Yunong Li

Junichiro Sugihara, Masaki Kitagawa, Jinjie Li et al.

Multirotor aerial robots excel at maneuvering in three-dimensional space, and recent advances enable nimble navigation in cluttered and confined environments, especially for small airframes. By contrast, platforms built for high-altitude work tend to be larger to deliver high thrust for stable physical interaction with the environment. However, these conflicting design requirements create a long-standing trade-off between nimble navigation and robust aerial manipulation. Here, we present LEGION units, which are reconfigurable modular aerial robots capable of in-flight self-assembly for cooperative manipulation, drawing inspiration from the self-organized collectives formed by ants. Each unit retains nimble maneuverability while joint-equipped docking interfaces at both ends enable end-to-end self-assembly into a flying manipulator. We show that multiple units autonomously dock in flight; once latched, they maintain a zero-clearance interlock by controlling the contact force and torque, enabling reliable aggregation and articulated motion even outdoors. We further show that self-reconfigurability enables morphological switching between nimble individual flight and collective articulated manipulation, while realizing core in-flight manipulation primitives including pushing, pulling, rotating, grasping, and carrying. LEGION's self-organization enables aerial robots, especially in swarms, to shift from passive observers to active participants in their environment, broadening the scope of aerial physical interaction.

Lanqing Du, Yunong Li, YuJie Long et al.

Leveraging Large Language Models (LLMs) for Mental Health Question Answering (MHQA) is promising for mitigating resource shortages. However, existing Cognitive Behavioral Therapy (CBT)-based approaches predominantly favor a "top-down" rational restructuring, often neglecting clients' embodied experiences and primary emotion processing. To address this, we propose an Emotion-Focused Therapy (EFT)-based Multi-Agent Chain-of-Thought framework (EFT-CoT). Adopting a "bottom-up" trajectory, it deconstructs the intervention into a three-stage reasoning flow: "Embodied Perception - Cognitive Exploration - Narrative Intervention." Utilizing eight specialized agents, the system explicitly executes critical components such as somatic awareness mapping, adaptive assessment, core belief extraction, and narrative restructuring. We further constructed "EFT-Instruct," a high-quality dataset via Chain-of-Thought distillation of approximately 67,000 authentic texts, and fine-tuned a specialized model, EFT-LLM. Experimental evaluations demonstrate that EFT-LLM outperforms strong baselines and human responses across metrics like empathy depth and structural professionalism. Ablation studies confirm the necessity of the multi-agent mechanism. The model exhibits superior psychological reasoning, offering an effective pathway for interpretable, high-empathy counseling systems.

Haokun Liu, Zhaoqi Ma, Yunong Li et al.

Heterogeneous multirobot systems show great potential in complex tasks requiring coordinated hybrid cooperation. However, existing methods that rely on static or task-specific models often lack generalizability across diverse tasks and dynamic environments. This highlights the need for generalizable intelligence that can bridge high-level reasoning with low-level execution across heterogeneous agents. To address this, we propose a hierarchical multimodal framework that integrates a prompted large language model (LLM) with a fine-tuned vision-language model (VLM). At the system level, the LLM performs hierarchical task decomposition and constructs a global semantic map, while the VLM provides semantic perception and object localization, where the proposed GridMask significantly enhances the VLM's spatial accuracy for reliable fine-grained manipulation. The aerial robot leverages this global map to generate semantic paths and guide the ground robot's local navigation and manipulation, ensuring robust coordination even in target-absent or ambiguous scenarios. We validate the framework through extensive simulation and real-world experiments on long-horizon object arrangement tasks, demonstrating zero-shot adaptability, robust semantic navigation, and reliable manipulation in dynamic environments. To the best of our knowledge, this work presents the first heterogeneous aerial-ground robotic system that integrates VLM-based perception with LLM-driven reasoning for global high-level task planning and execution.