Papers
2
Total Citations
23
H-Index
1
About
Ji Yin is an emerging researcher working at the intersection of autonomous systems, robust control, and safety-critical decision-making. Their work focuses on advancing model predictive control and probabilistic inference methods for reliable robotic applications. One of their most notable contributions is the development of Shield Model Predictive Path Integral (Shield-MPPI), a computationally efficient robust control framework that integrates Control Barrier Functions with sampling-based model predictive control. This work directly addresses practical limitations of traditional MPPI approaches — such as safety guarantees and computational overhead — that have historically constrained real-world deployment of autonomous systems. Garnering 22 citations since 2023, this research has quickly established itself as a meaningful advancement in the autonomous vehicle and robotics control community. Yin has also contributed to the challenge of autonomous system validation through learning-based Bayesian inference techniques, enabling more efficient failure mode prediction in simulation prior to costly hardware testing. Together, these contributions reflect a coherent research vision: making autonomous systems both computationally tractable and demonstrably safe, addressing two of the most pressing challenges facing the robotics and autonomous systems community today.
Research Focus
Key Achievements
Top Papers
- 1
- 2Learning-Based Bayesian Inference for Testing of Autonomous Systems1 citations · 2024