Naiyao Wang
Papers
2
Total Citations
46
H-Index
2
About
Naiyao Wang is a researcher at the forefront of autonomous systems and embodied AI, with key contributions in pedestrian trajectory prediction and robot obstacle avoidance. Wang’s most cited work, "SEEM: A Sequence Entropy Energy-Based Model for Pedestrian Trajectory All-Then-One Prediction" (2022, 40 citations), introduces a novel energy-based framework that addresses critical limitations in trajectory forecasting—namely, the lack of diversity, poor accuracy, and instability in predicting pedestrian paths. This work has become a foundational reference for researchers working on safe autonomous driving and social robot navigation. Building on this, Wang’s "DUEL: Depth visUal Ego-motion Learning for autonomous robot obstacle avoidance" (2023) tackles the challenge of reliable obstacle perception and multi-modal avoidance using depth-based visual ego-motion. By integrating latent factor cognition, DUEL enhances the robustness of autonomous navigation in real-world environments. Wang’s research directly impacts the safety and efficiency of autonomous systems, bridging the gap between predictive modeling and real-time decision-making. With a growing citation footprint, Wang is recognized for pushing the boundaries of how machines understand and navigate dynamic human spaces.
Research Focus
Key Achievements
Top Papers
- 1
- 2