Geometric Task Networks: Learning Efficient and Explainable Skill Coordination for Object Manipulation

09/18/2021
by   Meng Guo, et al.
0

Complex manipulation tasks can contain various execution branches of primitive skills in sequence or in parallel under different scenarios. Manual specifications of such branching conditions and associated skill parameters are not only error-prone due to corner cases but also quickly untraceable given a large number of objects and skills. On the other hand, learning from demonstration has increasingly shown to be an intuitive and effective way to program such skills for industrial robots. Parameterized skill representations allow generalization over new scenarios, which however makes the planning process much slower thus unsuitable for online applications. In this work, we propose a hierarchical and compositional planning framework that learns a Geometric Task Network (GTN) from exhaustive planners, without any manual inputs. A GTN is a goal-dependent task graph that encapsulates both the transition relations among skill representations and the geometric constraints underlying these transitions. This framework has shown to improve dramatically the offline learning efficiency, the online performance and the transparency of decision process, by leveraging the task-parameterized models. We demonstrate the approach on a 7-DoF robot arm both in simulation and on hardware solving various manipulation tasks.

READ FULL TEXT

page 1

page 4

page 7

page 8

page 9

research
03/01/2022

Interactive Human-in-the-loop Coordination of Manipulation Skills Learned from Demonstration

Learning from demonstration (LfD) provides a fast, intuitive and efficie...
research
08/24/2020

Learning and Sequencing of Object-Centric Manipulation Skills for Industrial Tasks

Enabling robots to quickly learn manipulation skills is an important, ye...
research
09/07/2022

Optimizing Demonstrated Robot Manipulation Skills for Temporal Logic Constraints

For performing robotic manipulation tasks, the core problem is determini...
research
03/26/2021

Robot Program Parameter Inference via Differentiable Shadow Program Inversion

Challenging manipulation tasks can be solved effectively by combining in...
research
07/28/2022

Learning Dynamic Manipulation Skills from Haptic-Play

In this paper, we propose a data-driven skill learning approach to solve...
research
09/09/2021

Learning Forceful Manipulation Skills from Multi-modal Human Demonstrations

Learning from Demonstration (LfD) provides an intuitive and fast approac...
research
11/08/2019

Visual Geometric Skill Inference by Watching Human Demonstration

We study the problem of learning manipulation skills from human demonstr...

Please sign up or login with your details

Forgot password? Click here to reset