in latent space. We show in extensive experiments that our Social ODE approach compares favorably with state-of-the-art, and more importantly, can successfully avoid sudden obstacles and effectively control the motion of the agent, while previous methods often fail in such cases.more » « less
-
Abstract Over the last 7 years, geodetic data have detected periods of uplift and subsidence of the active volcano Ol Doinyo Lengai in Tanzania. Although numerous eruptions of the volcano have occurred historically, a systematic investigation of transient deformation using continuous Global Navigation Satellite System (GNSS) data has not been undertaken. We use the Targeted Projection Operator (TPO) to assess 7 years of continuous GNSS data from the TZVOLCANO network for transient signals and find rapid uplift spanning March 2022–December 2022 and then steady‐state uplift through August 2023. We conduct a nonlinear inversion of the GNSS velocities associated with the transient signal using dMODELS and find consistency with an inflating spheroidal source located 2.3 ± 0.6 km beneath the crater. Prior to March 2022, geodetic data indicated quiescence just below Ol Doinyo Lengai, thus detecting transient deformation with TPO allows for tracking changes in the magmatic system over time in the Natron Rift.more » « less
-
This dataset includes anonymized interview data collected virtually and in-person with stakeholders from the Yukon-Kuskokwim Delta between November 2021 and August 2022. These interviews were designed to capture water sector stakeholders’ experiences and perceptions of their water infrastructure systems. Interview questions included, for example: “Can you walk us through a typical workday in your role?”; “Who do you interact with most often in your role?”; “What are some of the biggest challenges you face in your role in the water sector?”; and “How do you resolve issues that arise in the water system?” We conducted eight virtual interviews and nine in-person interviews with stakeholders between November 22, 2021 and August 5, 2022. Interviews were recorded (with permission), transcribed, checked for quality, and anonymized for archival.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
