In recent years, object-oriented simultaneous localization and mapping (SLAM) has attracted increasing attention due to its ability to provide high-level semantic information while maintaining computational efficiency. Some researchers have attempted to enhance localization accuracy by integrating the modeled object residuals into bundle adjustment. However, few have demonstrated better results than feature-based visual SLAM systems, as the generic coarse object models, such as cuboids or ellipsoids, are less accurate than feature points. In this paper, we propose a Visual Object Odometry and Mapping framework VOOM using high-level objects and low-level points as the hierarchical landmarks in a coarse-to-fine manner instead of directly using object residuals in bundle adjustment. Firstly, we introduce an improved observation model and a novel data association method for dual quadrics, employed to represent physical objects. It facilitates the creation of a 3D map that closely reflects reality. Next, we use object information to enhance the data association of feature points and consequently update the map. In the visual object odometry backend, the updated map is employed to further optimize the camera pose and the objects. Meanwhile, local bundle adjustment is performed utilizing the objects and points-based covisibility graphs in our visual object mapping process. Experiments show that VOOM outperforms both object-oriented SLAM and feature points SLAM systems such as ORB-SLAM2 in terms of localization. The implementation of our method is available at https://github.com/yutongwangBIT/VOOM.git.

We propose a dense mapping algorithm based on surfel with line constraint, called SLD-MAP for room-scale and urban-size environment, which aims to improve reconstruction accuracy and reduce void space on the reconstruction surface. We apply visual odometry to estimate camera poses, and reconstruct the 3D environment according to the input depth image and RGB image. The first step is to optimize the pose with line constraints. The second step is to extract the superpixel and resize the radius and position of the superpixel with line constraints. The third step is to generate surfels and fuse them with local maps. The fourth step is plane fitting of local map. The last step is to update the local map and deform the global map. Finally, the reconstruction accuracy is evaluated on public datasets, compare with the state-of-the-art methods.

This paper designs a fault-tolerant controller for the path-following of independently actuated (IA) electric autonomous vehicles (AVs) with steer-by-wire (SBW) systems. Such a controller can handle the effect of steering motor fault and the bounded disturbances of the vehicle dynamic system. Firstly, we formulate the dynamic models of the vehicle, the tire, the SBW system, and the steering motor. Secondly, with the models, we identify the effectiveness coefficient of the steering motor and calculate the steering resistance torque. Both the two parameters are used to determine the potential maximum front-wheel angle. The effectiveness coefficient can determine when the control system switches to the fault-tolerant control (FTC) mode. For the FTC mode, we then introduce a tube-based model predictive control (MPC) framework to guarantee vehicle stability in steering processes and maintain the tracking performance. The disturbances of the vehicle dynamic system affect both the control input and the state. On one hand, the disturbances are formulated to be a tightened state constraint. On the other hand, together with the potential maximum front-wheel angle, the disturbances are formulated to be a tightened input constraint. Finally, we show the effectiveness of the designed fault-tolerant controller via Carsim-Simulink joint simulation and real-vehicle experiment.

This paper proposes a multi-hop distributed sensor network localization method based on UWB ranging measurements. Different from the positioning algorithm suitable for known indoor environments, this algorithm is designed for the exploration needs of unknown areas. Based on the barycentric coordinates of the tetrahedron, the expansion of the sensor network is realized through the multi-hop of the UWB sensor. The proposed algorithm can be applied for three-dimensional space. By designing time-varying weight coefficients and combining Taylor expansion, the localization performance is enhanced. Finally, a numerical simulation is given to verify the effectiveness of the proposed algorithm.

This paper proposes a positioning method using an adaptive Kalman filter (AKF) with linear equality road constraints. The AKF algorithm used in vehicle localization can adaptively adjust the covariance matrices of both the system noise and the measurement noise based on the innovation sequence. Linear equality road constraints incorporated into AKF architecture can restrict the unconstrained position estimates to the constraint set via projection method and then give the final positioning results. Finally., two simulation cases based on segmented straight roads are provided to show the effectiveness of the proposed method.

Human activity recognition plays a unique role in many important applications, including ubiquitous computing, health-care services, and smart buildings. Due to the nonintrusive property of smartphones, smartphone sensors are widely used for the identification of human activities. Since the signals of smartphone sensors are quite noisy, feature engineering will be performed to extract more discriminant representations. Then, various machine learning algorithms can be employed to recognize different human activities. Extreme learning machine (ELM) has been shown to be effective in classification tasks with extremely fast learning speed. Due to its randomness property, it is naturally suitable for ensemble learning. In this paper, we propose a novel ensemble ELM algorithm for human activity recognition using smartphone sensors. Gaussian random projection is employed to initialize the input weights of base ELMs. By doing this, more diversities can be generated to boost the performance of ensemble learning. Real experimental data has been applied to evaluate the performance of our proposed approach. We also conduct a comparison of the proposed approach with some state-of-the-art approaches in the literature. The experimental results indicate that our proposed ensemble ELM approach outperforms these approaches and can achieve recognition accuracies of$\text{97.35}\%$and$\text{98.88}\%$on two datasets.

Human activity recognition can benefit various applications including healthcare services and context awareness. Since human actions will influence WiFi signals, which can be captured by the channel state information (CSI) of WiFi, WiFi CSI based human activity recognition has gained more and more attention. Due to the complex relationship between human activities and WiFi CSI measurements, the accuracies of current recognition systems are far from satisfactory. In this paper, we propose a new deep learning based approach, i.e., attention based bi-directional long short-term memory (ABLSTM), for passive human activity recognition using WiFi CSI signals. The BLSTM is employed to learn representative features in two directions from raw sequential CSI measurements. Since the learned features may have different contributions for final activity recognition, we leverage on an attention mechanism to assign different weights for all the learned features. Real experiments have been carried out to evaluate the performance of the proposed ABLSTM for human activity recognition. The experimental results show that our proposed ABLSTM is able to achieve the best recognition performance for all activities when compared with some benchmark approaches.

Occupant detection using carbon-dioxide sensors is prevalent but its accuracy is restricted by the inherent sensing delays. This paper proposes an indoor occupant detection method using real-time carbon-dioxide and Pyroelectric Infrared (PIR) sensor measurements overcoming the sensing delays. The occupancy detection problem is formulated as a classification problem wherein the classifier learns from offline carbon-dioxide data and the actual occupancy measurements of the room. While the classifier can provide realtime occupancy detection, the delays in carbon-dioxide sensors influence their accuracy. To overcome the delays, observations from PIR sensors are combined with the results of the single-layer feedforward neural network (SLFN) based classifier. The classifier works in four steps: (i) data-preprocessing, (ii) feature-selection, (iii) learning, and (iv) validation. The data is preprocessed by smoothing and several features are selected as input to the SLFN. Then, the classifier is validated with realtime experiments. Our results demonstrate that the proposed approach provides accuracy up to 99.79% and also overcomes the delays found in carbon-dioxide sensors.

This study proposes a novel method of energy efficiency improvement in Air-Conditioning and Mechanical Ventilation (ACMV) systems on the basis of occupant thermal states (ComforyDiscomfort) evaluated by Predictive Thermal State (PTS) models. An ACMV Operating State (OS) algorithm is proposed and integrated with PTS models under assumptions of Markov Decision Process (MDP). The ACMV OS algorithm and the developed PTS models are applied in our thermal laboratory. The results show that NN based PTS models perform better than ELM based ones in terms of energy saving in our case studies. The optimal sampling time of the applied ACMV OS algorithm is 10 mins without the issues of system lagging and losing sharpness of tracking thermal states of occupants. The experimental results show that the proposed ACMV OS algorithm can significantly reduce around 10 kWh out of 74 kWh (about 13.5% energy saving) daily in laboratory conditions without compromising the thermal comfort level of occupants.

This paper provides a new approach to reconstruct a fluid field from sparse sensor observations. Using the extreme learning machine (ELM) autoencoder, we can extract a dominant basis of the fluid field of interest from a database consisting of a series of fluid field snapshots obtained from offline computational fluid dynamics (CFD) simulations. The output weights of ELM autoencoder can be viewed as the compressed feature representations of the fluid field and represent the dominant behaviors of the database. With such a compressed representation, the fluid field of interest can be easily reconstructed from sparse sensor observations. The simulation results show that the new compressed representation approach can achieve better reconstruction accuracy as compared with the traditional principal component analysis (PCA) method.