2018 IEEE International Conference on Robotics and Automation (ICRA) 2018
DOI: 10.1109/icra.2018.8460528
|View full text |Cite
|
Sign up to set email alerts
|

Sim-to-Real Transfer of Robotic Control with Dynamics Randomization

Abstract: Simulations are attractive environments for training agents as they provide an abundant source of data and alleviate certain safety concerns during the training process. But the behaviours developed by agents in simulation are often specific to the characteristics of the simulator. Due to modeling error, strategies that are successful in simulation may not transfer to their real world counterparts. In this paper, we demonstrate a simple method to bridge this "reality gap". By randomizing the dynamics of the si… Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
608
0
1

Year Published

2019
2019
2024
2024

Publication Types

Select...
7
2
1

Relationship

0
10

Authors

Journals

citations
Cited by 860 publications
(609 citation statements)
references
References 21 publications
0
608
0
1
Order By: Relevance
“…In [5], the authors use a recurrent neural network to explicitly learn model parameters through real time interaction with an environment; these parameters are then used to augment the observation for a standard reinforcement learning algorithm. In [6], the authors use a recurrent policy and value function in a modified deep deterministic policy gradient algorithm to learn a policy for a robotic manipulator arm that uses real camera images as observations. In both cases, the agents train over a wide range of randomized system parameters.…”
Section: Introductionmentioning
confidence: 99%
“…In [5], the authors use a recurrent neural network to explicitly learn model parameters through real time interaction with an environment; these parameters are then used to augment the observation for a standard reinforcement learning algorithm. In [6], the authors use a recurrent policy and value function in a modified deep deterministic policy gradient algorithm to learn a policy for a robotic manipulator arm that uses real camera images as observations. In both cases, the agents train over a wide range of randomized system parameters.…”
Section: Introductionmentioning
confidence: 99%
“…Others perform full manipulation tasks based on multiple input modalities [1,20,31] but require a pre-specified manipulation graph [31], demonstrate only on one task [20,31], or require human demonstration and object CAD models [1]. There have been promising works that train manipulation policies in simulation and transfer them to a real robot [3,10,50]. However, only few works focused on contact-rich tasks [24] and none relied on haptic feedback in simulation, most likely because of the lack of fidelity of contact simulation and collision modeling for articulated rigid-body systems [21,25].…”
Section: A Contact-rich Manipulationmentioning
confidence: 99%
“…However, when transferred to real-world robotic systems, most of these methods become less attractive due to high sample complexity and a lack of explainability of state-of-the-art deep RL algorithms. As a consequence, the research field of domain randomization has recently been gaining interest [10,11,12,13,14,15,16,17]. This class of approaches promises to transfer control policies learned in simulation (source domain) to the real world (target domain) by randomizing the simulator's parameters (e.g., masses, extents, or friction coefficients) and hence train from a set of models instead of just one nominal model.…”
Section: Introductionmentioning
confidence: 99%