Narrow Results

With the rapid development of computer technology and electronics industry, computer processing capability and image processing technology have been greatly improved, making robots based on computer processing and image processing have entered a new development in the field of navigation path recognition research. As an indispensable carrier for intelligent manufacturing and industrial development, robots are expanding their applications. The key to the successful execution of the mobile robot is to move according to the planned path and to avoid obstacles autonomously. These two points depend on the validity and accuracy of navigation path identification. At present, research on mobile robot navigation path recognition mainly uses visual navigation as the main method, which uses visual sensors to simulate human eye functions, obtains relevant information from external environment images, and processes them to realize related functions that the system needs to complete. The two major problems in visual navigation are poor recognition ability and insufficient ability to resist light source interference. The main purpose of this paper is to improve the recognition ability of mobile robot navigation path and the ability to resist light source interference. It mainly uses the $K$-means algorithm for visual navigation research. By simulating the acquired image and the selected color space, the results show that the average time taken to complete a path identification method is 152ms. Under different illumination environments, the information extraction rate of mobile robot navigation path can reach 90%, and the effect of strong light on navigation path recognition is effectively reduced under strong illumination environment. The results show that the recognition of the visual navigation path of a mobile robot using the $K$-means algorithm is more precise than the conventional method, and it takes less time to better meet the timeliness requirements of mobile robots.

Desert ant (Cataglyphis) is famous for its ability in navigation. In deserts with very few visual and odor information, the ant can return to its den almost along a straight line after foraging away in a distance of much more than thousands of times longer than its body length. Several kinds of information must be acquired during its trip, and the most important two are: path integration and visual navigation. Path integration is achieved by using sky light compass based on polarized light and odometer, while visual navigation relies on landmark based memory and matching. In this paper, a survey of research work on desert ant navigation from the viewpoint of information acquisition and fusion is presented, as well as the application of these kinds of information to navigate robots, especially bionic robots cruising in strange environment.

During the last decade, significant progress has been made towards the goal of using machine vision as an aid to highway driving. This chapter describes a few pieces of representative work which have been done in the area.

The two most important tasks to be performed by an automatic vehicle are road following and collision avoidance. Road following requires the recognition of the road and of the position of the vehicle with respect to the road so that appropriate lateral control commands (steering) can be generated. Collision avoidance requires the detection of obstacles and other vehicles, and the measurement of the distances of these objects to the vehicle.

We first explain the significance of vision-based automatic road vehicle guidance. We then describe the different road models, and contrast the approaches based on model-based lane marker detection with adaptive approaches. We describe in detail the important approach of road following by recursive parameter estimation, which is the basis for the most successful systems. We then address the issue of obstacle detection, first detailing monocular approaches. We finally describe an integrated stereo approach which is beneficial not only for obstacle detection, but also for road following.