Explaining the Decisions of Deep Policy Networks for Robotic Manipulations

Cited 2 time in webofscience Cited 0 time in scopus
  • Hit : 184
  • Download : 0
Deep policy networks enable robots to learn behaviors to solve various real-world complex tasks in an end-to-end fashion. However, they lack transparency to provide the reasons of actions. Thus, such a black-box model often results in low reliability and disruptive actions during the deployment of the robot in practice. To enhance its transparency, it is important to explain robot behaviors by considering the extent to which each input feature contributes to determining a given action. In this paper, we present an explicit analysis of deep policy models through input attribution methods to explain how and to what extent each input feature affects the decisions of the robot policy models. To this end, we present two methods for applying input attribution methods to robot policy networks: (1) we measure the importance factor of each joint torque to reflect the influence of the motor torque on the end-effector movement, and (2) we modify a relevance propagation method to handle negative inputs and outputs in deep policy networks properly. To the best of our knowledge, this is the first report to identify the dynamic changes of input attributions of multi-modal sensor inputs in deep policy networks online for robotic manipulation.
Publisher
IEEE Robotics and Automation Society
Issue Date
2021-09-30
Language
English
Citation

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp.2663 - 2669

ISSN
2153-0858
DOI
10.1109/IROS51168.2021.9636594
URI
http://hdl.handle.net/10203/290682
Appears in Collection
AI-Conference Papers(학술대회논문)
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 2 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0