Multi-sensor-fusion-based unstructured environment understanding method

Abstract

The invention discloses a multi-sensor-fusion-based unstructured environment understanding method, which comprises the following steps of: firstly, registering and aligning the characteristic information of each vision sensor, and projecting the characteristic information to a current vehicle coordinate system; secondly, extracting fused road edges by adopting a confidence-weighting-based road edge characteristic extraction method; thirdly, performing inter-frame data comparison and judgment on the fused road edges to obtain more stable road edges; fourthly, extracting a passable area from three-dimensional radar data, and fusing the passable area with the stable road edges obtained from the vision sensors to obtain optimal road edge information; and finally performing inter-frame fusion on road edge results to reduce the change of inter-frame data and finally realize stable and reliable understanding in an unstructured environment. A confidence-weighting-based road edge fusion algorithm is adopted, so that the problem of incapability of effectively extracting road edge characteristics under the condition of a single sensor or a single frame of data is solved.

Description

technical field [0001] The invention belongs to the technical field of intelligent information processing, in particular to an unstructured environment understanding method based on multi-sensor fusion. Background technique [0002] The intelligent mobile platform is in a certain environment, and it needs to realize autonomous navigation in an unknown environment. The agent must know what kind of environment it is in, its specific position and orientation, which places around it are safe areas, and where there are dangers, and it must know exactly where the danger is. These must be based on an effective and reliable environment. based on perception. [0003] Because the working environment of the smart mobile platform is not a relatively constant indoor environment such as light and scenery, but an outdoor environment with complex and changeable light, scenery, weather, seasons and geographical location. Moreover, a single sensor has its own limitations, and it is difficul...

AI Technical Summary

Problems solved by technology

[0007] Due to the following characteristics of rural roads: (1) road surface coverings are various, which may be soil, gravel, asphalt and cement; It can allow one car to pass through; (3) The road boundary is varied, and most of the road boundaries are formed by the intersection of artificial paved roads and natural scenery (plants), so it cannot be soared in a simple straight line, and will change with the seasons; (4) The roughness of the road is poor, and it may be uneven, which affects the driving speed of the vehicle; (5) There are various random static or dynamic obstacles on the road surface

Therefore, the existing environmental understanding methods based on multi-sensor fusion cannot solve the problem of unstructured rural road environmental understanding.

Images