Advanced Robotics

Ocampo Jimenez, Jorge; Suleiman, Wael

doi: 10.1080/01691864.2026.2681402pmid: N/A

This paper presents a novel method for accelerating path planning tasks in unknown scenes with obstacles by utilizing Wasserstein Generative Adversarial Networks (WGANs) with Gradient Penalty (GP) to learn the distribution of the collision-free configuration space under given conditions. Our proposed approach involves conditioning the WGAN-GP with a Variational Auto-Encoder in a continuous latent space to handle multimodal datasets. However, training a Variational Auto-Encoder with WGAN-GP can be challenging for image-to-configuration-space problems, as the Kullback-Leibler loss function often converges to a random distribution. To overcome this issue, we simplify the configuration space as a set of Gaussian distributions and divide the dataset into several local models. This enables us to not only learn the model but also speed up its convergence. Our experiments show promising results for accelerating path planning tasks in unknown scenes while generating quasi-optimal paths with our WGAN-GP. The source code is openly available (https://bitbucket.org/joro3001/multiwgangp/).

Takase, Yutaka; Yamazaki, Kimitoshi

doi: 10.1080/01691864.2026.2686313pmid: N/A

We propose an occlusion-aware framework for human pose estimation based on temporal point-cloud sequences. Training data are generated via simulation and augmented with synthetic occlusions using Perlin-noise masks. The network combines PointNet++ for spatial features extraction, a Transformer for temporal encoding, and a graph convolutional network with inverse DCT for skeletal reconstruction. We evaluate the method against an RGB-based baseline (MediaPipe) under real robot-induced occlusions using 128 annotated frames of right-hand reaching. The proposed method achieves significantly lower errors than the baseline at the shoulder and elbow. An ablation study shows that occlusion augmentation significantly improves performance under occlusion. Visibility analysis further indicates that, after multiple-comparison correction, error-visibility correlations remain for the baseline but not for the proposed method, suggesting reduced sensitivity to occlusion. These results demonstrate the potential of simulation-to-real training for robust single-sensor pose estimation in assistive robotics.

Zhao, Weitao; Azizul, Zati Hakim; Woo, Chaw Seng; Wang, Huan; Li, Yafeng

doi: 10.1080/01691864.2026.2680954pmid: N/A

Task allocation is a central challenge in swarm robotics, yet most existing approaches assume known target locations or global communication, limiting their applicability in real-world search-and-rescue (SAR). This paper proposes a distributed method, the adaptive dynamic response threshold model (A-DRTM), to address SAR tasks in unknown and noisy environments under communication constraints. A-DRTM defines a task selection probability function that dynamically adjusts thresholds according to task demand disparities. Stimulation and jitter mechanisms are further incorporated to enhance flexibility and avoid local optima, improving responsiveness to environmental changes and coordination efficiency. Comprehensive simulations across varying initial positions, map sizes, robot-to-task ratios, communication ranges, and moving targets show that A-DRTM consistently outperforms six representative threshold-based algorithms. It achieves higher task completion, better resource utilisation, and stronger scalability, particularly in large-scale and communication-limited conditions.

Ahmed, Abdullah; Hu, Zhengtao; Wan, Weiwei; Watanabe, Tetsuyou; Harada, Kensuke

doi: 10.1080/01691864.2026.2682940pmid: N/A

This paper presents a novel exosuit designed to augment elbow capabilities using a hybrid actuator that integrates chain mail fabrics with a fiber-reinforced actuator. The actuator provides a bending moment to support elbow movement, while the chain mail enables tunable stiffness through a self-stiffening approach. Unlike conventional jamming-based exosuits, ours does not rely on an external power source to induce the jamming transition, making the exosuit lighter, more efficient, and more comfortable than traditional designs. Rotational stiffness experiments were performed to evaluate the mechanical characteristics and validate the jamming transition within the proposed actuator. Experimental results (at 120 kPa) showed that the hybrid actuator achieved a maximum increase in rotational stiffness of a factor of 13 compared to the fiber-reinforced actuator alone. To define the design space, additional experiments were conducted to evaluate the bending deformation angle, radius of curvature, and output force. Further tests were performed to evaluate the efficacy of the exosuit in enhancing human performance during load-lifting activity. The results demonstrated the ability of the exosuit to support elbow function effectively.