Zhangjun Song

Real-time vehicle detection based on Haar features and Pairwise Geometrical Histograms

The Pairwise Geometrical Histograms (PGH) is a generalization of Chain Code Histogram(CCH). It is a powerful shape descriptor that is applied to contours matching which is not affected by rotation. As we know, this method is seldom used for vehicle detection. Feature extraction is a very common and useful method of pattern recognition. In recent years, the Viola and Jones rapid object detection approach became very popular. In this paper, we combine the Haar features and PGH together for vehicle detection. We discuss three methods: the vehicle detection using only Haar features, Haar features combined with hu moments and Haar features combined with PGH. The experimental results show that the last one has the best performance.

A novel high adaptability out-door mobile robot with diameter-variable wheels

A novel high adaptability out-door mobile robot with diameter-variable wheels was proposed in this paper. The robot has advantages of good climbing obstacle capability, high terrain adaptability and stability for the self-adapting suspension and walking wheel combining the efficiency of wheels with the climbing mobility of legs. The mechanism structure and working principle were described. The kinematics model and dynamic model are presented of the folding and unfolding of the wheel and interaction between wheel and terrain respectively. A simulation in MSC.ADAMS has been carried out to verify the operation and the reality of the prototype. The simulation results show that the robot with diameter-variable wheels has good performance of climbing obstacles in the rough terrain.

Catering service robot

Catering service robot working in restaurants is integrated with autonomous mobile, multi-sensor data fusion, and multimodal human computer interaction techniques. Catering service robot can replace or partially take place of the restaurant staffs; it has good marketing effectiveness and potential profitable advantages. In this paper the design of a catering service robot is introduced. Beautiful appearance is used on the robots upper body; the wheeled mobile platform is installed in the bottom of the robot. The robot can be used for customers ordering dishes and offers delivering services in the restaurant with a friendly interactions and self-mobility. The paper analyzes the catering service robot system and describes the framework of the hardware platform and mechanical structure. The software system of the robot includes the motor unit of software module, the realization of autonomous mobile and ordering software module. Finally, the simulation and experiments are carried out.

Model-based state recognition of bone drilling with robotic orthopedic surgery system

Screw path drilling is an important process among many orthopedic surgeries. To guarantee the safety and correctness of this process, a model-based drilling state recognition method is proposed in this paper. The thrust force in the drilling process is modeled based on an accurate 3D bone model restructured by means of Micro-CT images. In theoretical modeling of the thrust force, the resistance and the elasticity of the bone tissues are considered. The cutting energy and elastic modulus are defined as the material parameters in the theoretical model, which are identified via a least square method. Some key parameters are proposed to support the state recognition: the peak forces in the first and the second cortical layers, the average force in the cancellous layer and the thickness of each layer. Based on these key parameters in the model, a state recognition strategy with a robotic orthopedic surgery system is proposed to recognize the switch position of each layer. Experiments are performed to demonstrate the effectiveness of the modeling approach and the state recognition method.

Domestic robots with multi-function and safe internet connectivity

This paper presents a kind of domestic robot with multi-function such as cleaning, surveillance. The domestic robot is mainly composed of four functional modules, namely motion and cleaning module, vision module, sensory module, and GSM module. Motion and cleaning module is a mobile platform with cleaning tools. The main part of the vision module is an IP camera, which is used for telepresence. The sensory module is made up of some sensors apperceiving the surrounding and detecting anomalies. The GSM module is just like a mobile phone, which could send messages to an appointed telephone. The security of Internet connecting in our proposed design is described detailedly. Through the Internet or mobile phones, we could accomplish telepresence and take remote control of the domestic robot. The experimental results show the implement of cleaning, surveillance and remote control.

Kinematics and cooperative control of a robotic spinal surgery system

Spinal surgery is considered a high-risk surgery. To improve the accuracy, stability, and safety of such operations, we report the development of a novel six-degrees-of-freedom Robotic Spinal Surgical System that can assist surgeons in performing transpedicular surgery, one of the most common spinal surgeries. After optimization performed using Response Surface Methodology, the largest available workspace of the robot is determined and is found to easily cover the entire operation area. Cooperative control and navigation-based active control are implemented for different processes of the operation. We propose a hybrid control approach based on the speed and torque interface at the joint level. In this mode, the robot is compliant in Cartesian space, benefitting both the accuracy and efficiency of the operation. A comprehensive assessment index, combining the subjective and objective criteria in terms of positioning and operation efficiency, is proposed to compare the performance of cooperative control in speed mode, torque mode, and hybrid control mode. Active fine adjustment experiments are carried out to verify the positioning accuracy, and the results are found to satisfy the requirements of operation. As an application example, a pedicle screw insertion experiment is performed on a pig vertebral bone, demonstrating the effectiveness of our system.

A localization algorithm for low-cost cleaning robots based on kalman filter

A novel localization algorithm with low-cost sensors for cleaning robots is presented in this paper, which includes fusing the data of encoders and an electronic compass to estimate the posture state of the robot by using Kalman filter. It judges the confidence of the data of the electronic compass with magnetic field intensity; judges the confidence of data of odometer by the information of slippage and collision. A coverage strategy and map construction methods with the localization algorithm are also introduced. Experimental results show that the proposed algorithm can achieve adequate localization precise enough for complete coverage and the cleaning robots have a superior coverage ratio with the coverage strategy.

Error propagation of the robotic system for liver cancer coagulation therapy

The goal of this paper is to establish the error propagation model of the ultrasound-guided robot for liver cancer coagulation therapy, which consists of ultrasound machine, image-guided software subsystem, position tracking unit and needle-driven robot. The target of tumor is transformed to robot coordinate frame to let the robot move to the target. The transformation includes three dimension ultrasound construction, registration between pre-operative model and intra-operative physical body, coordinate transformation from position tracking unit to robot. The factors affecting the system accuracy can be expressed by the sum of target mapping error and robot positioning error. Then, the propagation model of target mapping error on the Euclidean motion group is established. At last, the simulations of the propagation model of target mapping error and the experiment of the system accuracy are carried out and the results show our proposed error propagation model is efficient and the system accuracy can satisfy the need of coagulation therapy for liver cancer.

Point-based registration using Extended Kalman Filter in medical robotic system

The goal of this paper is to develop a needle insertion robotic system for ultrasound-guided minimally invasive surgery, which is composed of a robot, a surgical planning subsystem and a pose tracking device. In the surgery procedure, the target coordinate should be transformed from one coordinate frame to another coordinate frame through point-based registration. The point-based registration using Extended Kalman Filter is proposed and the state estimation is given by the transformation matrix solved by the traditional Singular Value Decomposition method. In this case, the Extended Kalman Filter can quickly converge and avoid trapped in local minima of the function. Then, the simulation experiment is carried out to evaluate the proposed method accuracy and system accuracy. The results demonstrate that the proposed methods improve the coordinate transformation accuracy and the efficiency of the medical robotic system.