No autonomous vehicle drives in a vacuum; it must share the road space with other road users (i.e.,
human drivers, pedestrians, and cyclists) and negotiate with them to achieve its goals in social traffic
scenes. When negotiating with other traffic participants, one challenging mission is making socially
compatible decisions and maneuvers that should be recognizable, understandable, and informative for
other agents while practically plannable and controllable for themselves. Inspired by human's driving
capability to interact with other human agents in a socially compatible way, AVs should leverage the
explicit sensory and perceptual information and the implicit social inferences and anticipations in
other human drivers' behavior to generate safe and socially-acceptable maneuvers. Major challenges
naturally arise in addressing the lack of first principles and proven mathematical models for systematic
and reliable solutions to reveal the mechanisms underlying man-driving behaviors' interaction processes.
We have envisioned that the computational cognitive science, Bayesian learning, optimization & control
community, and their integration will play a more crucial role in Socially Interactive Autonomous
Mobility [see Wang et al. 2022]. SIAM
workshop aims to report
recent research achievements, identify these relevant challenges, and review benchmarks and facilities for
this research domain. Through invited talks, panel discussions, and paper presentations, attendees will
become familiar with the latest research and network for new collaborations.
SIAM workshop is motivated by the healthy growth of the body of research in many areas related to social
interactions among multiple AI-based mobilities, including but not limited to theoretical frameworks and
practical algorithms for modeling, quantification & evaluation, trustworthy decision-making, behavior
prediction, intention recognition, and safety control toward inter-human and/or human-vehicle
interactions. The aim of this workshop focuses on sharing state-of-the-art methods, datasets, and
experiments while identifying the most critical challenges. We expect this workshop will become the
focal point for bringing together researchers from the growing robotics, control, transportation,
machine learning, and cognitive science communities to foster collaborative and creative solutions.
