|Date:||2019, January 22|
|Title:||What Stands-in for a Missing Tool: A Prototypical Grounded Knowledge-based Approach to Tool Substitution|
When a robot is operating in a dynamic environment, it cannot be assumed that a tool required to solve a given task will always be available. In case of a missing tool, an ideal response would be to find a substitute to complete the task. In this paper, we present a proof of concept of a grounded knowledge-based approach to tool substitution where knowledge is generated in an unsupervised manner from robotís sensory data about objects. Such robot-centric grounded knowledge is then used to identify a substitute from the available objects in the environment.
The performance of the proposed approach was evaluated by performing two experiments. The first experiment consisted of 22 substitution scenarios and second consisted of 11 substitution scenarios. The substitutes computed by the proposed approach were validated on the basis of the expertsí choices for each scenario in both the experiments. Our evaluation showed that the approach mostly identified the same substitutes as the experts: in the first experiment, this was the case for 20 out of 22 scenarios (91%), and in the second experiment for 9 out of 11 scenarios (82%). In the third experiment, we integrated the proposed system with an object detection system and evaluated its performance.