The recent advancementsin autonomous driving technology have led to an increased utilization of mobile robots across various industries. Notably, four-wheel steering robots have gained significant attention due to their robustness and agile maneuvering capabilities. This paper presents a novel four-wheel steering robot platform for research purposes and an adaptive four-wheel steering control algorithm for efficient manual operation. The proposed robot platform is specifically designed as a simple and compact research-oriented platform for developing navigation and manual operation of four-wheel steering robots. The compact design of the robot platform allows for additional space utilization, while the horizontal independent steering system provides precise control and enhanced maneuverability. The adaptive four-wheel steering control algorithm aims to offer efficient and intuitive manual operation of the four-wheel steering robot, aligning with the intentions of the human operator. It enables the platform to utilize front-wheel steering under normal circumstances and efficiently reduce the turning radius by employing rear wheel steering when additional steering input is required. Experimental results demonstrated the accurate steering performance of the robot platform and effectiveness of the adaptive steering algorithm. The developed four-wheel steering robot platform and the adaptive steering control algorithm serve as valuable tools for further research and development in the fields of autonomous driving and steering algorithms.

Visual object tracking is the process of tracking an arbitrary object in a video, where the bounding box of the object is given in the first frame. Siamese network-based visual object tracking approaches have recently received considerable attention for their high speed and superior performance. However, for scale and angle estimation, Siamese trackers require multiple search regions, which increases the computation time, thereby decreasing the real-time tracking performance. This paper proposes a oneshot Siamese network, named Siam-OS, for fast and efficient visual object tracking. Siam-OS uses only a single search region and estimates the scale and angle of the target bounding box. This significantly reduces the number of computations required for deep convolutional feature extraction, and thus increases the tracking speed. Experimental results with Visual Object Tracking (VOT) benchmarks show the effectiveness of the proposed Siam-OS in terms of the accuracy, robustness, expected average overlap, and speed.

The visual object tracking problem seeks to track an arbitrary object in a video, and many deep convolutional neural network-based algorithms have achieved significant performance improvements in recent years. However, most of them do not guarantee real-time operation due to the large computation overhead for deep feature extraction. This paper presents a single-crop visual object tracking algorithm based on a fully convolutional Siamese network (SiamFC). The proposed algorithm significantly reduces the computation burden by extracting multiple scale feature maps from a single image crop. Experimental results show that the proposed algorithm demonstrates superior speed performance in comparison with that of SiamFC.

This paper presents a novel local planning approach called Agile and SAfe Pursuit (ASAP) for autonomous mobile robots. It aims to enable agile path following and safe collision avoidance in cluttered environments, while ensuring computational efficiency for real-time performance in embedded systems with limited computational power. For agile path following, the proposed approach utilizes a local path that includes a line path, arc path, and in-place rotation, and generates a target velocity based on the kinematic constraints of the robot. For safe collision avoidance, the proposed approach uses obstacle information to generate safety corners, which represent points in free space to circumvent obstacles with arbitrary shapes, and selects the best safety corner with the minimum travel time. To reach the target velocity as quickly as possible, the proposed approach uses a normalized velocity space to calculate control velocity that achieves the ratio of the linear and angular components of the target velocity in the shortest possible time period. For end-users to easily adapt a robot’s behavior to different environments, the proposed approach is designed to require only a few tuning parameters. The proposed algorithm’s agile control, rigorous collision avoidance, and computational efficiency were demonstrated through experimental results from hardware-in-the-loop simulations under various scenarios and real-robot tests in cluttered environments. Remarkably, the proposed approach achieves computational speeds that are 25 to 200 times faster than other existing algorithms.