Representation of Behavioral Knowledge for Planning and Plan-Recognition in a Cognitive Vision System

The algorithmic generation of textual descriptions of image sequences requires conceptual knowledge. In our case, a stationary camera recorded image sequences of road traffic scenes. The necessary conceptual knowledge has been provided in the form of a so-called Situation Graph Tree (SGT). Other endeavors such as the generation of a synthetic image sequence from a textual description or the transformation of machine vision results for use in a driver assistance system could profit from the exploitation of the same conceptual knowledge, but more in a planning (pre-scriptive) rather than a de-scriptive context.A recently discussed planning formalism, Hierarchical Task Networks (HTNs), exhibits a number of formal similarities with SGTs. These suggest to investigate whether and to which extent SGTs may be re-cast as HTNs in order to re-use the conceptual knowledge about the behavior of vehicles in road traffic scenes for planning purposes.

[1]  Hector Muñoz-Avila,et al.  SHOP: Simple Hierarchical Ordered Planner , 1999, IJCAI.

[2]  Karl Schäfer,et al.  Unscharfe zeitlogische Modellierung von Situationen und Handlungen in Bildfolgenauswertung und Robotik , 1996, DISKI.

[3]  Earl D. Sacerdoti,et al.  Planning in a Hierarchy of Abstraction Spaces , 1974, IJCAI.

[4]  Hans-Hellmut Nagel,et al.  Incremental recognition of traffic situations from video image sequences , 2000, Image Vis. Comput..

[5]  Ralf Gerber,et al.  Natürlichsprachliche Beschreibung von Straáenverkehrsszenen durch Bildfolgenauswertung [online] , 2000 .

[6]  K. Fleischer,et al.  Machine-vision-based detection and tracking of stationary infrastructural objects beside inner-city roads , 2001, ITSC 2001. 2001 IEEE Intelligent Transportation Systems. Proceedings (Cat. No.01TH8585).

[7]  Amitabha Mukerjee,et al.  Visualisation of Conceptual Descriptions Derived from Image Sequences , 1999, DAGM-Symposium.

[8]  Bart Selman,et al.  Encoding Plans in Propositional Logic , 1996, KR.

[9]  James A. Hendler,et al.  UMCP: A Sound and Complete Procedure for Hierarchical Task-network Planning , 1994, AIPS.

[10]  Pietro Perona,et al.  Bayesian reasoning on qualitative descriptions from images and speech , 2000, Image Vis. Comput..

[11]  Yue Cao,et al.  Total-Order Planning with Partially Ordered Subtasks , 2001, IJCAI.

[12]  Hans-Hellmut Nagel,et al.  Natural Language Description of Image Sequences as a Form of Knowledge Representation , 1999, KI.

[13]  H.-H. Nagel,et al.  3D-model-based-vision for innercity driving scenes , 2002, Intelligent Vehicle Symposium, 2002. IEEE.

[14]  Ralf Gerber.  Natürlichsprachliche Beschreibung von Straßenverkehrsszenen durch Bildfolgenauswertung , 1999 .

[15]  Subbarao Kambhampati,et al.  A comparative analysis of partial order planning and task reduction planning , 1995, SGAR.

[16]  KambhampatiSubbarao.  A comparative analysis of partial order planning and task reduction planning , 1995 .

[17]  Hans-Hellmut Nagel,et al.  From image sequences towards conceptual descriptions , 1988, Image Vis. Comput..

[18]  James A. Hendler,et al.  HTN Planning: Complexity and Expressivity , 1994, AAAI.

[19]  Michael Haag.  Bildfolgenauswertung zur Erkennung der Absichten von Straßenverkehrsteilnehmern , 1998, DISKI.

[20]  Subbarao Kambhampati,et al.  Encoding HTN Planning in Propositional Logic , 1998, AIPS.

[21]  Hilary Buxton,et al.  Conceptual descriptions from monitoring and watching image sequences , 2000, Image Vis. Comput..

[22]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[23]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[24]  Richard Fikes,et al.  STRIPS: A New Approach to the Application of Theorem Proving to Problem Solving , 1971, IJCAI.