6 papers
Natural Geometry of Robust Data Attribution: From Convex Models to Deep Networks
Shihao Li, Jiachen Li, Dongmei Chen
Data attribution methods identify which training examples are responsible for a model's predictions, but their sensitivity to distributional perturbations undermines practical reli…
From Natural Language to Certified H-infinity Controllers: Integrating LLM Agents with LMI-Based Synthesis
Shihao Li, Jiachen Li, Jiamin Xu +1
We present \textsc{S2C} (Specification-to-Certified-Controller), a multi-agent framework that maps natural-language requirements to certified state-feedback co…
Algorithm-Relative Trajectory Valuation in Policy Gradient Control
Shihao Li, Jiachen Li, Jiamin Xu +3
We study how trajectory value depends on the learning algorithm in policy-gradient control. Using Trajectory Shapley in an uncertain LQR, we find a negative correlation between Per…
MDR-DeePC: Model-Inspired Distributionally Robust Data-Enabled Predictive Control
Shihao Li, Jiachen Li, Christopher Martin +2
This paper presents a Model-Inspired Distributionally Robust Data-enabled Predictive Control (MDR-DeePC) framework for systems with partially known and uncertain dynamics. The prop…
Constrained Optimal Planning to Minimize Battery Degradation of Autonomous Mobile Robots
Jiachen Li, Jian Chu, Feiyang Zhao +3
This paper proposes an optimization framework that addresses both cycling degradation and calendar aging of batteries for autonomous mobile robot (AMR) to minimize battery degradat…
Robust Optimal Task Planning to Maximize Battery Life
Jiachen Li, Chu Jian, Feiyang Zhao +3
This paper proposes a control-oriented optimization platform for autonomous mobile robots (AMRs), focusing on extending battery life while ensuring task completion. The requirement…