Search

A multisteering tractor–trailer mobile robot (MSTTMR) is a kind of complex multibody system, which consists of a tractor and a chain of steerable trailers. If both the tractor and the trailers can track an identical geometric path, the overall width of the system is only equal to that of the tractor or the trailer. Thus, the robot can perform transport tasks in a narrow space. The MSTTMR with one trailer is referred to as the double-steering tractor–trailer mobile robot (DSTTMR), since the system has two steering inputs. In this paper, trajectory generation and tracking control for the DSTTMR with on-axle hitching are addressed. We first propose an approach to generate the desired full-state trajectory from a desired geometric path given in the Cartesian plane, in order that the desired state trajectories of the tractor and trailer can form the same desired path. Then, a trajectory tracking controller is designed based on the backstepping technique to drive the system's states to converge to their desired trajectories. As a result, the tractor and the trailer can track the desired geometric path simultaneously. Simulation and experimental results are presented to show the effectiveness of the proposed approach. [ABSTRACT FROM PUBLISHER]

• The framework pays attention to the spatial relations in certain places. • A graph-based representation is presented to describe the environment. • Two models are fused for graph matching to perform place recognition. • Experimental evaluation to show greater precision, recall and viewpoint robustness. In the field of robotics, due to the complexity of real environments, place recognition using the 3D LiDAR is always a challenging problem. The spatial relations of internal structures underlying the LiDAR data from different places are distinguishable, which can be used to describe the environment. In this paper, we utilize the spatial relations of internal structures and propose a two-level framework for 3D LiDAR place recognition based on the spatial relation graph (SRG). At first, the proposed framework segments the point cloud into multiple clusters, then the features of the clusters and the spatial relation descriptors (SRDs) between the clusters are extracted, and the point cloud is represented by the SRG, which uses the clusters as the nodes and their spatial relations as the edges. After that, we propose a two-level matching model in which two different models are fused for accurately and efficiently matching the SRGs, including the upper-level searching model (U-LSM) and lower-level matching model (L-LMM). In the U-LSM, an incremental bag-of-words model is used to search for candidate SRGs through the distribution of the SRDs in the SRG. In the L-LMM, we utilize the improved spectral method to calculate similarities between the current SRG and the candidates. The experimental results demonstrate that our framework achieves good precision, recall and viewpoint robustness on both public benchmarks and self-built campus dataset. [ABSTRACT FROM AUTHOR]

Purpose: Selective tibial neurotomy (STN) is a surgical procedure for treating spastic equinovarus foot. Hyperselective neurectomy (HSN) of tibial nerve is a modified STN procedure, which was rarely discussed. This study aimed to describe the branching patterns of the tibial nerve and propose an optimal surgical incision of HSN for treatment of spastic equinovarus foot. Methods: Sixteen lower limbs were dissected to determine the various branching patterns of the tibial nerve and categorized according to these branching patterns. The mean distances from the nerve entry points to the tip of femur's medial epicondyle were measured, as well as their percentage to the overall length of the leg. The surgical incision was designed according to the range of these nerve entry points. Results: The tibial nerve sent out proximal and distal motor branches based on their position relative to the soleus muscle's tendinous arch. For proximal motor branches, the branches innervating the medial gastrocnemius, lateral gastrocnemius and proximal soleus were categorized into types I (9/16), II (5/16) and III (2/16). Measurements from the medial epicondyle to the nerve entry points into the medial gastrocnemius, lateral gastrocnemius and proximal soleus ranged from 14 to 33 mm (4–9% of leg length), 22–45 mm (6–12%) and 35–81 mm (10–22%), respectively. Distal motor branches including the distal soleus, posterior tibialis, flexor digitorum longus and flexor hallucis longus, were classified as types A (8/14), B (4/14) and C (2/14), with the distances from their respective terminal points to the medial epicondyle were 67–137 mm (19–39%), 74–125 mm (20–35%), 116–243 mm (33–69%) and 125–272 mm (35–77%). Conclusions: The motor branches of tibial nerve were classified into two groups and each subdivided into three types. Detailed location parameters may serve as an anatomical basis for designing incision of HSN. [ABSTRACT FROM AUTHOR]

People tracking based on multisensor information fusion is addressed. A framework is presented for fusing the laser range finder (LRF) data and the monocular camera data. Based on this framework, an LRF-based detection algorithm is proposed to identify the pairs of human legs, by combining motion information and metric features. Moreover, a geometric observation model is developed for the camera to extract both the range and bearing measurements of the target person by focusing the target’s shoes with the camera. Then, a near-optimal particle filter is designed to fuse the measurements from the LRF and the camera. To prevent the sample impoverishment, a procedure of sample diversity improvement is used after the resampling step. The full occlusion problem is solved using image matching based on speeded up robust feature. Note that either of the LRF and the camera can work independently, since both the range and bearing are simultaneously acquired from the LRF or the camera. As a result, flexible and robust tracking can be achieved. Extensive experiments demonstrate that the proposed approach achieves high tracking accuracy and robustness. Especially, only a very small number of particles suffice to maintain good tracking performance. [ABSTRACT FROM PUBLISHER]

In this paper, we focus on the unknown environments without artificial landmarks and features, such as disaster situations and polar regions. An approach to active exploration based on an on-line scheme for autonomous allocation of landmarks is proposed. Specifically, the robot carries along with itself some landmarks which are to be allocated during the exploration according to some heuristic rules. The utility of landmark allocation is analyzed and calculated. Then the active exploration is converted into a problem of multi-objective optimization. The objective function includes three weighted terms: the accuracy of localization and mapping, the coverage rate of the unknown environment and the utility of the allocated landmarks. By solving this optimization problem, control inputs of the robot are computed to guarantee that accurate localization, high-quality mapping and complete exploration can be achieved simultaneously. Moreover, supplementation and redundancy elimination of the allocated landmarks are executed to make a complete and non-redundant coverage for the environment. Finally, some landmarks, together with a device for allocating these landmarks, are developed. Both experiment and simulation results are presented to demonstrate the effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]