Loading [MathJax]/extensions/MathZoom.js
You Wang - IEEE Xplore Author Profile

Showing 1-25 of 38 results

Results

This letter proposes a novel linear online identification framework for the spherical robot to address the modeling difficulties posed by nonlinearity and time-varying characteristics. Firstly, the Koopman theory is applied to the spherical robot to build a linear model to approximate the nonlinearity. After selecting a set of observables based on spherical robots' dynamics, the model is identifie...Show More
Multi-terrain trajectory tracking control is a prerequisite for robots to execute tasks in the wild and unknown environments. However, due to the uncertainties in both kinematics and dynamics, the current trajectory tracking framework for mobile robots, such as spherical robots cannot function effectively on multiple terrains, especially uneven and unknown ones. Thus, an efficient online adaptive ...Show More
Predicting future motions of road participants is an important task for driving autonomously. Most existing models excel at predicting the marginal trajectory of a single agent, but predicting joint trajectories for multiple agents that are consistent within a scene remains a challenge. Previous research has often focused on marginal predictions, but the importance of joint predictions has become ...Show More
The spherical robot epitomizes an underactuated and non-holonomic system, where the control input is less than the system's degrees of freedom, thus rendering navigation and control complex. To equip the spherical robot with the ability to navigate various environments, perform multi-scene inspection tasks, and dynamically update its motion path in real time, necessitating the exploration of a pat...Show More
Previous research has demonstrated that combining Simultaneous Localization and Mapping (SLAM) and Multiple Object Tracking (MOT) yields better performance than using either one alone. In this paper, we present LVIO-MOT, an online stereo lidar-visual-inertial odometry which simultaneously tracks poses of objects while performing robot ego-motion tracking. LVIO-MOT consists of the visual-inertial s...Show More
To improve the trajectory tracking ability of the high nonlinear spherical robot, this paper proposes a model predictive trajectory tracker that considers the kino-dynamic model (KDMPC). Utilizing data identification algorithm based on the Koopman theory, we derived an equivalent linear approximated dynamic model. The kinematic model is linearized by the Taylor expansion. Consequently, the nonline...Show More
The dynamic model of a spherical robot exhibits nonlinearity and underactuation, posing significant challenges for model-based trajectory tracking control. Previous control methods often required two cascaded controllers to compute the motor torques needed for trajectory tracking. Additionally, controllers using Taylor series expansion-based linearization methods could only maintain high accuracy ...Show More
Model Predictive Control (MPC)-based trajectory planning has been widely used in robotics, and incorporating Control Barrier Function (CBF) constraints into MPC can greatly improve its obstacle avoidance efficiency. Unfortunately, traditional optimizers are resource-consuming and slow to solve such non-convex constrained optimization problems (COPs) while learning-based methods struggle to satisfy...Show More
Objective assessment of taste sensation is essential for medical diagnosis, food development, and multisensory interaction. Human taste sensation can be characterized through biosignals such as electroencephalography (EEG) and electromyography (EMG). However, taste sensation recognition on multiple-subject datasets remains challenging due to the low signal-to-noise ratio and substantial individual...Show More
The chemical selectivity and the sensor replacements challenge the applications of electronic noses (E-noses) in the detection of complex odors in natural environments. A hybrid of virtual sensor array (VSA) and multisensor array (MSA) was proposed in this article to enhance the selectivity of an E-nose by operating one of the sensor units at multiparameters instead of adding more sensors conventi...Show More
This paper presents an amphibious spherical robot with water surface posture stability. The robot is equipped with two sets of propulsion systems: an internal pendulum and a pair of main-secondary motors for rolling motion, and external left and right propellers for water surface propulsion motion. To enable autonomous motion of the water surface spherical robot, a path planning framework is desig...Show More
The spherical robot based on pendulum is a novel type of mobile robot whose motion is realized by changing the center of mass. Since the exteroceptive sensors such as camera and LiDAR are significantly hindered or even uninformative inside the spherical shell, the pose estimation for spherical robot is challenging. In this paper, we present a concise kinematic model for pendulum-driven spherical r...Show More
Due to nonholonomic dynamics, the motion planning of nonholonomic robots is always a difficult problem. This letter presents a Discrete States-based Trajectory Planning(DSTP) algorithm for autonomous nonholonomic robots. The proposed algorithm represents the trajectory as x and y positions, orientation angle, longitude velocity and acceleration, curvature, and time intervals. More variables make t...Show More
In this paper, we propose an efficient trajectory planning algorithm with path smoothing based on the Bézier curve with curvature constraints and piecewise-jerk speed-time optimization. We use hybrid A* to generate a rough path and construct a safe corridor by inflating the path. After that, we formulate the smooth problem as a nonlinear programming(NLP) with piecewise Bézier curves. Since the cur...Show More
This article proposes an adaptive and robust terrain classification control algorithm for a pendulum-driven spherical robot, aiming to solve the problem of insufficient control accuracy caused by using the same controller for different terrains. The common terrains are classified into three categories, and a terrain classification dataset is established based on the vibration signal of the robot. ...Show More
Terrain classification is a necessary and difficult task for all off-road robots. Most existing methods use images or proprioceptive sensors for recognition. However, while taking proprioceptive sensors as input requires more actual contact (which also means risks), images are susceptible to ambient light change. We also found that a combination of multiple optical channels in Lidars is quite usef...Show More
Path planning is a crucial module in motion planning for autonomous driving, aiming at generating kinematically feasible and collision-free paths. Furthermore, the smoothness of generated path is significant for passengers’ comfortable feelings. In this paper, we propose an improved quadratic programming approach that generates optimal paths in urban structure scenarios with the Frenét frame, taki...Show More
Taste sensation recognition is a keystone for taste-related brain–computer interface (BCI). A commonly used measurement of brain activity in response to specific stimulation is through electroencephalography (EEG) signals. However, it remains challenging to develop accurate and generalizable EEG-based measurement for human taste sensations. This article proposes EEG-MSRNet, a novel fully convoluti...Show More
Silent Speech Interface (SSI) based on neuromuscular signals has become popular in Human–Computer Interaction. Articulatory neuromuscular activity can be captured with surface electromyography (sEMG). However, in the absence of acoustic sounds, it remains challenging to convert the articulatory neuromuscular signals of silent speakers into corresponding audio. This article proposes a Mandarin-base...Show More
Taste sensation can be objectively measured using electroencephalography (EEG) or electromyography (EMG). How-ever, it is still challenging to effectively utilize the complementary information from EEG and EMG signals in taste sensation recognition. This paper proposes a bimodal fusion network (Bi-FusionNet) for recognizing basic taste sensations (sour, sweet, bitter, salty, umami, and blank). Two...Show More
In recent years, brain-computer interfaces based on sEMG and EEG have made progress in taste sensation recognition, but mainly focus on the classification of different tastes. This paper designs and carries out experiments to record the sEMG and EEG signals of different intensities of the five basic tastes stimulus: sour, sweet, bitter, salty and umami. Then time and frequency domain features are ...Show More
Taste sensation recognition is valuable for developing virtual taste and the early diagnosis of taste system disorders. Electromyography (EMG) can characterize the information of taste sensation and have the advantages of a high signal-to-noise ratio and easy acquisition. This paper presents feature extraction and feature combination methods for taste sensation knowledge based on facial EMG. The t...Show More
Since the sensors of spherical robots rotate with the longitudinal axis, an efficient velocity controller must also account for robot's attitude. Therefore, this paper proposed an optimal velocity controller for spherical robots based on the offset-free linear model predictive control (LMPC), which controls the velocity while considering robot's attitude, motor's current and other variables. The p...Show More
A spherical robot is a nonlinear, nonholonomic, and unstable system which increases the difficulty of the direction and trajectory tracking problem. In this study, we propose a new direction controller Hierarchical Terminal Sliding Mode Controller (HTSMC), an instruction planning controller called Model Prediction Control-based Planner (MPCBP), and a trajectory tracking framework named MPCBP-HTSMC...Show More
Human taste sensation can be qualitatively described with surface electromyography (sEMG). However, the pattern recognition models trained on one subject (the source domain) do not generalize well on other subjects (the target domain). To improve the generalizability and transferability of taste sensation models developed with sEMG data, two methods were innovatively applied in this study: domain ...Show More