Learning Robotic Manipulation Skills Using an Adaptive Force-Impedance Action Space

10/19/2021
by   Maximilian Ulmer, et al.
0

Intelligent agents must be able to think fast and slow to perform elaborate manipulation tasks. Reinforcement Learning (RL) has led to many promising results on a range of challenging decision-making tasks. However, in real-world robotics, these methods still struggle, as they require large amounts of expensive interactions and have slow feedback loops. On the other hand, fast human-like adaptive control methods can optimize complex robotic interactions, yet fail to integrate multimodal feedback needed for unstructured tasks. In this work, we propose to factor the learning problem in a hierarchical learning and adaption architecture to get the best of both worlds. The framework consists of two components, a slow reinforcement learning policy optimizing the task strategy given multimodal observations, and a fast, real-time adaptive control policy continuously optimizing the motion, stability, and effort of the manipulator. We combine these components through a bio-inspired action space that we call AFORCE. We demonstrate the new action space on a contact-rich manipulation task on real hardware and evaluate its performance on three simulated manipulation tasks. Our experiments show that AFORCE drastically improves sample efficiency while reducing energy consumption and improving safety.

READ FULL TEXT
research
06/20/2019

Variable Impedance Control in End-Effector Space: An Action Space for Reinforcement Learning in Contact-Rich Tasks

Reinforcement Learning (RL) of contact-rich manipulation tasks has yield...
research
03/02/2020

Learning Contact-Rich Manipulation Tasks with Rigid Position-Controlled Robots: Learning to Force Control

To fully realize industrial automation, it is indispensable to give the ...
research
03/18/2020

Learning Contact-Rich Manipulation Tasks with Rigid Position-Controlled Robots

To fully realize industrial automation, it is indispensable to give the ...
research
11/13/2020

Robotic self-representation improves manipulation skills and transfer learning

Cognitive science suggests that the self-representation is critical for ...
research
10/30/2020

Learning Stable Normalizing-Flow Control for Robotic Manipulation

Reinforcement Learning (RL) of robotic manipulation skills, despite its ...
research
10/21/2019

Modelling Generalized Forces with Reinforcement Learning for Sim-to-Real Transfer

Learning robotic control policies in the real world gives rise to challe...
research
03/29/2021

LASER: Learning a Latent Action Space for Efficient Reinforcement Learning

The process of learning a manipulation task depends strongly on the acti...

Please sign up or login with your details

Forgot password? Click here to reset