Jie Song

Yuechen Xie, Xiaoyan Zhang, Yicheng Shan et al.

Vision-Language Models (VLMs) have been increasingly applied in real-world scenarios due to their outstanding understanding and reasoning capabilities. Although VLMs have already demonstrated impressive capabilities in common visual question answering and logical reasoning, they still lack the ability to make reasonable decisions in complex real-world environments. We define this ability as spatial logical reasoning, which not only requires understanding the spatial relationships among objects in complex scenes, but also the logical dependencies between steps in multi-step tasks. To bridge this gap, we introduce Spatial Logical Question Answering (SpatiaLQA), a benchmark designed to evaluate the spatial logical reasoning capabilities of VLMs. SpatiaLQA consists of 9,605 question answer pairs derived from 241 real-world indoor scenes. We conduct extensive experiments on 41 mainstream VLMs, and the results show that even the most advanced models still struggle with spatial logical reasoning. To address this issue, we propose a method called recursive scene graph assisted reasoning, which leverages visual foundation models to progressively decompose complex scenes into task-relevant scene graphs, thereby enhancing the spatial logical reasoning ability of VLMs, outperforming all previous methods. Code and dataset are available at https://github.com/xieyc99/SpatiaLQA.

Jie Song, Yang Bai, Naoki Wakamiya

This work proposes a novel cooperative transportation framework for multi-agent systems that does not require any prior knowledge of cargo locations or sizes. Each agent relies on local sensing to detect cargos, recruit nearby agents, and autonomously form a transportation team with an appropriate size. The core idea is that once an agent detects a cargo within its sensing range, it generates an attraction field represented by a density function, which pulls neighboring agents toward the cargo. When multiple cargos are present, the attraction fields generated by different agents are adaptively weighted and combined with Centroidal Voronoi Tessellation (CVT), enabling agents to self-organize into balanced formations while automatically allocating more agents to larger cargos. To prevent agents from clustering on one side of a large cargo, a Control Barrier Function (CBF)-based mechanism is introduced to enforce safe inter-agent distances and promote a uniform, symmetric distribution of agents around each cargo, which is essential for stable transportation. Simulation results demonstrate that the proposed framework can simultaneously transport multiple cargos of different sizes in a coordinated and collision-free manner.

Xu Wan, Chao Yang, Cheng Yang et al.

Safe Reinforcement Learning (RL) is crucial for achieving high performance while ensuring safety in real-world applications. However, the complex interplay of multiple uncertainty sources in real environments poses significant challenges for interpretable risk assessment and robust decision-making. To address these challenges, we propose Fuz-RL, a fuzzy measure-guided robust framework for safe RL. Specifically, our framework develops a novel fuzzy Bellman operator for estimating robust value functions using Choquet integrals. Theoretically, we prove that solving the Fuz-RL problem (in Constrained Markov Decision Process (CMDP) form) is equivalent to solving distributionally robust safe RL problems (in robust CMDP form), effectively avoiding min-max optimization. Empirical analyses on safe-control-gym and safety-gymnasium scenarios demonstrate that Fuz-RL effectively integrates with existing safe RL baselines in a model-free manner, significantly improving both safety and control performance under various types of uncertainties in observation, action, and dynamics.