Pengju Jin
Papers
2
Total Citations
27
H-Index
2
About
Pengju Jin is a robotics researcher whose work bridges the critical gap between perception and social interaction in autonomous systems. His primary research areas include sensor fusion for robust pose estimation, adaptive human-robot interaction, and online policy learning for socially-aware navigation. Jin’s most cited work, “Sensor fusion for fiducial tags: Highly robust pose estimation from single frame RGBD” (2017, 25 citations), addresses a fundamental challenge in robotics: accurately estimating pose from noisy sensor data. By fusing RGB-D information with fiducial markers, he developed a method that significantly improves robustness for applications in augmented reality and robotic manipulation, providing a practical solution for real-world deployment where data quality is inconsistent. His more recent contribution, “A-EXP4: Online Social Policy Learning for Adaptive Robot-Pedestrian Interaction” (2019), explores self-supervised adaptation in social robotics. This work introduces a framework for robots to dynamically adjust their communication strategies—through audio or visual signals—based on changing social contexts, inspired by human behavioral adaptation. While still early in its citation impact, this research represents a forward-looking approach to creating robots that can seamlessly integrate into human environments. Jin’s work demonstrates a commitment to making robots both more perceptually reliable and socially intelligent, with implications for service robotics, autonomous navigation, and human-robot collaboration.
Research Focus
Key Achievements
Top Papers
- 1
- 2