Data fusion of radar and image measurements for multi-object tracking via Kalman filtering

The aim of this paper is to propose a novel markerless human–robot interface, which is derived from the idea that the manipulator copies the movements of human hands. With this method, one operator could control dual robots through both his or her hands in a contactless and markerless environment. In order to obtain the position and orientation of human hands in real time, a sensor called leap motion (LM) is employed in this paper. However, because of the tracking errors and noises of the sensor, the measurement errors increase with time. Therefore, interval Kalman filter (IKF) and improved particle filter (IPF) are used to estimate the position and the orientation of the human hands, respectively. Furthermore, in order to avoid the perceptive limitations and the motor limitations, which prevent the operator from carrying out the high-precision experiment, a modification of adaptive multispace transformation (AMT) method is raised to assist the operator to determine the posture of the manipulator. The greatest strength of our method is that it is totally contactless and could estimate the pose of the human hands accurately and stably without any assistance from markers. A series of experiments have been conducted to verify the human–manipulator interface system, and the results show that the system is indeed of high availability and fault tolerance in teleoperation, which means even a novice can easily and successfully control robots with this human–manipulator interface.

Markerless Human–Manipulator Interface Using Leap Motion With Interval Kalman Filter and Improved Particle Filter

With the development of Industry 4.0, robots tend to be intelligent and collaborative. For one, robots can interact naturally with humans. For another, robots can work collaboratively with humans in a common area. The traditional teaching method is no longer suitable for the production mode with human–robot collaboration. Since the traditional teaching processes are complicated, they need highly skilled staffs. This paper focuses on the natural way of online teaching, which can be applied to the tasks such as welding, painting, and stamping. This paper presents an online teaching method with the fusion of speech and gesture. A depth camera (Kinect) and an inertial measurement unit are used to capture the speech and gesture of the human. Interval Kalman filter and improved particle filter are employed to estimate the gesture. To integrate speech and gesture information more deeply, a novel method of audio-visual fusion based on text is proposed, which can extract the most useful information from the speech and gestures by transforming them into text. Finally, a maximum entropy algorithm is employed to deal with the fusion text into the corresponding robot instructions. The practicality and effectiveness of the proposed approach were validated by five subjects without robot teaching skills. The results indicate that the online robot teaching system can successfully teach robot manipulators.

Online Robot Teaching With Natural Human–Robot Interaction

Kalman filter (KF) algorithm is a form of recursive optimal estimations, which utilizes information in time domain with less computational efforts to reduce the system errors. Recently, Kalman filtering technique has become a standard approach for reducing errors in a least squares sense and is widely applied in navigation and positioning fields. Unfortunately, the traditional KF needs accurate statistical information about mobile terminal; otherwise, it will result in lower precision and even divergence. To make up for the deficiency of KF algorithm, this paper presents a novel robust single global position system (GPS) navigation algorithm based on dead reckoning and strong tracking filter (STF), which still has strong tracking ability even when precise knowledge of the system models is not available. The proposed algorithm utilizes adaptive fading factor to adjust the gain matrix in real time to satisfy the orthogonality principle (OP), which indicates all useful information has been extracted from residual. Furthermore, we define residual covariance (RC) as an important index to evaluate the performance of the filtering algorithm and deduce the closed relationship of RCs in KF under the case of: 1) inaccurate system model; 2) erroneous initial value; and 3) abrupt change of states, respectively. We find that the RCs of the KF algorithm under all three above-mentioned cases have a bias compared with desired ones; as a result, they do not conform to the OP and have poor tracking ability, while the RC of STF conforms to the OP due to the fading factor which indicates the tracking performance is greatly improved in the proposed algorithm. The theoretical analysis and simulation results demonstrate that the performance of the proposed single GPS navigation algorithm based on STF outperforms that of the traditional KF algorithm.

A Robust Single GPS Navigation and Positioning Algorithm Based on Strong Tracking Filtering

The detection of indoor location based on magnetic fields collected by embedded sensors in smartphones has been progressed rapidly. Most current approaches rely on the particle filter (PF) scheme which combines the pedestrian dead reckoning (PDR) technique with patterns of previously recorded magnetic field intensity. The key challenges include inherent blindness and particle degradation problems. Here, a fusion algorithm combining the extended Kalman filter (EKF) and the PF scheme is proposed to address these issues. EKF is first used to reduce the possible location regions by fusing the PDR and magnetic field intensity results. The particle generation, update, and resampling processes are conducted afterward, and the final position is calculated by using the weighted mean of particles. As such, the blindness and particle degradation problems are alleviated by using particles in the reduced location regions at each processing step. Experiments show a localization accuracy of 1-2m when the user walks smoothly, which is better than those of traditional PF schemes, especially in cases under heavy magnetic distortions by using a reduced number of particles.

Magnetic-Based Indoor Localization Using Smartphone via a Fusion Algorithm

For a nonlinear integrated GPS/IMU system with an uncertain dynamic model, the standard extended Kalman filtering algorithm is no longer applicable. In this research, an interval filtering algorithm is applied to the uncertain integrated system. The system parameters uncertainties are described by intervals. The IAKF algorithm is established for the uncertain integrated system. The IAKF algorithm has the same structure as the standard extended Kalman filtering algorithm. The testing results indicate that the IAKF algorithm is effective for the uncertain nonlinear integrated system, and it can be used to test the chosen parameters of an integrated GPS/IMU system. Thus, the IAKF algorithm has good potential in real-time applications for nonlinear integrated systems with parameter and noise uncertainties.

Xiufeng He

Papers

MEMS IMU and two-antenna GPS integration navigation system using interval adaptive Kalman filter