Aiguo Song

• Doctor of Engineering
• Southeast University

With the aging population and rising demand for assistive devices, electric wheelchairs have garnered significant attention. However, existing stair-climbing wheelchairs often suffer from complex structural complexity and limited flexibility. Spoke-wheel mechanisms, known for their simple structure and strong obstacle-crossing capabilities, hold pr...

Huffman coding is foundational to data compression algorithms. We propose an advanced application‐specific integrated circuit (ASIC) design for a canonical Huffman encoder, optimised for high throughput and low power consumption. Our design introduces a high‐speed sorting circuit, an efficient Huffman tree canonisation algorithm and an innovative e...

Chinese acupuncture practitioners primarily depend on muscle memory and tactile feedback to insert needles and accurately target acupuncture points, as the current workflow lacks imaging modalities and visual aids. Consequently, new practitioners often learn through trial and error, requiring years of experience to become proficient and earn the tr...

During the inspection and maintenance of the underwater part of hydraulic structures, it is often necessary to clean the surface of a certain area for subsequent operations. At present, there are still few robots capable of underwater fine cleaning. Therefore, this article introduces the design of a novel tracked robot system that can be used for u...

With the popularization of robots in various fields such as industry and healthcare, tactile perception ability has gradually become the key to achieving precise operation of physical objects by robots. Although existing tactile sensors can enable robots to accurately detect pressure, shear force, and strain, the ability of robots to perceive the e...

Myoelectric control interfaces, which map electromyographic (EMG) signals into control commands for external devices, have applications in active prosthesis control. However, the statistical characteristics of EMG signals change over time (e.g., because of changes in the electrode location), which makes interfaces based on static mapping unstable....

A significant number of people with disabilities rely on assistive devices, yet these technologies often face limitations, including restricted functionality, inadequate user-centered design, and a lack of standardized evaluation metrics. While upper-limb prosthetics remain a key research focus, existing commercial solutions still fall short of mee...

Chinese acupuncture practitioners primarily depend on muscle memory and tactile feedback to insert needles and accurately target acupuncture points, as the current workflow lacks imaging modalities and visual aids. Consequently, new practitioners often learn through trial and error, requiring years of experience to become proficient and earn the tr...

Visual feedback derived from digital subtraction angiography (DSA) images is indispensable for guiding interventional decisions during vascular procedures, as real-time DSA imaging provides critical information about the precise positioning of instruments within the vasculature. Excessive bending of the guidewire or microwire tip can pose significa...

To help the blind or visually impaired (BVI) read digitally conveniently and at low cost, we propose a bounce-type actuator driven by electromagnetic force, and based on this, a refreshable Braille display (RBD) which can display both Braille and tactile graphic information is manufactured. The internal components of the bounce-type actuator includ...

The COVID-19 pandemic has highlighted the importance of social distancing to prevent the spread of infectious diseases. However, enforcing social distancing in public spaces with traditional methods, such as hiring workers or using robots to remind people, can be unwelcome. In this paper, we propose a new technique to help maintain social distancin...

Interaction accuracy and transparency of force feedback devices (FFDs) are crucial in applications like remote surgery, where high force feedback accuracy (FFA) ensures the safety of delicate procedures. However, few studies have introduced the force calibration of FFDs, especially addressing the low FFA issue in high dynamic motions. This paper pr...

Controlling the bending angle of the pneumatic soft bending actuator (PSBA) under external loads presents a significant challenge. Previous studies have indicated that the Koopman-based model predictive control (MPC) strategy, combined with active disturbance rejection technologies, shows promise but also has limitations due to coarse Koopman model...

In recent years, various haptic rendering methods have been proposed to help people obtain interactive experiences with virtual textures through vibration feedback. However, due to impaired vision, the blind or visually impaired (BVI) is still unable to effectively perceive and learn virtual textures through these methods. To help BVIs have the opp...

Purpose This paper aims to propose a novel wheel-based multiaxis force sensor designed to detect the interaction forces and moments between the planetary rover’s wheel and the terrain, thereby assisting the rover in environmental perception. Design/methodology/approach The authors’ design approach encompasses the mechanical structure design, decou...

Continuum robots (CRs) possess better compliance than rigid manipulators. However, existing CRs suffer from difficulties in manipulating objects for the conflicting needs of high stiffness and flexibility. This letter proposes an elephant trunk-inspired CR for grasping and moving objects. The CR features a deformation mechanism based on coupling ri...

Simultaneous Localization and Mapping (SLAM) is a critical technology in robotics, with LiDAR-based SLAM has shown remarkable success in outdoor environments. However, real-time, robust, and precise state estimation in indoor environments remains a major challenge. This paper presents an innovative 3D LiDAR SLAM framework that incorporates multi-la...

The cooperation of a pair of robot manipulators is required to manipulate a target object without any fixtures. The conventional control methods coordinate the end-effector pose of each manipulator with that of the other using their kinematics and joint coordinate measurements. Yet, the manipulators' inaccurate kinematics and joint coordinate measu...

Investigating the role of haptics in emotional communication, specifically in emotion induction and regulation, is critical in the field of affective haptics. Although haptic vibrations are widely used for emotion display due to their simplicity and portability, existing studies have not fully explored vibration characteristics and lack objective m...

Simultaneous localization and mapping (SLAM) is a key technology for robot localization. Currently, most robot application scenarios are limited to either indoor or outdoor environments. When robots operate across both indoor and outdoor environments, they often experience significant positioning errors or even failures. To address this problem, we...

An aerial manipulator (AM) system for thickness measurement of metal facilities is introduced in this paper, which includes a fully actuated flying platform and an end-effector. The AM utilizes the fully actuated advantage of the flying platform to apply controlled contact forces to the environment without the need for complex robotic manipulators....

To address the issue that current transformable spoke-wheeled leg-wheel robots cannot simultaneously achieve simple structure, stable locomotion and open step climbing ability, a novel robot design method is proposed. The robot called BiTSpoke is driven by two transformable spoke wheels, with a passive wheel mounted at the tail end serving as suppo...

Recently, deep convolutional neural networks (CNNs) have achieved outstanding success in sensor-based human activity recognition (HAR) scenario, but at the cost of huge computational complexity, thereby restricting their practical deployment on resource-limited wearable devices. This may be partly attributed to static nature of most existing CNNs,...

Joint stiffness control is essential for safe and compliant human–robot interaction in rehabilitation exoskeletons. Variable stiffness actuators (VSAs), with controllable physical stiffness, offers a potential solution. However, existing VSAs generally do not allow both motors to contribute to power output simultaneously, which limits their perform...

In this study, for the musculoskeletal robot system, we aim at optimizing the angle tracking control based on the system model. First, we analyze the driving principle of muscles and establish a bionic muscle dynamics model. Further, based on the geometric relationship between muscles and skeletons, we establish the kinematics model and dynamics mo...

Lightweight convolutional neural networks (CNNs) are well suited for human activity recognition (HAR) applications deployed on edge devices like smartphones and wearable devices. However, the small-kernel convolutional operation is able to only capture local details within a window region, thereby preventing further performance improvement. Though...

During the past decade, deep neural networks (DNNs) have been widely deployed to a variety of mobile devices for sensor-based human activity recognition (HAR), where their computational budgets are usually dynamic and restricted. Anytime algorithms are especially suitable for such dynamic HAR computing environments, which can return a prediction at...

Existing works on controlling a concentric tube robot (CTR) mostly focus on the trajectory of its tip position or pose. In order to safely send CTRs in a confined lumen space, we propose to continuously steer the CTRs so that its entire shape will always attempt to approximate target curves over time. We focus on stiffness-dominant CTRs. Considerin...

During recent years, dynamic early-exit has provided a promising paradigm to improve the computational efficiency of deep neural networks by constructing multiple classifiers to let easy samples exit at shallow layers while avoiding redundant computations at deep exits, which has been seldom explored in the context of latency-aware human activity r...

Decoding natural hand movements using Movement-Related Cortical Potentials (MRCPs) features is crucial for the natural control of neuroprosthetics. However, current research has primarily focused on the characteristics of individual channels or on brain networks within a single frequency or time segment, overlooking the potential of brain networks...

During recent years, deep neural networks have achieved outstanding success in sensor-based human activity recognition (HAR). Particularly, dynamic convolution has emerged as a promising solution to accelerate activity inference of deep networks on mobile devices. Exploiting spatial redundancy, such a dynamic strategy can adaptively sample the sali...

Phase transition materials have the potential to be utilized as high‐resolution temperature‐sensitive materials. However, it is a challenge to develop them into temperature sensors with good stability and repeatability. In this work, inspired by phase transition theory and the electrical double‐layer capacitance principle, a novel high‐resolution f...

Flexible strain monitoring of hand and joint muscle movement is recognized as an effective method for the diagnosis and rehabilitation of neurological diseases such as stroke and Parkinson's disease. However, balancing high sensitivity and large strain, improving wearing comfort, and solving the separation of diagnosis and treatment are important c...

It is challenging to model and control rigid and flexible structures coupled systems (RFSCS). This article presents an automated robot for drum-to-drum cable winding in industrial scenes. The cable winding process encounters unprecedented disturbances that induce tension vibrations and winding errors. We seek to stabilize cable tension with an unde...

This study focuses on the flexible tube of a bronchoscope robot used in pulmonary intervention surgery, which is considered as a continuum robot. The dynamics model is proposed based on the Koopman operator, leveraging real data to solve for the system matrix parameters accurately. To enhance control precision, we designed a model predictive contro...

Recently, deep neural networks have triumphed over a large variety of human activity recognition (HAR) applications on resource-constrained mobile devices. However, most existing works are static and ignore the fact that the computational budget usually changes drastically across various devices, which prevent real-world HAR deployment. It still re...

While tangible user interface has shown its power in naturally interacting with rigid or soft objects, users cannot conveniently use different types of granular materials as the interaction media. We introduce DipMe as a smart device to recognize the types of granular media in real time, which can be used to connect the granular materials in the ph...

The cooperation of a pair of robot manipulators is required to manipulate a target object without any fixtures. The conventional control methods coordinate the end-effector pose of each manipulator with that of the other using their kinematics and joint coordinate measurements. Yet, the manipulators' inaccurate kinematics and joint coordinate measu...

Carbon dots (CDs) with intrinsic bioactivities are candidates for bioimaging and disease therapy due to their diverse bioactivities, high biocompatibility, and multiple functionalities in multimodal theranostics. It is a multidisciplinary research hotspot that includes biology, physics, materials science, and chemistry. This progress report discuss...

Acupuncture manipulation is a key factor that directly affects efficacy, but it lacks accurate quantification and identification at present. For the current problems of low precision, complex operation, interference with operation, single identification category and small sample size, it is the first time that identification of four acupuncture man...

Point cloud registration is a fundamental task in intelligent robots, aiming to achieve globally consistent geometric structures and providing data support for robotic manipulation. Due to the limited view of measurement devices, it is necessary to collect point clouds from multiple views to construct a complete model. Previous multi-view registrat...

High-quality chest compressions (CCs) are crucial for cardiopulmonary resuscitation. This paper presents a vision-based real-time CC detection system that can detect the CC depth (CCD), CC rate (CCR), CC posture (CCP), and CC person based on binocular vision and human key point detection techniques. We propose a method combining target detection an...

The event-triggered predictor design problem for a class of nonlinear MIMO systems with large time delays is investigated in this paper. A periodic event-triggered mechanism is designed to avoid unnecessary data transmission and save communication energy. The triggering condition is only determined by sampled outputs of the system, such that it is...

Autonomous exploration in unknown environments has become a critical capability of mobile robots. Many methods often suffer from problems such as exploration goal selection based solely on information gain and inefficient tour optimization. Recent reinforcement learning-based methods do not consider full area coverage and the performance of transfe...

Early-exiting has recently provided an ideal solution for accelerating activity inference by attaching internal classifiers to deep neural networks. It allows easy activity samples to be predicted at shallower layers, without executing deeper layers, hence leading to notable adaptiveness in terms of accuracy-speed trade-off under varying resource d...

The rapid development of collaborative robotics has provided a new possibility of helping the elderly who has difficulties in daily life, allowing robots to operate according to specific intentions. However, efficient human-robot cooperation requires natural, accurate and reliable intention recognition in shared environments. The current paramount...

We introduce a novel approach for bronchoscopic navigation that leverages neural radiance fields (NeRF) to passively locate the endoscope solely from bronchoscopic images. This approach aims to overcome the limitations and challenges of current bronchoscopic navigation tools that rely on external infrastructures or require active adjustment of the...

How to design and deploy efficient neural network backbones always plays a crucial role in sensor-based human activity recognition (HAR) on mobile devices, which have targeted at reducing floating-point operations (FLOPs) and parameter count, hence offering a faster activity inference. However, since the most commonly used efficiency indicators suc...

Deep convolutional neural networks (CNNs) have recently achieved outstanding success in human activity recognition (HAR) due to their ability to automatically extract hierarchical features. However, prior most works have always relied on a discrete grid-based formulation, which lacks flexibility and adaptiveness to handle multimodal activity signal...

In order to achieve natural tactile sensation and satisfactory perception for robots in complex environments, this paper presents a novel human-inspired robotic tactile sensing system for fluid. Specifically, a Biomimetic Fluid-Sensitive Handlike Sensor (BFHS) is designed by mimicking the perception mechanism of human skin. A deep learning model is...

Object handover is one of the fundamental tasks of service robots. This paper focuses on a robot-to-human object handover controller applied to a domestic service robot. People in need often have manual operation constraints caused by different body postures or declined physical functions. The preplanned handover strategy used in previous studies p...

Cancer, with high morbidity and high mortality, is one of the major burdens threatening human health globally. Intervention procedures via percutaneous puncture have been widely used by physicians due to its minimally invasive surgical approach. However, traditional manual puncture intervention depends on personal experience and faces challenges in...

Automated sleep staging is essential to assess sleep quality and treat sleep disorders, so the issue of electroencephalography (EEG)-based sleep staging has gained extensive research interests. However, the following difficulties exist in this issue: 1) how to effectively learn the intrinsic features of salient waves from single-channel EEG signals...