GEOMETRIC UNCERTAINTIES IN POLYHEDRAL OBJECT RECOGNITION

被引:6
作者
ELLIS, RE
机构
[1] Robotics and Perception Laboratory, Department of Computing and Information Science, Queen’s University, Kingston, Ont.
来源
IEEE TRANSACTIONS ON ROBOTICS AND AUTOMATION | 1991年 / 7卷 / 03期
关键词
D O I
10.1109/70.88145
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Data gathered from robotic sensors inherently contain uncertainties or errors that cause them to deviate from their nominal values. When the data are interpreted as coming from the surface of a known object, the initial errors propagate. As a result, there are further uncertainties about which object best interprets the data and also about where in space the object may lie. It is this latter uncertainty that this paper addresses. We show, by direct geometric construction, that previous uncertainty bounds on the location of polygonal or polyhedral objects can be tightened considerably. The improvement of the bounds is a result of considering the cross-coupling between rotational and translation uncertainties in the interpretation of the sensor data.
引用
收藏
页码:361 / 371
页数:11
相关论文
共 14 条
[2]  
Boissonnat J., 1984, Seventh International Conference on Pattern Recognition (Cat. No. 84CH2046-1), P745
[3]  
BOLLES RC, 1983, 1ST INT C ROB AUT RE, P413
[4]  
Brooks R. A., 1982, INT J ROBOT RES, V1, P29
[5]  
DURRANTWHYTE HF, 1987, INTEGRATION COORDINA
[6]  
Ellis R. E., 1986, Proceedings AAAI-86: Fifth National Conference on Artificial Intelligence, P632
[7]  
ELLIS RE, 1991, IN PRESS INT J ROBOT
[8]  
ELLIS RE, 1987, IEEE T ROBOTIC AUTOM, P1799
[9]  
FAUGERAS OD, 1983, 8TH P INT JOINT C AR, P996
[10]  
FAUGERAS OD, 1984, ROBOTICS RES, P425