Map reconstruction in the factory storehouse for the purpose of autonomous vehicle using laser radar

摘要

Needs of the autonomous vehicle in indoor environment such as factory storehouses arernincreasing. Variety types of indoor vehicles are available in commercial market. However, inrnpractice to realize the autonomous vehicle, it is required to change the whole arrangement ofrnstorehouse, because of the lack of intelligence of the vehicle. Our aim in this paper is to makernautonomous vehicle more intelligent. The geometric information of the factory storehousernchanges frequently due to the turnover of the cargo. To let the vehicle run safely, real time maprnconstruction is necessary. Here, we apply in such a situation the sensor fusion technique by use ofrnthe Omni directional image sensor and laser radar. We propose a new update algorithm called SMTrn(Shift Matching Transform) that obtains region segments with trusted semi-real-time geometricrnmap. The key point of proposed update algorithm is the fusion of laser radar and Omni directionalrncamera. These have same property that keeps profile of angles. By using developed the newrnalgorithm SMT, the processing time was drastically reduced. Successful experimental result wasrnpresented at processing interval is less than 500 msec. We demonstrate to find arbitrary complexrnwalls to determine the absolute position of the vehicle. Based on experimental results on therncorridor, we demonstrate semi-real-time map reconstruction.