Let's Handle It: Generalizable Manipulation of Articulated Objects

02/23/2022
by   Zhutian Yang, et al.
0

In this project we present a framework for building generalizable manipulation controller policies that map from raw input point clouds and segmentation masks to joint velocities. We took a traditional robotics approach, using point cloud processing, end-effector trajectory calculation, inverse kinematics, closed-loop position controllers, and behavior trees. We demonstrate our framework on four manipulation skills on common household objects that comprise the SAPIEN ManiSkill Manipulation challenge.

READ FULL TEXT

page 2

page 3

page 4

research
07/16/2021

DeformerNet: A Deep Learning Approach to 3D Deformable Object Manipulation

In this paper, we propose a novel approach to 3D deformable object manip...
research
02/21/2023

Sim2Real^2: Actively Building Explicit Physics Model for Precise Articulated Object Manipulation

Accurately manipulating articulated objects is a challenging yet importa...
research
10/14/2022

Frame Mining: a Free Lunch for Learning Robotic Manipulation from 3D Point Clouds

We study how choices of input point cloud coordinate frames impact learn...
research
03/07/2018

Adapting Everyday Manipulation Skills to Varied Scenarios

We address the problem of executing tool-using manipulation skills in sc...
research
07/11/2022

Learning Closed-loop Dough Manipulation Using a Differentiable Reset Module

Deformable object manipulation has many applications such as cooking and...
research
02/09/2023

ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills

Generalizable manipulation skills, which can be composed to tackle long-...
research
03/18/2021

Generalizing Object-Centric Task-Axes Controllers using Keypoints

To perform manipulation tasks in the real world, robots need to operate ...

Please sign up or login with your details

Forgot password? Click here to reset