Cable-driven robotic systems are widely adopted for transport tasks due to their high load-bearing efficiency. However, their deployment in unstructured or unknown environments is hindered by the challenge of rapidly and reliably anchoring the cable endpoint. This work introduces a deployable cable-driven transport system that combines a tethered unmanned aerial vehicle (UAV) with a winch mechanism to autonomously form a topologically stable entanglement for cable anchoring. At the core of the system is a modular knot planner that integrates human-in-the-loop enclosing plane extraction, frontier-based enclosing path search, and knotting trajectory generation, incorporating metrics such as enclosing planarity, tether visibility, and tether clearance. In real-world experiments conducted in an urbanized outdoor environment, the system autonomously interpreted high-level user commands, executed a full knotting operation around a target structure, and successfully lifted a 15.3-kg payload to a height of 3.5 m. Beyond real-world trials, simulation studies confirmed the system’s shape-agnostic knotting capability. A set of ablation experiments further demonstrated the necessity and effectiveness of these joint optimization metrics. Together, these results highlight the practicality and robustness of the proposed system for autonomous heavy-load transport in complex and previously unprepared environments, offering new capabilities for rapidly deployable robotic logistics.

This article studies distributed pose (orientation and position) estimation of leader–follower multi-agent systems over κ-layer graphs in 2-D plane. Only the leaders have access to their orientations and positions, while the followers can measure the relative bearings or (angular and linear) velocities in their unknown local coordinate frames. For the orientation estimation, the local relative bearings are used to obtain the relative orientations among the agents, based on which a distributed orientation estimation algorithm is proposed for each follower to estimate its orientation. For the position estimation, the local relative bearings are used to obtain the position constraints among the agents, and a distributed position estimation algorithm is proposed for each follower to estimate its position by solving its position constraints. Both the orientation and position estimation errors converge to zero asymptotically. A simulation example is given to verify the theoretical results.

In this paper, we introduce a novel approach for efficiently estimating the six-Degree-of-Freedom (DoF) robot pose with a decoupled, noniterative method that capitalizes on overlapping planar elements. Conventional RGB-D Visual Odometry (RGBD-VO) often relies on iterative optimization solvers to estimate pose and involves a process of feature extraction and matching. This results in significant computational burden and time delays. To address this, our innovative method for RGBD-VO separates the estimation of rotation and translation. Initially, we exploit the overlaid planar characteristics within the scene to calculate the rotation matrix. Following this, we utilize a Kernel Cross-Correlator (KCC) to ascertain the translation. By sidestepping the resource-intensive iterative optimization and feature extraction and alignment procedures, our methodology offers improved computational efficacy, achieving a performance of 71 Hz on a lower-end i5 CPU. When the RGBD-VO does not rely on feature points, our technique exhibits enhanced performance in low-texture degenerative environments compared to state-of-the-art methods.

In this work, we present a data-driven solution for the attitude control of DoubleBee on slopes. DoubleBee is a novel hybrid aerial-ground robot with two rotors and two active wheels. Inspired by the physics modeling of the system, we add a channel-separated attention head to a deep ReLU neural network to predict disturbances from ground effects, motor torques and rotation axis shift. The proposed neural network is Lipschitz continuous, has fewer parameters and performs better for disturbance estimation than the baseline deep ReLU neural network. Then, we design a sliding mode controller using these predictions and establish its input-to-state stability and error bounds. Experiments show improvements of the proposed neural network in training speed and robustness over a baseline ReLU network, and a 40% reduction in tracking error compared to a baseline PID controller.

In response to the evolving challenges posed by small unmanned aerial vehicles (UAVs), which have the potential to transport harmful payloads or cause significant damage, we present AV-FDTI, an innovative Audio-Visual Fusion system designed for Drone Threat Identification. AV-FDTI leverages the fusion of audio and omnidirectional camera feature inputs, providing a comprehensive solution to enhance the precision and resilience of drone classification and 3D localization. Specifically, AV-FDTI employs a CRNN network to capture vital temporal dynamics within the audio domain and utilizes a pretrained ResNet50 model for image feature extraction. Furthermore, we adopt a visual information entropy and cross-attention-based mechanism to enhance the fusion of visual and audio data. Notably, our system is trained based on automated Leica tracking annotations, offering accurate ground truth data with millimeter-level accuracy. Comprehensive comparative evaluations demonstrate the superiority of our solution over the existing systems. In our commitment to advancing this field, we will release this work as open-source code and wearable AV-FDTI design, contributing valuable resources to the research community.

Multi-agent reinforcement learning (MARL) has been a rapidly evolving field. This paper presents a comprehensive survey of MARL and its applications. We trace the historical evolution of MARL, highlight its progress, and discuss related survey works. Then, we review the existing works addressing inherent challenges and those focusing on diverse applications. Some representative stochastic games, MARL means, spatial forms of MARL, and task classification are revisited. We then conduct an in-depth exploration of a variety of challenges encountered in MARL applications. We also address critical operational aspects, such as hyperparameter tuning and computational complexity, which are pivotal in practical implementations of MARL. Afterward, we make a thorough overview of the applications of MARL to intelligent machines and devices, chemical engineering, biotechnology, healthcare, and societal issues, which highlights the extensive potential and relevance of MARL within both current and future technological contexts. Our survey also encompasses a detailed examination of benchmark environments used in MARL research, which are instrumental in evaluating MARL algorithms and demonstrate the adaptability of MARL to diverse application scenarios. In the end, we give our prospect for MARL and discuss their related techniques and potential future applications.

Road segmentation is essential to unmanned systems, contributing to road perception and navigation in the field of autonomous driving. While multi-modal road segmentation methods have shown promising results by leveraging the complementary data of RGB and Depth to provide robust 3D geometry information, existing methods suffer from severe efficiency problems that hinder their practical application in autonomous driving. Their direct concatenation of multi-modal features with a densely-connected network leads to increased semantic gaps among modalities and scales, causing high computational and time complexity. To address these issues, we propose a Multi-modal Scale-aware Attention Network (MSAN) to fuse RGB and Depth data effectively via a novel transformer-based cross-attention module, namely Multi-modal Scare-aware Transformer (MST), which fuses RGB-D features from a global perspective across multiple scales. To better consolidate different scales of features, we further propose a Scale-aware Attention Module (SAM) that captures channel-wise attention efficiently for cross-scale fusion. These two attention-based modules explore the complementarity of modalities and scales, narrowing the gaps and avoiding complex structures for road segmentation. Extensive experiments demonstrate MSAN achieves competitive performance at a low computational cost, suitable for real-time implementation on edge-devices in autonomous driving systems.