arXiv subjects

Zhenwei Huang

Publications and source records attributed to Zhenwei Huang.

4 recordsLinked to original sources

arXiv2026

Event-Adaptive Motion Planning with Distilled Vision-Language Model in Safety-Critical Situations

Robot navigation in safety-critical scenarios faces significant challenges from unforeseen semantic events, where collisions arise primarily from the unpredictable behaviors of dynamic agents rather than unseen objects. While large vision-language models (VLMs) offer remarkable capabilities in commonsense reasoning, frequently invoking them within the continuous control loop introduces severe computational latency, fundamentally destabilizing physical execution. To address these challenges, we propose event-adaptive motion planning (EAMP), an efficient framework for VLM-based robot navigation. Specifically, a prompt-configurable semantic event trigger (PC-SET) selectively activates semantic intervention by continuously monitoring short temporal clips for behavioral anomalies. Upon triggering, an event-triggered distilled SemNav-VLM, fine-tuned via physically verified semantic distillation, maps detected anomalies into discrete strategy-level decisions. Subsequently, a semantic model predictive control (SMPC) module translates these strategies into dynamic reconfigurations of optimization objectives and geometric references. Extensive experiments in safety-critical logistics scenarios demonstrate that EAMP effectively aligns high-level reasoning with low-level control, significantly improving dynamic safety margins over existing baselines while preserving real-time efficiency.

cs.RO↗

arXiv2024

Riemannian Federated Learning via Averaging Gradient Streams

Federated learning (FL) as a distributed learning paradigm has a significant advantage in addressing large-scale machine learning tasks. In the Euclidean setting, FL algorithms have been extensively studied with both theoretical and empirical success. However, there exist few works that investigate federated learning algorithms in the Riemannian setting. In particular, critical challenges such as partial participation and data heterogeneity among agents are not explored in the Riemannian federated setting. This paper presents and analyzes a Riemannian FL algorithm, called RFedAGS, based on a new efficient server aggregation -- averaging gradient streams, which can simultaneously handle partial participation and data heterogeneity. We theoretically show that the proposed RFedAGS has global convergence and sublinear convergence rate under decaying step sizes cases; and converges sublinearly/linearly to a neighborhood of a stationary point/solution under fixed step sizes cases. These analyses are based on a vital and non-trivial assumption induced by partial participation, which is shown to hold with high probability. Extensive experiments conducted on synthetic and real-world data demonstrate the good performance of RFedAGS.

cs.LG↗

arXiv2024

Federated Learning on Riemannian Manifolds with Differential Privacy

In recent years, federated learning (FL) has emerged as a prominent paradigm in distributed machine learning. Despite the partial safeguarding of agents' information within FL systems, a malicious adversary can potentially infer sensitive information through various means. In this paper, we propose a generic private FL framework defined on Riemannian manifolds (PriRFed) based on the differential privacy (DP) technique. We analyze the privacy guarantee while establishing the convergence properties. To the best of our knowledge, this is the first federated learning framework on Riemannian manifold with a privacy guarantee and convergence results. Numerical simulations are performed on synthetic and real-world datasets to showcase the efficacy of the proposed PriRFed approach.

math.OC↗

arXiv2024

An increasing rank Riemannian method for generalized Lyapunov equations

In this paper, we consider finding a low-rank approximation to the solution of a large-scale generalized Lyapunov matrix equation in the form of $A X M + M X A = C$, where $A$ and $M$ are symmetric positive definite matrices. An algorithm called an Increasing Rank Riemannian Method for Generalized Lyapunov Equation (IRRLyap) is proposed by merging the increasing rank technique and Riemannian optimization techniques on the quotient manifold $\mathbb{R}_*^{n \times p} / \mathcal{O}_p$. To efficiently solve the optimization problem on $\mathbb{R}_*^{n \times p} / \mathcal{O}_p$, a line-search-based Riemannian inexact Newton's method is developed with its global convergence and local superlinear convergence rate guaranteed. Moreover, we derive a preconditioner which takes $M \neq I$ into consideration. Numerical experiments show that the proposed Riemannian inexact Newton's method and preconditioner has superior performance and IRRLyap is preferable compared to the tested state-of-the-art methods when the lowest rank solution is desired.

math.OC↗