Saved in:
Bibliographic Details
Main Authors: Li, Linfeng, Yang, Gang, Shao, Lin, Hsu, David
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.17725
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912736806436864
author Li, Linfeng
Yang, Gang
Shao, Lin
Hsu, David
author_facet Li, Linfeng
Yang, Gang
Shao, Lin
Hsu, David
contents From serving a cup of coffee to positioning mechanical parts during assembly, stable object placement is a crucial skill for future robots. It becomes particularly challenging under geometric uncertainties, e.g., when the object pose or shape is not known accurately. This work leverages a differentiable simulation model of contact dynamics to tackle this challenge. We derive a novel gradient that relates force-torque sensor readings to geometric uncertainties, thus enabling uncertainty estimation by minimizing discrepancies between sensor data and model predictions via gradient descent. Gradient-based methods are sensitive to initialization. To mitigate this effect, we maintain a belief over multiple estimates and choose the robot action based on the current belief at each timestep. In experiments on a Franka robot arm, our method achieved promising results on multiple objects under various geometric uncertainties, including the in-hand pose uncertainty of a grasped object, the object shape uncertainty, and the environment uncertainty.
format Preprint
id arxiv_https___arxiv_org_abs_2409_17725
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Differentiable Contact Dynamics for Stable Object Placement Under Geometric Uncertainties
Li, Linfeng
Yang, Gang
Shao, Lin
Hsu, David
Robotics
From serving a cup of coffee to positioning mechanical parts during assembly, stable object placement is a crucial skill for future robots. It becomes particularly challenging under geometric uncertainties, e.g., when the object pose or shape is not known accurately. This work leverages a differentiable simulation model of contact dynamics to tackle this challenge. We derive a novel gradient that relates force-torque sensor readings to geometric uncertainties, thus enabling uncertainty estimation by minimizing discrepancies between sensor data and model predictions via gradient descent. Gradient-based methods are sensitive to initialization. To mitigate this effect, we maintain a belief over multiple estimates and choose the robot action based on the current belief at each timestep. In experiments on a Franka robot arm, our method achieved promising results on multiple objects under various geometric uncertainties, including the in-hand pose uncertainty of a grasped object, the object shape uncertainty, and the environment uncertainty.
title Differentiable Contact Dynamics for Stable Object Placement Under Geometric Uncertainties
topic Robotics
url https://arxiv.org/abs/2409.17725