Learning Multimodal Contact-Rich Skills from Demonstrations Without Reward Engineering

03/01/2021
by   Mythra V. Balakuntala, et al.
0

Everyday contact-rich tasks, such as peeling, cleaning, and writing, demand multimodal perception for effective and precise task execution. However, these present a novel challenge to robots as they lack the ability to combine these multimodal stimuli for performing contact-rich tasks. Learning-based methods have attempted to model multi-modal contact-rich tasks, but they often require extensive training examples and task-specific reward functions which limits their practicality and scope. Hence, we propose a generalizable model-free learning-from-demonstration framework for robots to learn contact-rich skills without explicit reward engineering. We present a novel multi-modal sensor data representation which improves the learning performance for contact-rich skills. We performed training and experiments using the real-life Sawyer robot for three everyday contact-rich skills – cleaning, writing, and peeling. Notably, the framework achieves a success rate of 100 skill, and 80 be extended for learning other physical manipulation skills.

READ FULL TEXT

page 1

page 5

page 6

research
09/25/2019

Deep Dynamics Models for Learning Dexterous Manipulation

Dexterous multi-fingered hands can provide robots with the ability to fl...
research
03/02/2022

InsertionNet 2.0: Minimal Contact Multi-Step Insertion Using Multimodal Multiview Sensory Input

We address the problem of devising the means for a robot to rapidly and ...
research
02/13/2021

Learning Variable Impedance Control via Inverse Reinforcement Learning for Force-Related Tasks

Many manipulation tasks require robots to interact with unknown environm...
research
07/02/2023

RH20T: A Robotic Dataset for Learning Diverse Skills in One-Shot

A key challenge in robotic manipulation in open domains is how to acquir...
research
04/24/2023

Efficient Robot Skill Learning with Imitation from a Single Video for Contact-Rich Fabric Manipulation

Classical policy search algorithms for robotics typically require perfor...
research
10/12/2022

Holo-Dex: Teaching Dexterity with Immersive Mixed Reality

A fundamental challenge in teaching robots is to provide an effective in...
research
12/07/2022

Combining Planning, Reasoning and Reinforcement Learning to solve Industrial Robot Tasks

One of today's goals for industrial robot systems is to allow fast and e...

Please sign up or login with your details

Forgot password? Click here to reset