Sampling visual SLAM with a wide‐angle camera for legged mobile robots

Abstract

Precise localisation and navigation are the two most important tasks for mobile robots. Visual simultaneous localisation and mapping (VSLAM) is useful in localisation systems of mobile robots. The wide-angle camera has a broad field of vision and more abundant information on images, so it is widely used in mobile robots, including legged robots. However, wide-angle cameras are more complicated than ordinary cameras in the design of visual localisation systems, and higher requirements and challenges are put forward for VSLAM technologies based on wide-angle cameras. In order to resolve the problem of distortion in wide-angle images and improve the accuracy of localisation, a sampling VSLAM based on a wide-angle camera model for legged mobile robots is proposed. For the predictability of the periodic motion of a legged robot, in the method, the images are sampled periodically, image blocks with clear texture are selected and the image details are enhanced to extract the feature points on the image. Then, the feature points of the blocks are extracted and by using the feature points of the blocks in the images, the feature points on the images are extracted. Finally, the points on the incident light through the normalised plane are selected as the template points; the relationship between the template points and the images is established through the wide-angle camera model, and the pixel coordinates of the template points in the images and the descriptors are calculated. Moreover, many experiments are conducted on the TUM datasets with a quadruped robot . The experimental results show that the trajectory error and translation error measured by the proposed method are reduced compared with the VINS-MONO, ORB-SLAM3 and Periodic SLAM systems.

On the Importance of Precise Positioning in Robotised Agriculture

“…Another method of supporting position determination can be the use of a simultaneous localisation and mapping (SLAM) algorithm with passive cameras or laser scanners (often referred to as LiDARs). Depending on the main sensing modality being used, SLAM can be divided into LiDAR SLAM or visual SLAM [59,68,69]. GNSS support by LiDAR SLAM enables a more accurate estimation of the machine's position by tracking the machine's trajectory (LiDAR odometry), using static elements of the environment as a reference to determine the machine's pose [59,70].…”

“…Depending on the main sensing modality being used, SLAM can be divided into LiDAR SLAM or visual SLAM [59,68,69]. GNSS support by LiDAR SLAM enables a more accurate estimation of the machine's position by tracking the machine's trajectory (LiDAR odometry), using static elements of the environment as a reference to determine the machine's pose [59,70]. Through the use of data fusion and filtering or optimisation algorithms, it is possible to achieve high positioning precision even when satellite signals are difficult to access [62,69].…”

“…However, visual SLAM, or its simplified version, called visual odometry [68], requires identifiable objects within the field of view of the camera for effective pose tracking [59]. Hence, this approach is successfully used in agriculture when working in man-made environments (e.g., greenhouses) or near buildings, which often interfere with the correct operation of GNSS receivers by their presence [73].…”

“…The device enables objects to be accurately mapped in space in the form of a point cloud. The system can also make use of machine learning methods to distinguish between crops and weeds [57][58][59]. An unquestionable advantage of systems based on LiDAR-class sensors is their resistance to changing lighting conditions [57].…”