Exploiting Symmetries in Reinforcement Learning of Bimanual Robotic Tasks

By Fabio Amadio, Adrià Colomé, Carme Torras. 2019

33 citations recorded by the source corpus.

Movement primitives (MPs) have been widely adopted for representing and learning robotic movements using reinforcement learning policy search. Probabilistic movement primitives (ProMPs) are a kind of MP based on a stochastic representation over sets of trajectories, able to capture the variability allowed while executing a movement. This approach has proved effective in learning a wide range of robotic movements, but it comes with the necessity of dealing with a high-dimensional space of parameters. This may be a critical problem when learning tasks with two robotic manipulators, and this work proposes an approach to reduce the dimension of the parameter space based on the exploitation of symmetry. A symmetrization method for ProMPs is presented and used to represent two movements, employing a single ProMP for the first arm and a symmetry surface that maps that ProMP to the second arm. This symmetric representation is then adopted in reinforcement learning of bimanual tasks (from user-provided demonstrations), using relative entropy policy search algorithm. The symmetry-based approach developed has been tested in an experiment of cloth manipulation, showing a speed increment in learning the task.

Subfields: Artificial Intelligence, Biomedical Engineering, Control and Systems Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Yuke Zhu
2. Li Fei-Fei
3. Silvio Savarese
4. Ajay Mandlekar
5. Roberto Mart'in-Mart'in
6. Abhinav Kumar Gupta
7. Josiah Wong
8. Trevor Darrell

In Biomedical Engineering

1. Ajay Mandlekar
2. Yuke Zhu
3. Roberto Mart'in-Mart'in
4. Silvio Savarese
5. Li Fei-Fei

In Control and Systems Engineering

1. Yuke Zhu
2. Ajay Mandlekar
3. Li Fei-Fei
4. Silvio Savarese
5. Roberto Mart'in-Mart'in
6. Josiah Wong
7. Danfei Xu
8. Linxi (Jim) Fan

Citations in the corpus

• Learning Multi-Arm Manipulation Through Collaborative Teleoperation (2020, methodology): “Reinforcement Learning (RL) has been applied to bimanual manipulation tasks [3, 7, 8, 14, 18], but RL methods must deal with the increased burden of exploration due to the presence of two arms.”
• RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation (2024, unknown): “…biases, such as distinguishing two arms for stabilization and functionality (Grannen et al., 2023b), parameterizing movement primitives (Batinica et al., 2017; Amadio et al., 2019; Chitnis et al., 2020; Franzese et al., 2023), or using voxel representations (Grotz et al., 2024; Liu et al., 2024).”