Towards Explainable Inference about Object Motion using Qualitative Reasoning

AAAI Conferences

The capability of making explainable inferences regarding physical processes has long been desired. One fundamental physical process is object motion. Inferring what causes the motion of a group of objects can even be a challenging task for experts, e.g., in forensic science. Most of the work in the literature rely on physics simulation to draw such inferences. The simulation requires a precise model of the underlying domain to work well and is essentially a black-box from which one can hardly obtain any useful explanation. By contrast, qualitative reasoning methods have the advantage in making transparent inferences with ambiguous information, which makes it suitable for this task. However, there has been no suitable qualitative theory proposed for object motion in three-dimensional space. We take this challenge and develop a qualitative theory for the motion of rigid objects. Based on this theory, we develop a reasoning method to solve a very interesting problem: Assuming there are several objects that were initially at rest and now have started to move. We want to infer what action causes the movement of these objects.



ualitative Approach to echanical Constraint

AAAI Conferences

This paper provides a qualitative analysis of instantaneous, constrained motions in rigid bodies. We develop a symbolic spatial representation to describe the effects of configuration on the dynamic behavior of rigid objects. We also explore the way symbolic shape information may be used to reason about force transmission. This information may be used to provide a static analysis for a given configuration and is an important component of the calculation of behavioral transitions when envisioning device behavior. All results are based on an implementation.


A Model for Integrated ualit at ive Spatial and Dynamic easoning about Physical Systems

AAAI Conferences

Qualitative spatial reasoning has many applications in such diverse areas as natural language understanding, cognitive mapping, and reasoning about the physical world. We address problems whose solutions require integrated spatial and dynamic reasoning.


Automated Critique of Sketched Mechanisms

AAAI Conferences

Designers often use a series of sketches to explain how their design goes through different states or modes to achieve its intended function. Learning how to create such explanations turns out to be a difficult problem for engineering students. An automated "crash test dummy" to let students practice explanations would be desirable. This paper describes how to carry out a core piece of the reasoning needed in such system. We show how an open-domain sketch understanding system can be used to enter many aspects of such explanations, and how qualitative mechanics can be used to check the plausibility of the intended state transitions. The system is evaluated using a corpus of sketches based on designs from an engineering school design and communications course.