Saved in:
Bibliographic Details
Main Authors: Dai, Cunxi, Liu, Xiaohan, Sreenath, Koushil, Li, Zhongyu, Hollis, Ralph
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.13418
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929547884101632
author Dai, Cunxi
Liu, Xiaohan
Sreenath, Koushil
Li, Zhongyu
Hollis, Ralph
author_facet Dai, Cunxi
Liu, Xiaohan
Sreenath, Koushil
Li, Zhongyu
Hollis, Ralph
contents This paper introduces a framework for interactive navigation through adaptive non-prehensile mobile manipulation. A key challenge in this process is handling objects with unknown dynamics, which are difficult to infer from visual observation. To address this, we propose an adaptive dynamics model for common movable indoor objects via learned SE(2) dynamics representations. This model is integrated into Model Predictive Path Integral (MPPI) control to guide the robot's interactions. Additionally, the learned dynamics help inform decision-making when navigating around objects that cannot be manipulated.Our approach is validated in both simulation and real-world scenarios, demonstrating its ability to accurately represent object dynamics and effectively manipulate various objects. We further highlight its success in the Navigation Among Movable Objects (NAMO) task by deploying the proposed framework on a dynamically balancing mobile robot, Shmoobot. Project website: https://cmushmoobot.github.io/AdaptivePushing/.
format Preprint
id arxiv_https___arxiv_org_abs_2410_13418
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Interactive Navigation with Adaptive Non-prehensile Mobile Manipulation
Dai, Cunxi
Liu, Xiaohan
Sreenath, Koushil
Li, Zhongyu
Hollis, Ralph
Robotics
This paper introduces a framework for interactive navigation through adaptive non-prehensile mobile manipulation. A key challenge in this process is handling objects with unknown dynamics, which are difficult to infer from visual observation. To address this, we propose an adaptive dynamics model for common movable indoor objects via learned SE(2) dynamics representations. This model is integrated into Model Predictive Path Integral (MPPI) control to guide the robot's interactions. Additionally, the learned dynamics help inform decision-making when navigating around objects that cannot be manipulated.Our approach is validated in both simulation and real-world scenarios, demonstrating its ability to accurately represent object dynamics and effectively manipulate various objects. We further highlight its success in the Navigation Among Movable Objects (NAMO) task by deploying the proposed framework on a dynamically balancing mobile robot, Shmoobot. Project website: https://cmushmoobot.github.io/AdaptivePushing/.
title Interactive Navigation with Adaptive Non-prehensile Mobile Manipulation
topic Robotics
url https://arxiv.org/abs/2410.13418