Improving Object Permanence using Agent Actions and Reasoning

Page view(s)
21
Checked on Aug 26, 2025
Improving Object Permanence using Agent Actions and Reasoning
Title:
Improving Object Permanence using Agent Actions and Reasoning
Journal Title:
2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Keywords:
Publication Date:
16 December 2021
Citation:
Liang, Y. S., Zhang, C., Choi, D., & Kwok, K. (2021). Improving Object Permanence using Agent Actions and Reasoning. 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 8044–8051. https://doi.org/10.1109/iros51168.2021.9636502
Abstract:
Object permanence in psychology means knowing that objects still exist even if they are no longer visible. It is a crucial concept for robots to operate autonomously in uncontrolled environments. Existing approaches learn object permanence from low-level perception, but perform poorly on more complex scenarios, like when objects are contained and carried by others. Knowledge about manipulation actions performed on an object prior to its disappearance allows us to reason about its location, e.g., that the object has been placed in a carrier. In this paper we argue that object permanence can be improved when the robot uses knowledge about executed actions and describe an approach to infer hidden object states from agent actions. We show that considering agent actions not only improves rule-based reasoning models but also purely neural approaches, showing its general applicability. Then, we conduct quantitative experiments on a snitch localization task using a dataset of 1,371 synthesized videos, where we compare the performance of different object permanence models with and without action annotations. We demonstrate that models with action annotations can significantly increase performance of both neural and rule-based approaches. Finally, we evaluate the usability of our approach in real-world applications by conducting qualitative experiments with two Universal Robots (UR5 and UR16e) in both lab and industrial settings. The robots complete benchmark tasks for a gearbox assembly and demonstrate the object permanence capabilities with real sensor data in an industrial environment.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the Agency for Science, Technology and Research - Human-Robot Collaborative AI for Advanced Manufacturing and Engineering (AME) Programme
Grant Reference no. : A18A2b0046
Description:
© 2021 IEEE.  Personal use of this material is permitted.  Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
ISSN:
2153-0866
Files uploaded:

File Size Format Action
211000238v1.pdf 3.04 MB PDF Open