Figure - uploaded by Mohan Sridharan
Content may be subject to copyright.
(Simulated scenes) Precision and recall of retriev- ing relevant literals for constructing answers to questions with and without reasoning with learned axioms. Using the learned axioms significantly improves the ability to provide accurate explanations.
Source publication
A robot's ability to provide descriptions of its decisions and beliefs promotes effective collaboration with humans. Providing such transparency is particularly challenging in integrated robot systems that include knowledge-based reasoning methods and data-driven learning algorithms. Towards addressing this challenge, our architecture couples the c...
Contexts in source publication
Context 1
... The literals present in the answers were compared against the expected literals in the "ground truth" response, with the average precision and recall scores reported in Table 4. 4. We also performed these experiments with simulated images, and the results are summarized in Table 5. Tables 4, 5 show that when the learned axioms were used for reasoning, the precision and recall of relevant literals (for constructing the explanation) were higher than when the learned axioms were not included. ...Context 2
... The literals present in the answers were compared against the expected literals in the "ground truth" response, with the average precision and recall scores reported in Table 4. 4. We also performed these experiments with simulated images, and the results are summarized in Table 5. Tables 4, 5 show that when the learned axioms were used for reasoning, the precision and recall of relevant literals (for constructing the explanation) were higher than when the learned axioms were not included. The improvement in performance is particularly pronounced when the robot has to answer questions about actions that it has not actually executed. ...Context 3
... The literals present in the answers were compared against the expected literals in the "ground truth" response, with the average precision and recall scores reported in Table 4. 4. We also performed these experiments with simulated images, and the results are summarized in Table 5. Tables 4, 5 show that when the learned axioms were used for reasoning, the precision and recall of relevant literals (for constructing the explanation) were higher than when the learned axioms were not included. ...Context 4
... The literals present in the answers were compared against the expected literals in the "ground truth" response, with the average precision and recall scores reported in Table 4. 4. We also performed these experiments with simulated images, and the results are summarized in Table 5. Tables 4, 5 show that when the learned axioms were used for reasoning, the precision and recall of relevant literals (for constructing the explanation) were higher than when the learned axioms were not included. The improvement in performance is particularly pronounced when the robot has to answer questions about actions that it has not actually executed. ...Similar publications
Programming and executing robot trajectories is a routine manufacturing procedure. However, current interfaces (i.e., teach pendants) are bulky, unintuitive, and interrupts task flow. Recently, augmented reality (AR) has been used to create alternative solutions. However, input modalities of such systems tend to be limited. By introducing the use o...
Industrial manipulators are rarely used in high-force processes even though they provide flexibility, adaptability, relatively low cost, and a large workspace. This limited utilization is mainly due to their inherent low stiffness, which results in significant deformation. Hence, it is necessary to improve their accuracy in order to achieve high-pr...
A robot’s ability to provide explanatory descriptions of its decisions and beliefs promotes effective collaboration with humans. Providing such transparency in decision making is particularly challenging in integrated robot systems that include knowledge-based reasoning methods and data-driven learning algorithms. Towards addressing this challenge,...
