arXiv subjects

Yaosheng Deng

Publications and source records attributed to Yaosheng Deng.

7 recordsLinked to original sources

arXiv2026

Flying to Image-Specified Objects: 3D Quadrotor Navigation via Cross-Graph Memory and Viewpoint Planning

Instance-Specific Image-Goal Navigation (InstanceImageNav) requires a robot to navigate toward the exact object instance depicted in a query image. Extending this task to quadrotors is challenging due to continuous 3D control, limited field of view (FOV), and safety constraints, which make successful navigation highly dependent on selecting informative viewpoints. We propose a hierarchical navigation framework for quadrotor InstanceImageNav that separates high-level decision making from low-level motion execution. Instead of navigating directly to spatial locations, the system generates viewpoint-aware action nodes around frontier regions and potential target objects, enabling the robot to explore while maintaining informative viewpoints for detecting the target instance. A lightweight semantic memory maintains object-level and observation-level context, allowing semantic cues to propagate to candidate action nodes for decision making. A learning-based policy selects the most promising action node, and a trajectory planner generates dynamically feasible 3D flight paths for safe execution. Experiments in simulation demonstrate consistent improvements over strong baselines, and real-world quadrotor flights validate the practicality and robustness of the proposed framework.

cs.RO↗

arXiv2026

TRUST-UP: Trustworthy Reinforcement learning Using Safe Techniques for UAV Pursuit

Reinforcement Learning (RL) enables autonomous aerial vehicles to adapt quickly and make efficient decisions, making it well-suited for dynamic urban air mobility operations. However, the lack of safety guarantees and transparency hinders the airworthiness certification of RL-based flight control systems, particularly in low-altitude urban environments with human presence. This paper proposes a trustworthy reinforcement learning algorithm that utilizes safe techniques to address the AI trustworthiness requirements for aviation safety, ensuring the transparent and certifiable deployment of RL in safety-critical aerial operations. Specifically, we proposed a Trustworthy Reinforcement learning Using Safe Techniques for UAV Pursuit (TRUST-UP), which consists of two key components: a safety filter constructed from Control Barrier Functions (CBFs) that transforms unsafe RL actions into provably safe flight commands, and a switching strategy that enhances feasibility while maintaining operational transparency. These components enable trustworthy AI deployment in urban airspace, satisfying technical robustness and transparency requirements for aviation certification. Simulation results demonstrate that TRUST-UP enables autonomous UAVs to safely navigate congested urban environments while maintaining human-interpretable decision logic. This work contributes toward certifiable and explainable AI frameworks for low-altitude aviation, addressing the critical need for trustworthy autonomous flight systems in future urban air mobility.

eess.SY↗

arXiv2025

Toward generic control for soft robotic systems

Soft robotics has advanced rapidly, yet its control methods remain fragmented: different morphologies and actuation schemes still require task-specific controllers, hindering theoretical integration and large-scale deployment. A generic control framework is therefore essential, and a key obstacle lies in the persistent use of rigid-body control logic, which relies on precise models and strict low-level execution. Such a paradigm is effective for rigid robots but fails for soft robots, where the ability to tolerate and exploit approximate action representations, i.e., control compliance, is the basis of robustness and adaptability rather than a disturbance to be eliminated. Control should thus shift from suppressing compliance to explicitly exploiting it. Human motor control exemplifies this principle: instead of computing exact dynamics or issuing detailed muscle-level commands, it expresses intention through high-level movement tendencies, while reflexes and biomechanical mechanisms autonomously resolve local details. This architecture enables robustness, flexibility, and cross-task generalization. Motivated by this insight, we propose a generic soft-robot control framework grounded in control compliance and validate it across robots with diverse morphologies and actuation mechanisms. The results demonstrate stable, safe, and cross-platform transferable behavior, indicating that embracing control compliance, rather than resisting it, may provide a widely applicable foundation for unified soft-robot control.

cs.RO↗

arXiv2025

Safety Critical Control for Nonlinear Systems with Complex Input Constraints

In this paper, we propose a novel Control Barrier Function (CBF) based controller for nonlinear systems with complex, time-varying input constraints. To deal with these constraints, we introduce an auxiliary control input to transform the original system into an augmented one, thus reformulating the constrained-input problem into a constrained-output one. This transformation simplifies the Quadratic Programming (QP) formulation and enhances compatibility with the CBF framework. As a result, the proposed method can systematically address the complex, time-varying, and state-dependent input constraints. The efficacy of the proposed approach is validated using numerical examples.

eess.SY↗

arXiv2024

Swarm navigation of cyborg-insects in unknown obstructed soft terrain

Cyborg insects refer to hybrid robots that integrate living insects with miniature electronic controllers to enable robotic-like programmable control. These creatures exhibit advantages over conventional robots in adaption to complex terrain and sustained energy efficiency. Nevertheless, there is a lack of literature on the control of multi-cyborg systems. This research gap is due to the difficulty in coordinating the movements of a cyborg system under the presence of insects' inherent individual variability in their reactions to control input. Regarding this issue, we propose a swarm navigation algorithm and verify it under experiments. This research advances swarm robotics by integrating biological organisms with control theory to develop intelligent autonomous systems for real-world applications.

cs.RO↗

arXiv2023

Collision-Free Shepherding Control of a Single Target within a Swarm

The shepherding problem refers to guiding a group of agents (called sheep) to a specific destination using an external agent with repulsive forces (called shepherd). Although various movement algorithms for the shepherd have been explored in the literature, there is a scarcity of methodologies for selective guidance, which is a key technology for precise swarm control. Therefore, this study investigates the problem of guiding a single target sheep within a swarm to a given destination using a shepherd. We first present our model of the dynamics of sheep agents and the interaction between sheep and shepherd agents. The model is shown to be well-defined with no collision if the interaction magnitude between sheep and shepherd is reasonably limited. Based on the analysis with Lyapunov stability principles, we design a shepherd control law to guide the target sheep to the origin while avoiding collisions among sheep agents. Experimental results demonstrate the effectiveness of the proposed method in guiding the target sheep in both small and large scale swarms.

nlin.AO↗

arXiv2022

Shepherding Control for Separating a Single Agent from a Swarm

In this paper, we consider the swarm-control problem of spatially separating a specified target agent within the swarm from all the other agents, while maintaining the connectivity among the other agents. We specifically aim to achieve the separation by designing the movement algorithm of an external agent, called a shepherd, which exerts repulsive forces on the agents in the swarm. This problem has potential applications in the context of the manipulation of the swarm of micro- and nano-particles. We first formulate the separation problem, where the swarm agents (called sheep) are modeled by the Boid model. We then analytically study the special case of two-sheep swarms. By leveraging the analysis, we then propose a potential function-based movement algorithm of the shepherd to achieve separation while maintaining the connectivity within the remaining swarm. We demonstrate the effectiveness of the proposed algorithm with numerical simulations.

eess.SY↗