Adapting control policies from simulation to reality using a pairwise loss

07/27/2018
by   Ulrich Viereck, et al.
2

This paper proposes an approach to domain transfer based on a pairwise loss function that helps transfer control policies learned in simulation onto a real robot. We explore the idea in the context of a 'category level' manipulation task where a control policy is learned that enables a robot to perform a mating task involving novel objects. We explore the case where depth images are used as the main form of sensor input. Our experimental results demonstrate that proposed method consistently outperforms baseline methods that train only in simulation or that combine real and simulated data in a naive way.

READ FULL TEXT
research
10/25/2022

DeXtreme: Transfer of Agile In-hand Manipulation from Simulation to Reality

Recent work has demonstrated the ability of deep reinforcement learning ...
research
02/13/2019

Simultaneously Learning Vision and Feature-based Control Policies for Real-world Ball-in-a-Cup

We present a method for fast training of vision based control policies o...
research
03/31/2021

Causal Reasoning in Simulation for Structure and Transfer Learning of Robot Manipulation Policies

We present CREST, an approach for causal reasoning in simulation to lear...
research
07/22/2022

Graph-Structured Policy Learning for Multi-Goal Manipulation Tasks

Multi-goal policy learning for robotic manipulation is challenging. Prio...
research
11/21/2019

Contextual Reinforcement Learning of Visuo-tactile Multi-fingered Grasping Policies

Using simulation to train robot manipulation policies holds the promise ...
research
03/18/2019

Learning to Augment Synthetic Images for Sim2Real Policy Transfer

Vision and learning have made significant progress that could improve ro...

Please sign up or login with your details

Forgot password? Click here to reset