Article
Automation & Control Systems
Daojin Yao, Lin Yang, Xiaohui Xiao, MengChu Zhou
Summary: This article develops a gait planning method for underactuated bipedal robot to walk on uneven and compliant terrain by controlling and tracking the robot's CoM and desired velocity.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2022)
Article
Engineering, Mechanical
Xin Ma, Jian Xu, Xiaoxu Zhang
Summary: This paper investigates the impact of the stochastic characteristics of uneven terrain on gait coordination and proposes modeling and control methods for prosthetic walking on uneven terrain. It accurately represents the stochastic ground reaction forces using data-driven modeling and establishes an extended stochastic dynamic model for amputee walking. A stochastic-gait-coordination oriented control architecture is proposed and realized using a bilateral constrained adaptive neural controller. Rigorous stochastic stability analysis of the proposed architecture shows that the controlled states are semi-globally uniformly ultimately bounded in probability. Prediction studies demonstrate that the proposed controller, BC-ANC, is more efficient than existing controllers.
INTERNATIONAL JOURNAL OF MECHANICAL SCIENCES
(2023)
Article
Automation & Control Systems
Haoran Zhong, Sicheng Xie, Xinyu Li, Liang Gao, Shengyu Lu
Summary: This paper proposes an online gait generation method using a pre-trained neural network to find periodic gaits for fast walking on uneven terrain. The improved walking pattern and application of the improved whale swarm algorithm enhance terrain adaptability. Simulation results demonstrate improvements in both maximum walking speed and terrain adaptability.
INTERNATIONAL JOURNAL OF CONTROL AUTOMATION AND SYSTEMS
(2022)
Article
Automation & Control Systems
Liang Wang, Tao Lei, Jinge Si, Kang Xu, Xiuwen Wang, Junzheng Wang, Shoukun Wang
Summary: In this study, a speed consensus control method combining distributed consensus algorithm with linear active disturbance rejection control is proposed to enhance the smoothness of wheel-legged robots while traversing uneven terrains.
Article
Biology
Nihav Dhawale, Madhusudhan Venkadesan
Summary: Running stably on uneven natural terrain requires skillful control and is crucial for human evolution. Human runners do not selectively step on more level ground areas, but their body's mechanical response helps maintain stability without requiring precise regulation of footsteps. Furthermore, their kinematics and energy consumption on uneven terrain show little change from flat ground, allowing them to devote attention to tasks besides guiding footsteps.
Article
Chemistry, Analytical
Sahana Prasanna, Jessica D'Abbraccio, Mariangela Filosa, Davide Ferraro, Ilaria Cesini, Giacomo Spigler, Andrea Aliperta, Filippo Dell'Agnello, Angelo Davalli, Emanuele Gruppioni, Simona Crea, Nicola Vitiello, Alberto Mazzoni, Calogero Maria Oddo
Summary: Recent advancements in prosthetics have greatly improved the quality of life for individuals with lower limb amputations, but there is still a lack of prostheses that can provide information about the foot-ground interaction and terrain irregularities. To address this issue, researchers have developed a biomimetic vibrotactile feedback system that conveys information about gait and terrain features sensed by a dedicated insole. In testing, subjects were able to accurately discriminate between even and uneven terrains solely relying on the replay of the vibrotactile feedback. This work is a significant step towards helping lower-limb amputees appreciate floor conditions, adapt their gait, and use their artificial limbs with more confidence.
Article
Computer Science, Artificial Intelligence
Fan Bailin, Zhang Yi, Chen Ye, Meng Lingbei
Summary: Based on the dynamic model of the intelligent firefighting vehicle, a linear 2-DOF lateral dynamic model and a preview error model are established. A Radial Basis Function neural network sliding mode controller is designed to solve the problems of non-linearity, time-varying parameters, output chattering, and poor robustness. Simulation results show that the controller has high accuracy in tracking the desired path and has good robustness to speed changes of the vehicle.
CAAI TRANSACTIONS ON INTELLIGENCE TECHNOLOGY
(2022)
Article
Robotics
Wataru Hashimoto, Kazumune Hashimoto, Shigemasa Takai
Summary: This letter presents a method for learning an RNN controller that maximizes the robustness of STL specifications. By introducing the concept of STL2vec, the controller can be efficiently constructed and validated through examples of path planning problem.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2022)
Article
Automation & Control Systems
Juntao Fei, Yun Chen, Lunhaojie Liu, Yunmei Fang
Summary: This study proposes a fuzzy double hidden layer recurrent neural network (FDHLRNN) controller for nonlinear systems using terminal sliding-mode control (TSMC). The FDHLRNN shows advantages in approximation capability and control performance, and its effectiveness is verified through simulation examples and hardware experiments.
IEEE TRANSACTIONS ON CYBERNETICS
(2022)
Article
Chemistry, Multidisciplinary
Phan Bui Khoi, Hong Nguyen Xuan
Summary: This paper investigates the problem of controlling a human-like bipedal robot during walking and proposes a method for building a fuzzy rule system suitable for bipedal robot control. By analyzing dynamical factors and designing motion trajectories, informational data and parameters are provided for the determination of the controller.
APPLIED SCIENCES-BASEL
(2021)
Article
Computer Science, Artificial Intelligence
Vasyl Teslyuk, Ivan Tsmots, Natalia Kryvinska, Taras Teslyuk, Yurii Opotyak, Mariana Seneta, Roman Sydorenko
Summary: This article introduces the development of a neural controller for an embedded control system, ensuring rapid system improvement through a modular principle. The hardware is based on the STM32 microcontroller, with a developed functional algorithm and data processing model using artificial neural networks.
PEERJ COMPUTER SCIENCE
(2023)
Article
Multidisciplinary Sciences
Ryan J. Downey, Natalie Richer, Rohan Gupta, Chang Liu, Erika M. Pliner, Arkaprava Roy, Jungyun Hwang, David J. Clark, Chris J. Hass, Todd M. Manini, Rachael D. Seidler, Daniel P. Ferris
Summary: This study investigated the effects of altering terrain unevenness on gait kinematics, and found that increasing terrain unevenness led to greater stride-to-stride variability and reduced perceived stability in participants.
Article
Chemistry, Analytical
Zhicheng He, Songhao Piao, Xiaokun Leng, Yucong Wu
Summary: This paper studies a walking control framework based on centroidal momentum allocation, which enables a child-size humanoid robot to walk on uneven terrain without using ground flatness information. The framework consists of three controllers: momentum decreasing controller, posture controller, and admittance controller. It shows the effectiveness of the momentum allocation method through experiments.
Article
Geochemistry & Geophysics
Elisabeth Schoenfeldt, Diego Winocur, Tomas Panek, Oliver Korup
Summary: Hundreds of basaltic plateau margins in eastern Patagonia are experiencing numerous giant slope failures. By utilizing deep learning models to analyze surface data, we discovered that this slope instability is widespread and constitutes one of the largest landslide clusters on Earth.
EARTH AND PLANETARY SCIENCE LETTERS
(2022)
Article
Engineering, Aerospace
Pierpaolo Mancini, Marco Cannici, Matteo Matteucci
Summary: The future of space exploration will involve closer operations with asteroids and comets, which often lack navigation infrastructure. This study proposes a siamese convolutional neural network for image matching and position retrieval to enable autonomous navigation. The system is robust, reusable, and does not require additional hardware deployment. It has been tested and shown promising results on real and simulated terrain maps.
ADVANCES IN SPACE RESEARCH
(2023)
Article
Computer Science, Artificial Intelligence
Rui Lv, Dingheng Wang, Jiangbin Zheng, Zhao-Xu Yang
Summary: In this paper, the authors investigate tensor decomposition for neural network compression. They analyze the convergence and precision of tensor mapping theory, validate the rationality of tensor mapping and its superiority over traditional tensor approximation based on the Lottery Ticket Hypothesis. They propose an efficient method called 3D-KCPNet to compress 3D convolutional neural networks using the Kronecker canonical polyadic (KCP) tensor decomposition. Experimental results show that 3D-KCPNet achieves higher accuracy compared to the original baseline model and the corresponding tensor approximation model.
Article
Computer Science, Artificial Intelligence
Xiangkun He, Zhongxu Hu, Haohan Yang, Chen Lv
Summary: In this paper, a novel constrained multi-objective reinforcement learning algorithm is proposed for personalized end-to-end robotic control with continuous actions. The approach trains a single model using constraint design and a comprehensive index to achieve optimal policies based on user-specified preferences.
Article
Computer Science, Artificial Intelligence
Zhijian Zhuo, Bilian Chen, Shenbao Yu, Langcai Cao
Summary: In this paper, a novel method called Expansion with Contraction Method for Overlapping Community Detection (ECOCD) is proposed, which utilizes non-negative matrix factorization to obtain disjoint communities and applies expansion and contraction processes to adjust the degree of overlap. ECOCD is applicable to various networks with different properties and achieves high-quality overlapping community detection.
Article
Computer Science, Artificial Intelligence
Yizhe Zhu, Chunhui Zhang, Jialin Gao, Xin Sun, Zihan Rui, Xi Zhou
Summary: In this work, the authors propose a Contrastive Spatio-Temporal Distilling (CSTD) approach to improve the detection of high-compressed deepfake videos. The approach leverages spatial-frequency cues and temporal-contrastive alignment to fully exploit spatiotemporal inconsistency information.
Review
Computer Science, Artificial Intelligence
Laijin Meng, Xinghao Jiang, Tanfeng Sun
Summary: This paper provides a review of coverless steganographic algorithms, including the development process, known contributions, and general issues in image and video algorithms. It also discusses the security of coverless steganography from theoretical analysis to actual investigation for the first time.
Article
Computer Science, Artificial Intelligence
Yajie Bao, Tianwei Xing, Xun Chen
Summary: Visual question answering requires processing multi-modal information and effective reasoning. Neural-symbolic learning is a promising method, but current approaches lack uncertainty handling and can only provide a single answer. To address this, we propose a confidence based neural-symbolic approach that evaluates NN inferences and conducts reasoning based on confidence.
Article
Computer Science, Artificial Intelligence
Anh H. Vo, Bao T. Nguyen
Summary: Interior style classification is an interesting problem with potential applications in both commercial and academic domains. This project proposes a method named ISC-DeIT, which combines data-efficient image transformer architectures and knowledge distillation, to address the interior style classification problem. Experimental results demonstrate a significant improvement in predictive accuracy compared to other state-of-the-art methods.
Article
Computer Science, Artificial Intelligence
Shashank Kotyan, Danilo Vasconcellos Vargas
Summary: This article introduces a novel augmentation technique called Dynamic Scanning Augmentation to improve the accuracy and robustness of Vision Transformer (ViT). The technique leverages dynamic input sequences to adaptively focus on different patches, resulting in significant changes in ViT's attention mechanism. Experimental results demonstrate that Dynamic Scanning Augmentation outperforms ViT in terms of both robustness to adversarial attacks and accuracy against natural images.
Article
Computer Science, Artificial Intelligence
Hiba Alqasir, Damien Muselet, Christophe Ducottet
Summary: The article proposes a solution to improve the learning process of a classification network by providing shape priors, reducing the need for annotated data. The solution is tested on cross-domain digit classification tasks and a video surveillance application.
Article
Computer Science, Artificial Intelligence
Dexiu Ma, Mei Liu, Mingsheng Shang
Summary: This paper proposes a method using neural dynamics solvers to solve infinity-norm optimization problems. Two improved solvers are constructed and their effectiveness and superiority are demonstrated through theoretical analysis and simulation experiments.
Article
Computer Science, Artificial Intelligence
Francesco Gregoretti, Giovanni Pezzulo, Domenico Maisto
Summary: Active Inference is a computational framework that uses probabilistic inference and variational free energy minimization to describe perception, planning, and action. cpp-AIF is a header-only C++ library that provides a powerful tool for implementing Active Inference for Partially Observable Markov Decision Processes through multi-core computing. It is cross-platform and improves performance, memory management, and usability compared to existing software.
Article
Computer Science, Artificial Intelligence
Zelin Ying, Dawei Cheng, Cen Chen, Xiang Li, Peng Zhu, Yifeng Luo, Yuqi Liang
Summary: This paper proposes a novel stock market trends prediction framework called SMART, which includes a self-supervised stock technical data sequence embedding model S3E. By training with multiple self-supervised auxiliary tasks, the model encodes stock technical data sequences into embeddings and uses the learned sequence embeddings for predicting stock market trends. Extensive experiments on China A-Shares market and NASDAQ market prove the high effectiveness of our model in stock market trends prediction, and its effectiveness is further validated in real-world applications in a leading financial service provider in China.
Article
Computer Science, Artificial Intelligence
Hao Li, Hao Jiang, Dongsheng Ye, Qiang Wang, Liang Du, Yuanyuan Zeng, Liu Yuan, Yingxue Wang, C. Chen
Summary: DHGAT1, a dynamic hyperbolic graph attention network, utilizes hyperbolic metric properties to embed dynamic graphs. It employs a spatiotemporal self-attention mechanism and weighted node representations, resulting in excellent performance in link prediction tasks.
Article
Computer Science, Artificial Intelligence
Jiehui Huang, Zhenchao Tang, Xuedong He, Jun Zhou, Defeng Zhou, Calvin Yu-Chian Chen
Summary: This study proposes a progressive learning multi-scale feature blending model for image deraining tasks. The model utilizes detail dilation and texture extraction to improve the restoration of rainy images. Experimental results show that the model achieves near state-of-the-art performance in rain removal tasks and exhibits better rain removal realism.
Article
Computer Science, Artificial Intelligence
Lizhi Liu, Zilin Gao, Yinhe Wang, Yongfu Li
Summary: This paper proposes a novel discrete-time interconnected model for depicting complex dynamical networks. The model consists of nodes and edges subsystems, which consider the dynamic characteristic of both nodes and edges. By designing control strategies and coupling modes, the stabilization and synchronization of the network are achieved. Simulation results demonstrate the effectiveness of the proposed methods.