arXiv subjects

Longsen Gao

Publications and source records attributed to Longsen Gao.

7 recordsLinked to original sources

arXiv2026

FARS: A Fully Automated Research System Deployed at Scale

Recent automated research systems show that language-model agents can generate hypotheses, run experiments, and write complete manuscripts, but most evidence still comes from selected examples, human-framed topics, or a few pre-defined research tasks. We present FARS (Fully Automated Research System), a fully automated AI-for-AI research system designed to operate across research topics at scale. FARS autonomously generates and advances projects through ideation, planning, experimentation, and writing, using stage-specific agents coordinated through a shared workspace that records proposals, code, logs, results, and manuscripts. In its first public deployment, FARS produced 166 complete research papers spanning 67 fine-grained AI/ML topics while preserving intermediate artifacts as an auditable corpus rather than a curated set of successes. We evaluate this corpus with 282 structured reviews from volunteer reviewers covering 140 papers, including overall ratings, sub-scores, integrity checks, and LLM-use disclosure. The reviews indicate that FARS can produce review-worthy and occasionally strong AI/ML research artifacts in a large-scale public deployment, while also exposing recurring failure modes in narrow experimental scope, methodological limitations, and integrity issues.

cs.AI↗

arXiv2026

AirBender: Adaptive Transportation of Bendable Objects Using Dual UAVs

The interaction of robots with bendable objects in midair presents significant challenges in control, often resulting in performance degradation and potential crashes, especially for aerial robots due to their limited actuation capabilities and constant need to remain airborne. This paper presents an adaptive controller that enables two aerial vehicles to collaboratively follow a trajectory while transporting a bendable object without relying on explicit elasticity models. Our method allows on-the-fly adaptation to the object's unknown deformable properties, ensuring stability and performance in trajectory-tracking tasks. We use Lyapunov analysis to demonstrate that our adaptive controller is asymptotically stable. Our method is evaluated through hardware experiments in various scenarios, demonstrating the capabilities of using multirotor aerial vehicles to handle bendable objects.

cs.RO↗

arXiv2025

Graph-Fused Vision-Language-Action for Policy Reasoning in Multi-Arm Robotic Manipulation

Acquiring dexterous robotic skills from human video demonstrations remains a significant challenge, largely due to conventional reliance on low-level trajectory replication, which often fails to generalize across varying objects, spatial layouts, and manipulator configurations. To address this limitation, we introduce Graph-Fused Vision-Language-Action (GF-VLA), a unified framework that enables dual-arm robotic systems to perform task-level reasoning and execution directly from RGB-D human demonstrations. GF-VLA employs an information-theoretic approach to extract task-relevant cues, selectively highlighting critical hand-object and object-object interactions. These cues are structured into temporally ordered scene graphs, which are subsequently integrated with a language-conditioned transformer to produce hierarchical behavior trees and interpretable Cartesian motion primitives. To enhance efficiency in bimanual execution, we propose a cross-arm allocation strategy that autonomously determines gripper assignment without requiring explicit geometric modeling. We validate GF-VLA on four dual-arm block assembly benchmarks involving symbolic structure construction and spatial generalization. Empirical results demonstrate that the proposed representation achieves over 95% graph accuracy and 93% subtask segmentation, enabling the language-action planner to generate robust, interpretable task policies. When deployed on a dual-arm robot, these policies attain 94% grasp reliability, 89% placement accuracy, and 90% overall task success across stacking, letter-formation, and geometric reconfiguration tasks, evidencing strong generalization and robustness under diverse spatial and semantic variations.

cs.RO↗

arXiv2025

Information-Theoretic Graph Fusion with Vision-Language-Action Model for Policy Reasoning and Dual Robotic Control

Teaching robots dexterous skills from human videos remains challenging due to the reliance on low-level trajectory imitation, which fails to generalize across object types, spatial layouts, and manipulator configurations. We propose Graph-Fused Vision-Language-Action (GF-VLA), a framework that enables dual-arm robotic systems to perform task-level reasoning and execution directly from RGB and Depth human demonstrations. GF-VLA first extracts Shannon-information-based cues to identify hands and objects with the highest task relevance, then encodes these cues into temporally ordered scene graphs that capture both hand-object and object-object interactions. These graphs are fused with a language-conditioned transformer that generates hierarchical behavior trees and interpretable Cartesian motion commands. To improve execution efficiency in bimanual settings, we further introduce a cross-hand selection policy that infers optimal gripper assignment without explicit geometric reasoning. We evaluate GF-VLA on four structured dual-arm block assembly tasks involving symbolic shape construction and spatial generalization. Experimental results show that the information-theoretic scene representation achieves over 95 percent graph accuracy and 93 percent subtask segmentation, supporting the LLM planner in generating reliable and human-readable task policies. When executed by the dual-arm robot, these policies yield 94 percent grasp success, 89 percent placement accuracy, and 90 percent overall task success across stacking, letter-building, and geometric reconfiguration scenarios, demonstrating strong generalization and robustness across diverse spatial and semantic variations.

cs.RO↗

arXiv2025

Safe On-Orbit Dislodging of Deployable Structures via Robust Adaptive MPC

This paper proposes a novel robust adaptive model predictive controller for on-orbit dislodging. We study orbit dislodging where a servicing spacecraft uses a robotic arm to free a jammed and unactuated solar panel mounted on a hybrid hinge that acts as a time-varying client on a space station. Our method couples online set-membership identification with a robust adaptive MPC to enforce safety under bounded disturbances. The controller explicitly balances exploration to excite the system and shrink uncertainty and exploitation to improve control performance through a dual-mode cost. The feasibility of the developed robust adaptive MPC method is also examined through dislodging simulations and hardware experiments in freefall and terrestrial laboratory environments, respectively. In addition, the advantages of our method are shown through comparison experiments with several state-of-the-art control schemes for both accuracy of parameter estimation and control performance.

eess.SY↗

arXiv2024

Adaptive Robot Detumbling of a Non-Rigid Satellite

The challenge of satellite stabilization, particularly those with uncertain flexible dynamics, has become a pressing concern in control and robotics. These uncertainties, especially the dynamics of a third-party client satellite, significantly complicate the stabilization task. This paper introduces a novel adaptive detumbling method to handle non-rigid satellites with unknown motion dynamics (translation and rotation). The distinctive feature of our approach is that we model the non-rigid tumbling satellite as a two-link serial chain with unknown stiffness and damping in contrast to previous detumbling research works which consider the satellite a rigid body. We develop a novel adaptive robotics approach to detumble the satellite by using two space tugs as servicer despite the uncertain dynamics in the post-capture case. Notably, the stiffness properties and other physical parameters, including the mass and inertia of the two links, remain unknown to the servicer. Our proposed method addresses the challenges in detumbling tasks and paves the way for advanced manipulation of non-rigid satellites with uncertain dynamics.

cs.RO↗

arXiv2024

Decentralized Adaptive Aerospace Transportation of Unknown Loads Using A Team of Robots

Transportation missions in aerospace are limited to the capability of each aerospace robot and the properties of the target transported object, such as mass, inertia, and grasping locations. We present a novel decentralized adaptive controller design for multiple robots that can be implemented in different kinds of aerospace robots. Our controller adapts to unknown objects in different gravity environments. We validate our method in an aerial scenario using multiple fully actuated hexarotors with grasping capabilities, and a space scenario using a group of space tugs. In both scenarios, the robots transport a payload cooperatively through desired three-dimensional trajectories. We show that our method can adapt to unexpected changes that include the loss of robots during the transportation mission.

cs.RO↗