Skip to content

This is a novel framework, which is to autonomously generate a manipulation plan to accomplish various complex tasks requiring dexterity, without requiring an expert to manually design a control strategy for a particular task in an ad-hoc manner.

Notifications You must be signed in to change notification settings

JS-RML/autonomous_manipulation_planner

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 

Repository files navigation

autonomous_manipulation_planner

This is a novel framework, which is to autonomously generate a manipulation plan to accomplish various complex tasks requiring dexterity, without requiring an expert to manually design a control strategy for a particular task in an ad-hoc manner.

The input includes a description of the environment, the initial finger position, shape and desnsity distribution of the object, the initial and target object poses, gripper to use, friction coefficient.

Here are four examples:

Task1: pick an object off the flat ground with a passive gripper featuring zero mobility. Please run task1.py.

Task2: place an object onto the flat ground with a passive gripper feturing zero mobility. Please run task2.py.

Task3: Scoop an object out of a hole. Please run task3.py.

Task4: Insert an object into a hole. Please run task4.py.

About

This is a novel framework, which is to autonomously generate a manipulation plan to accomplish various complex tasks requiring dexterity, without requiring an expert to manually design a control strategy for a particular task in an ad-hoc manner.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published