Toni Tan
Papers
1
Total Citations
5
H-Index
1
About
Toni Tan’s research lies at the intersection of embodied intelligence, probabilistic simulation, and human-robot interaction, with a focus on enabling robots to perceive and reason about physical environments in a human-like manner. Their most cited work, “NaivPhys4RP - Towards Human-like Robot Perception ‘Physical Reasoning based on Embodied Probabilistic Simulation’” (2022, 5 citations), introduces a novel framework that addresses three critical challenges often overlooked in classical perception: reasoning about object dynamics, anticipating physical interactions, and adapting to unpredictable human-centered settings. By grounding perception in embodied probabilistic simulation, Tan’s approach moves beyond standard classification tasks—such as identifying what and where objects are—to a deeper, more intuitive understanding of physical causality. This work has been recognized for its potential to bridge the gap between robotic perception and human-like common sense reasoning, particularly in dynamic environments where traditional methods fall short. Tan’s contributions are especially relevant for advancing autonomous systems in collaborative and domestic settings, where robots must navigate uncertainty and physical complexity. With a growing citation footprint, Toni Tan is establishing themselves as a thoughtful voice in the push toward more adaptive, cognitively inspired robotics.
Research Focus
Key Achievements
Top Papers
- 1