Robot Planning Under Uncertainty for Object Assembly and Troubleshooting Using Human Causal Models
Semanti Basu, Semir Tatlidil, Moon Hwan Kim, Tiffany Tran, Serena Saxena, Tom Williams, Steven A. Sloman, R. Iris Bahar
Abstract
In this paper we explore if human mental models of objects, even when flawed, can be integrated with a collaborative robot's decision making framework to allow it to make smarter choices under partial observability for different object-related tasks such as assembly and troubleshooting. We demonstrate how (1) these informative causal models can be extracted from humans through crowdsourcing, (2) object assembly and troubleshooting can be formulated as Partially Observable Markov Decision Processes (POMDPs) and (3) our extracted causal models can be incorporated into those models in the form of approximate priors. Finally, (4) we use systematic experimentation in simulation to demonstrate the success of this approach, with 2 X average improvement in reward observed for object assembly tasks, and 1.4 X average improvement in reward observed for troubleshooting tasks.
BibTeX
@inproceedings{icra2025_robotplanningund,
title = {Robot Planning Under Uncertainty for Object Assembly and Troubleshooting Using Human Causal Models},
author = {Semanti Basu and Semir Tatlidil and Moon Hwan Kim and Tiffany Tran and Serena Saxena and Tom Williams and Steven A. Sloman and R. Iris Bahar},
booktitle = {ICRA 2025},
year = {2025}
}