With the popularity of electric vehicles (EVs) and the gradual maturity of the technology of bidirectional power transfer between EVs and the grid, EVs as a mobile energy storage device to achieve peak shaving and valley filling of the grid has become a hot point. Hence, we are committed to exploring the use of EVs to achieve spatial and temporal energy supply redistribution via V2G and G2V. We propose a multi-type bidirectional power transfer network and minimize the system cost by determining facility siting and pricing, which can be modeled as a bi-level optimization problem. In lower-level, a transportation and power coupled network is constructed considering the bidirectional interaction between EVs and the grid. We propose a new user equilibrium to explain the equilibrium state under bidirectional interaction, construct the optimal power flow model under the equilibrium state, use variational inequality to solve the minimum travel cost, and obtain the locational marginal price by solving the Lagrange duality variable of the active power. In upper-level, we propose the government’s construction of multi-type charging facilities siting planning to minimize transportation system cost and facilities operation costs. For experimental analysis, we consider various interactive scenarios of EVs and the grid and use three comparative models to verify the effectiveness of the proposed model. Results show that considering coupled network will effectively reduce the grid load and system cost. Notably, to provide more useful inspiration, we also have made a sensitivity analysis on the change of bidirectional transfer power and service price.

Bus priority signal control can reduce bus delay at intersections and improve bus operation efficiency. The existing research focus mainly on bus priority control methods at isolated intersections, as well as urban arterial corridors. Rarely existing works consider a network-level bus priority control. Treating regional-wide intersections can be challenging, given that more traffic directions and large multi-modal traffic volume should be considered. The conventional transit signal priority (TSP) research focus on the delay of buses and social vehicles and neglect the delay of pedestrians. To fill these gaps, this paper proposes a regional coordinated bus priority signal control (RCBPSC) method, which is a network-level bus priority control method considering pedestrian and passenger delays. This method is divided into two stages. The first stage is the regional coordinated signal control to obtain the basic signal timing schemes. The second stage is the bus priority signal control. At this stage, the timing schemes at each intersection will be adjusted according to the bus arrival time and the delays. In order to verify the effectiveness of this method, we choose four intersections in Chengdu to study. The results show that the total delay of the proposed method at the first stage (control case 1) can be reduced by 602s (2.3%) and 606s (3.7%) comparing with the conventional timing method in the peak and non-peak period. At the second stage, the proposed method can reduce more pedestrian delay than the conventional TSP method in bothscenario 1andscenario 2.

Heavy truck drivers driving trucks under the situation of drowsiness can cause serious traffic accidents. In this paper, a heavy truck driver's drowsiness detection method using wearable electroencephalographic (EEG) based on convolution neural network (CNN) is proposed. The presented method consists of three parts: data collection using wearable EEG, heavy truck driver's drowsiness detection and the early warning strategy. Firstly, a homemade wearable brain computer interface (BCI) is used to monitor and collect the EEG signals in the simulation environment of drowsiness driving. Secondly, the neural networks with Inception module and improved AlexNet module are trained to classify the EEG signals. Finally, the early warning strategy module will function and it will sound an alarm if the heavy truck driver is judged as drowsy. The method was tested on driving EEG data from simulated drowsiness driving. The results show that using neural network with Inception module reached 95.59% correct classification in a one second time window and using improved AlexNet module reached 94.68%. The simulation and test results demonstrate the feasibility of the proposed drowsiness detection method for heavy truck driving safety.

Semi-autonomous control schemes can address the limitations of both teleoperation and fully autonomous robotic control of rescue robots in disaster environments by allowing a human operator to cooperate and share such tasks with a rescue robot as navigation, exploration, and victim identification. In this paper, we present a unique hierarchical reinforcement learning-based semi-autonomous control architecture for rescue robots operating in cluttered and unknown urban search and rescue (USAR) environments. The aim of the controller is to enable a rescue robot to continuously learn from its own experiences in an environment in order to improve its overall performance in exploration of unknown disaster scenes. A direction-based exploration technique is integrated in the controller to expand the search area of the robot via the classification of regions and the rubble piles within these regions. Both simulations and physical experiments in USAR-like environments verify the robustness of the proposed HRL-based semi-autonomous controller to unknown cluttered scenes with different sizes and varying types of configurations.

In this paper, we present a robust and accurate algorithm for interactive image segmentation. The level set method is clearly advantageous for image objects with a complex topology and fragmented appearance. Our method integrates discriminative classification models and distance transforms with the level set method to avoid local minima and better snap to true object boundaries. The level set function approximates a transformed version of pixelwise posterior probabilities of being part of a target object. The evolution of its zero level set is driven by three force terms, region force, edge field force, and curvature force. These forces are based on a probabilistic classifier and an unsigned distance transform of salient edges. We further propose a technique that improves the performance of both the probabilistic classifier and the level set method over multiple passes. It makes the final object segmentation less sensitive to user interactions. Experiments and comparisons demonstrate the effectiveness of our method.

In this technical sketch, we adopt the level set method for image segmentation that integrates region statistics and edge responses. It is well-known that a serious limitation of existing level set algorithms for image segmentation is that the final result is sensitive to the location of the initialization. This is because level set evolution is typically driven by forces computed from local image data. We overcome this problem by adopting a novel level set function based on foreground probabilities, and further integrating the level set method with a probabilistic pixel classifier [Liu and Yu 2012]. Since an accurate classifier does not exist at the beginning, the segmentation framework is based on the expectation-maximization (EM) algorithm. In summary, the motivations for our method based on level sets of probabilities are manifold.

Diffusion kurtosis imaging (DKI) is a recent approach in medical engineering that has potential value for both neurological diseases and basic neuroscience research. In this letter, we develop a robust method based on adaptive spherical integral that can compute kurtosis based quantities more precisely and efficiently. Our method integrates spherical trigonometry with a recursive computational scheme to make numerical estimations in kurtosis imaging convergent. Our algorithm improves the efficiency of computing integral invariants based on reconstructed diffusion kurtosis tensors and makes DKI better prepared for further clinical applications.

Diffusion kurtosis imaging (DKI) is a recent MRI based method that can quantify deviation from Gaussian behavior using a kurtosis tensor. DKI has potential value for the assessment of neurologic diseases. Existing techniques for diffusion kurtosis imaging typically need to capture hundreds of MRI images, which is not clinically feasible on human subjects. In this paper, we develop robust denoising and model fitting methods that make it possible to accurately reconstruct a kurtosis tensor from 75 or less noisy measurements. Our denoising method is based on subspace learning for multi-dimensional signals and our model fitting technique uses iterative reweighting to effectively discount the influences of outliers. The total data acquisition time thus drops significantly, making diffusion kurtosis imaging feasible for many clinical applications involving human subjects.

This paper analyzes track-terrain and vehicle-manipulator interactions and develops posture optimization algorithms for a reconfigurable tracked mobile modular manipulator negotiating slopes. A tracked mobile robot is associated with unavoidable slippage due to the fact that there are infinite number of contact points between the tracks and the terrain. Furthermore, the reconfiguration of the tracked mobile robot, motion of the onboard manipulator, as well as the centrifugal forces give rise to transfer of load distribution, complicating track-terrain interactions. For a tracked mobile manipulator negotiating slopes, posture optimization is essential for enhancing the traction performance, improving the efficiency of power consumption and avoiding tip-over instabilities. In this paper, track-terrain and vehicle-manipulator interactions are analyzed for a reconfigurable tracked mobile modular manipulator negotiating slopes, and a real-time posture optimization algorithm is developed by online reconfiguring the tracked mobile platform or adjusting motion of the onboard manipulator. The effectiveness of the developed algorithms has been verified by simulations and experiments.

This paper presents an innovative spring assisted modular and reconfigurable robot (MRR) design and control framework, which is developed based on a synergetic integration of robot control with a brake and an embedded spring at each modular joint. By activating the brake, static balancing can be established, allowing reinforced delicate operation in the neighborhood of a balanced configuration such as door opening, as well as spring assisted lift of heavy payload. The developed spring assisted MRR can improve the payload to weight ratio of the conventional robot manipulators without introducing sophisticated mechanisms. A distributed control method has been proposed to facilitate control of the spring assisted MRR. The developed control algorithm does not rely on a prior dynamic models and can suppress uncertainties introduced by module reconfigurations as well as uncertainties due to sensor inaccuracies and noises. With the developed controller, control parameters need not to be adjusted when adding modules to or removing modules from an MRR, or changing its configurations. Prototype modules have been developed, and the experimental results have confirmed the effectiveness of the proposed design and control.

This paper presents the investigation on mobile manipulation of a self-reconfigurable tracked mobile robot, using its tracks for both manipulation and locomotion. It is desirable for a mobile robot to possess manipulation capability in unstructured environments, especially in the scenario which is unsuitable for human beings. However, it is not convenient for such a mobile robot to carry an onboard manipulator and perform grasping and placing operations. An alternative is to realize the manipulation potential of the existing parts and perform manipulation without attaching additional hardware. Besides the enhanced locomotion ability, a self-reconfigurable tracked mobile robot has great potential in manipulation, which may take the forms of box-pushing, cylinder-moving or lateral hitting. However, the manipulation with tracks has to be controlled properly. One challenge is to optimize the tracks' configuration so as to get the optimal contact point. Furthermore, the speed and acceleration of the mobile robot have dramatic influence on mobile manipulation with tracks. To verify the effectiveness of the proposed algorithms, experiments are conducted using a tracked mobile robot in our laboratory.

This paper presents a systematic method to establish the kinematics model for a tracked mobile manipulator on firm grounds, with consideration of the interactive motions between the tracks and the terrain as well as those between the tracked vehicle and the onboard manipulator. Kinematics modeling for a tracked mobile manipulator is an intractable problem, because there are infinite number of contact points between the tracks and the terrain which makes slippage unavoidable. The track-terrain and vehicle-manipulator interactions make the problem even more complex and difficult to solve since the motion of the onboard manipulator and the centrifugal forces during moderate or high speed motion will give rise to transfer of the load distribution, which may affect the longitudinal and lateral tractive forces and the resistance. This work aims at developing a general kinematics modeling approach, which lays a solid foundation for automatic control of tracked mobile manipulators.

A novel design of a mobile parallel manipulator (MPM), which is composed by a multi-degree of freedom (DOF) parallel robot and an autonomous wheeled mobile platform, is proposed in this paper to overcome the shortcomings of the parallel robot and perform high accuracy tasks. Both the position and differential kinematics problems for the hybrid system are solved in details, and the dynamic model for the MPM is derived via Lagrangian formulation approach with simplifying hypotheses. Furthermore, taking the MPM self motion into consideration due to its redundancy, the dynamic control in task space is implemented by employing a model-based controller. Simulation results illustrate that not only the control algorithms are effective well, but also the established dynamic models are accurate enough as well

This paper addresses the multiple tasks performing issues for redundant nonholonomic mobile manipulators. An extended gradient projection redundancy resolution scheme is proposed which can determine the directions of self-motion to perform multiple secondary tasks. This scheme is easy to use and can avoid algorithm singularities. A general dynamic modeling method is presented in consideration of nonholonomic constraints, interactive motions and self-motions. A real-time fuzzy logic self-motion planner is devised to create desired self-motion magnitudes and a robust adaptive neural-network controller is designed to accomplish multiple secondary tasks without affecting the primary one in the workspace. The effectiveness of the proposed algorithm is verified through simulations for a 3DOF manipulator atop a 3-wheeled mobile platform system

This paper presents a new algorithm for automatic overturn prevention and path following control of redundant nonholonomic mobile modular manipulators. According to modular robot concept, a new dynamic modeling method is proposed in consideration of interactive motions, nonholonomic constraints and self-motions. Then, an online self-motion planner (SMP) and a robust adaptive neural-fuzzy controller (RANFC) are devised; the former is used to generate desired self-motions in a real-time manner, while the latter is used to prevent the robot from overturning and to control the end-effector to follow a desired spacial trajectory at the same time. The proposed algorithm does not need exact apriori knowledge of dynamic parameters and can suppress bounded external disturbance effectively. Simulation results for a real robot demonstrate that the proposed algorithm is effective.

The joint parameters of redundant manipulators are prerequisite data for effective dynamics control. An identification method via fuzzy theory and Genetic Algorithm has been presented to study modular redundant robots. The Genetic Algorithm is used in the fuzzy optimization expecting to obtain global optimal solutions. Experimental modal analysis and Finite Element Method have been exploited in dynamics modeling. The joint parameters of a 9-DOF modular redundant robot have been identified. Active vibration control has been approached to a simplified 4-DOF modular manipulator by DOF reduction to the 9-DOF modular manipulator.