PHASE: PHysically-grounded Abstract Social Events for Machine Social
Perception
- URL: http://arxiv.org/abs/2103.01933v1
- Date: Tue, 2 Mar 2021 18:44:57 GMT
- Title: PHASE: PHysically-grounded Abstract Social Events for Machine Social
Perception
- Authors: Aviv Netanyahu, Tianmin Shu, Boris Katz, Andrei Barbu, Joshua B.
Tenenbaum
- Abstract summary: We create a dataset of physically-grounded abstract social events, PHASE, that resemble a wide range of real-life social interactions.
Phase is validated with human experiments demonstrating that humans perceive rich interactions in the social events.
As a baseline model, we introduce a Bayesian inverse planning approach, SIMPLE, which outperforms state-of-the-art feed-forward neural networks.
- Score: 50.551003004553806
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The ability to perceive and reason about social interactions in the context
of physical environments is core to human social intelligence and human-machine
cooperation. However, no prior dataset or benchmark has systematically
evaluated physically grounded perception of complex social interactions that go
beyond short actions, such as high-fiving, or simple group activities, such as
gathering. In this work, we create a dataset of physically-grounded abstract
social events, PHASE, that resemble a wide range of real-life social
interactions by including social concepts such as helping another agent. PHASE
consists of 2D animations of pairs of agents moving in a continuous space
generated procedurally using a physics engine and a hierarchical planner.
Agents have a limited field of view, and can interact with multiple objects, in
an environment that has multiple landmarks and obstacles. Using PHASE, we
design a social recognition task and a social prediction task. PHASE is
validated with human experiments demonstrating that humans perceive rich
interactions in the social events, and that the simulated agents behave
similarly to humans. As a baseline model, we introduce a Bayesian inverse
planning approach, SIMPLE (SIMulation, Planning and Local Estimation), which
outperforms state-of-the-art feed-forward neural networks. We hope that PHASE
can serve as a difficult new challenge for developing new models that can
recognize complex social interactions.
Related papers
- Robot Interaction Behavior Generation based on Social Motion Forecasting for Human-Robot Interaction [9.806227900768926]
We propose to model social motion forecasting in a shared human-robot representation space.
ECHO operates in the aforementioned shared space to predict the future motions of the agents encountered in social scenarios.
We evaluate our model in multi-person and human-robot motion forecasting tasks and obtain state-of-the-art performance by a large margin.
arXiv Detail & Related papers (2024-02-07T11:37:14Z) - Interactive Humanoid: Online Full-Body Motion Reaction Synthesis with
Social Affordance Canonicalization and Forecasting [23.37555991996508]
We propose a new task named online full-body motion reaction synthesis.
It generates humanoid reactions based on the human actor's motions.
To support this task, we construct two datasets named HHI and CoChair.
arXiv Detail & Related papers (2023-12-14T14:29:52Z) - Habitat 3.0: A Co-Habitat for Humans, Avatars and Robots [119.55240471433302]
Habitat 3.0 is a simulation platform for studying collaborative human-robot tasks in home environments.
It addresses challenges in modeling complex deformable bodies and diversity in appearance and motion.
Human-in-the-loop infrastructure enables real human interaction with simulated robots via mouse/keyboard or a VR interface.
arXiv Detail & Related papers (2023-10-19T17:29:17Z) - SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents [107.4138224020773]
We present SOTOPIA, an open-ended environment to simulate complex social interactions between artificial agents and humans.
In our environment, agents role-play and interact under a wide variety of scenarios; they coordinate, collaborate, exchange, and compete with each other to achieve complex social goals.
We find that GPT-4 achieves a significantly lower goal completion rate than humans and struggles to exhibit social commonsense reasoning and strategic communication skills.
arXiv Detail & Related papers (2023-10-18T02:27:01Z) - SocialCircle: Learning the Angle-based Social Interaction Representation for Pedestrian Trajectory Prediction [19.075215661355486]
We build a new anglebased trainable social interaction representation, named SocialCircle, for continuously reflecting the context of social interactions.
We validate the effect of the proposed SocialCircle by training it along with several newly released trajectory prediction models.
Experiments show that the SocialCircle not only quantitatively improves the prediction performance, but also qualitatively helps better simulate social interactions.
arXiv Detail & Related papers (2023-10-09T02:59:21Z) - Bodily Behaviors in Social Interaction: Novel Annotations and
State-of-the-Art Evaluation [0.0]
We present BBSI, the first set of annotations of complex Bodily Behaviors embedded in continuous Social Interactions.
Based on previous work in psychology, we manually annotated 26 hours of spontaneous human behavior.
We adapt the Pyramid Dilated Attention Network (PDAN), a state-of-the-art approach for human action detection.
arXiv Detail & Related papers (2022-07-26T11:24:00Z) - Co-Located Human-Human Interaction Analysis using Nonverbal Cues: A
Survey [71.43956423427397]
We aim to identify the nonverbal cues and computational methodologies resulting in effective performance.
This survey differs from its counterparts by involving the widest spectrum of social phenomena and interaction settings.
Some major observations are: the most often used nonverbal cue, computational method, interaction environment, and sensing approach are speaking activity, support vector machines, and meetings composed of 3-4 persons equipped with microphones and cameras, respectively.
arXiv Detail & Related papers (2022-07-20T13:37:57Z) - The world seems different in a social context: a neural network analysis
of human experimental data [57.729312306803955]
We show that it is possible to replicate human behavioral data in both individual and social task settings by modifying the precision of prior and sensory signals.
An analysis of the neural activation traces of the trained networks provides evidence that information is coded in fundamentally different ways in the network in the individual and in the social conditions.
arXiv Detail & Related papers (2022-03-03T17:19:12Z) - SSAGCN: Social Soft Attention Graph Convolution Network for Pedestrian
Trajectory Prediction [59.064925464991056]
We propose one new prediction model named Social Soft Attention Graph Convolution Network (SSAGCN)
SSAGCN aims to simultaneously handle social interactions among pedestrians and scene interactions between pedestrians and environments.
Experiments on public available datasets prove the effectiveness of SSAGCN and have achieved state-of-the-art results.
arXiv Detail & Related papers (2021-12-05T01:49:18Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.