Target recognition is a challenging task for human following of mobile service robots. In this paper, we combine the principal-component-analysis (PCA)-based face recognition with the tracking-learning-detection applied to the human face (Face-TLD) to obtain an improvement, named as IFace-TLD. The proposed IFace-TLD can significantly improve the discrimination ability of the Face-TLD for ambiguous facial appearances. To further deal with motion uncertainties of the human head, especially the sudden motion change, which makes face-based target recognition methods unstable or even loses the target, a skeleton-based model is introduced to improve the accuracy and robustness of the target recognition. Specifically, within a walk half-cycle, the skeleton features are extracted from the upper-body three-dimensional skeleton coordinates. Then, the extracted skeleton features are fed into the support vector data description (SVDD) to identify the target person when the IFace-TLD becomes invalid. The seamless fusion of the skeleton recognition and the IFace-TLD, named as the SIFace-TLD, significantly enhances the robustness in complex scenarios, especially for people tracking from both front and behind. To achieve a complete human following system, the particle filter (PF) is adopted for estimating the state of the human motion. And then, a controller is designed to maintain the relative position between the robot and the target. Experimental results demonstrate that the proposed IFace-TLD is more accurate and flexible than the original Face-TLD. And the SIFace-TLD shows a robust performance to human motion uncertainties. Moreover, the developed controller can achieve a satisfactory human following performance.

Visual place recognition is a challenging problem in simultaneous localization and mapping (SLAM) due to a large variability of the scene appearance. A place is usually described by a single-frame image in conventional place recognition algorithms. However, it is unlikely to completely describe the place appearance using a single frame image. Moreover, it is more sensitive to the change of environments. In this article, a novel image-sequence-based framework for place detection and recognition is proposed. Rather than a single frame image, a place is represented by an image sequence in this article. Position invariant robust feature (PIRF) descriptors are extracted from images and processed by the incremental bag-of-words (BoWs) for feature extraction. The robot automatically partitions the sequentially acquired images into different image sequences according to the change of the environmental appearance. Then, the echo state network (ESN) is applied to model each image sequence. The resultant states of the ESN are used as features of the corresponding image sequence for place recognition. The proposed method is evaluated on two public datasets. Experimental comparisons with the FAB-MAP 2.0 and SeqSLAM are conducted. Finally, a real-world experiment on place recognition with a mobile robot is performed to further verify the proposed method.

In this paper, a new systematical method for extracting tree trunk landmarks from 3D point clouds of cluttered forested environments is proposed. This purely geometric method is established on scene understanding and automatic analysis of trees. The pipeline of our method includes three steps. First, the raw point clouds are segmented by utilizing the circular shape of trees, and segments are grouped into tree sections based on the principle of spatial proximity. Second, circles and axes are extracted from tree sections which are subject to loss of shape information. Third, by clustering and integrating the tree sections resulted from various space inconsistencies, straight tree trunk landmarks are finally formed for future localization. The experimental results from real forested environments are presented.

This paper presents a new feature based scan matching method for solving 6D localization problem in forested environments. The proposed registration process includes two steps. First, the largest group of approximately parallel tree trunk features is utilized to align successive scans along the five dimensions except z direction. Tree correspondences are established by matching point patterns which are abstracted from the position relationships of trees. The optimal 5D transformation is thus determined based on the axes of two key tree pairs which are selected by evaluating their ability of tree alignment. Second, we assign the ground points of two scans into a grid of cells, and minimize z-direction difference of points in shared cells. The experimental results on data collected in real forested environments have demonstrated the effectiveness of this method.

A cooperation approach with consideration of communication limit is proposed for multi-robot area exploration, in which all the robots select local destinations satisfying the constraints on communication range and reach their destinations at the same time to communicate and fuse their map information. Firstly, the robots compute the frontier between the explored region and the unexplored one. The robots choose the optimal frontier points, which maximize information gain, minimize navigation cost and satisfy communication limit as their local destinations. Then the problem of global exploration in unknown environment is converted into that of multi-stage trajectory planning in local known environment. Collision-free, synchronous and separate trajectories are planned for all the robots to realize the limited communication at their destinations. In such a way, efficient and distributed exploration can be achieved. Simulation results are presented to show the effectiveness of our method.

This paper investigates the on-line autonomous distribution for landmarks and the active exploration in environment without or lack of landmarks/features, such as disaster conditions and polar region. In such situation, the robot enters the environment carrying some landmarks and distributes them according to the rules given in this paper. The utility of the landmark distribution is analyzed. Then, based on the extended Kalman filter (EKF), the active exploration is converted into a problem of multi-objective optimization, in which the objective function includes three aspects, i.e. the accuracy of localization and mapping, the predictive area of the unknown environment that will be explored in next step and the information gain provided by the distributed landmarks respectively. The robot chooses the control input that optimizes the objective function such that accurate localization, high-quality mapping and complete exploration will be realized. And then, the supplementation and the redundancy elimination for landmarks are implemented. At last, a set of simulations is presented to show the effectiveness of our approach.

Path planned for tractor-trailer mobile robot (TTMR) does not seem to be easily adapted to the case when the number of the trailers increases, thus the repetitive path planning has to be introduced. For this problem, this paper investigates the connection relation of TTMR with variable structure, i.e. the number of the trailers is variable, and deals with the optimization design for it to avoid the repetitive path planning when the number of the trailers increases. After analyzing the motion trajectories of TTMR, we establish the quantitative relationship for the motion characteristics between the transient course and the steady state. Based on which, a new design method to optimize the connection relation for variable-structure TTMR is proposed. In our scheme, the length of each connecting rod between two adjacent bodies is adjusted properly such that the transient deviations of the trailers from the path followed by the tractor will be less than the steady ones. In such a way, the path planned for TTMR can also be appropriate for the case when the number of the trailers varies. The simulations and experiments show the validity of our method