论文信息 - A Logical Account of Perception Incorporating Feedback and Expectation

A Logical Account of Perception Incorporating Feedback and Expectation

This paper presents the theoretical foundations of a vision system in which the effects of highlevel reasoning percolate all the way down to influence the low-level processing of raw sensor data. This is achieved through the mechanisms of feedback and expectation. The main contribution of the paper is to present a formal framework, based on the abductive interpretation of sensor data, that incorporates the ideas of feedback and expectation in a way that marries them to logical reasoning. To enable this, two alternative measures of explanatory value are defined.

Murray Shanahan | M. Shanahan

[1] Hector J. Levesque,et al. What Is Planning in the Presence of Sensing? , 1996, AAAI/IAAI, Vol. 2.

[2] Murray Shanahan,et al. Robotics and the Common Sense Informatic Situation , 1996, ECAI.

[3] Rangachar Kasturi,et al. Machine vision , 1995 .

[4] Mark Witkowski,et al. From Images to Bodies: Modelling and Exploiting Spatial Occlusion and Motion Parallax , 2001, IJCAI.

[5] Jack Minker,et al. Logic-Based Artificial Intelligence , 2000 .

[6] Patrick Cavanagh,et al. Top-down processing in vision , 1999 .

[7] David Poole. Logic Programming for Robot Control , 1995, IJCAI.

[8] Hector J. Levesque,et al. The Frame Problem and Knowledge-Producing Actions , 1993, AAAI.

[9] Murray Shanahan,et al. Reinventing Shakey , 2001 .

[10] Murray Shanahan. Noise, Non-Determinism and Spatial Uncertainty , 1997, AAAI/IAAI.

[11] John R. Josephson,et al. Abductive inference : computation, philosophy, technology , 1994 .

[12] Yiannis Aloimonos,et al. Active vision , 2004, International Journal of Computer Vision.

[13] Dana H. Ballard,et al. Animate Vision , 1991, Artif. Intell..