Auto-Tuned Sim-to-Real Transfer
- URL: http://arxiv.org/abs/2104.07662v1
- Date: Thu, 15 Apr 2021 17:59:55 GMT
- Title: Auto-Tuned Sim-to-Real Transfer
- Authors: Yuqing Du, Olivia Watkins, Trevor Darrell, Pieter Abbeel, Deepak
Pathak
- Abstract summary: Policies trained in simulation often fail when transferred to the real world.
Current approaches to tackle this problem, such as domain randomization, require prior knowledge and engineering.
We propose a method for automatically tuning simulator system parameters to match the real world.
- Score: 143.44593793640814
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Policies trained in simulation often fail when transferred to the real world
due to the `reality gap' where the simulator is unable to accurately capture
the dynamics and visual properties of the real world. Current approaches to
tackle this problem, such as domain randomization, require prior knowledge and
engineering to determine how much to randomize system parameters in order to
learn a policy that is robust to sim-to-real transfer while also not being too
conservative. We propose a method for automatically tuning simulator system
parameters to match the real world using only raw RGB images of the real world
without the need to define rewards or estimate state. Our key insight is to
reframe the auto-tuning of parameters as a search problem where we iteratively
shift the simulation system parameters to approach the real-world system
parameters. We propose a Search Param Model (SPM) that, given a sequence of
observations and actions and a set of system parameters, predicts whether the
given parameters are higher or lower than the true parameters used to generate
the observations. We evaluate our method on multiple robotic control tasks in
both sim-to-sim and sim-to-real transfer, demonstrating significant improvement
over naive domain randomization. Project videos and code at
https://yuqingd.github.io/autotuned-sim2real/
Related papers
- Dynamics as Prompts: In-Context Learning for Sim-to-Real System Identifications [23.94013806312391]
We propose a novel approach that dynamically adjusts simulation environment parameters online using in-context learning.
We validate our approach across two tasks: object scooping and table air hockey.
Our approach delivers efficient and smooth system identification, advancing the deployment of robots in dynamic real-world scenarios.
arXiv Detail & Related papers (2024-10-27T07:13:38Z) - Learning autonomous driving from aerial imagery [67.06858775696453]
Photogrammetric simulators allow the synthesis of novel views through the transformation of pre-generated assets into novel views.
We use a Neural Radiance Field (NeRF) as an intermediate representation to synthesize novel views from the point of view of a ground vehicle.
arXiv Detail & Related papers (2024-10-18T05:09:07Z) - Sim-to-Real Transfer of Deep Reinforcement Learning Agents for Online Coverage Path Planning [15.792914346054502]
We tackle the challenge of sim-to-real transfer of reinforcement learning (RL) agents for coverage path planning ( CPP)
We bridge the sim-to-real gap through a semi-virtual environment, including a real robot and real-time aspects, while utilizing a simulated sensor and obstacles.
We find that a high inference frequency allows first-order Markovian policies to transfer directly from simulation, while higher-order policies can be fine-tuned to further reduce the sim-to-real gap.
arXiv Detail & Related papers (2024-06-07T13:24:19Z) - DrEureka: Language Model Guided Sim-To-Real Transfer [64.14314476811806]
Transferring policies learned in simulation to the real world is a promising strategy for acquiring robot skills at scale.
In this paper, we investigate using Large Language Models (LLMs) to automate and accelerate sim-to-real design.
Our approach is capable of solving novel robot tasks, such as quadruped balancing and walking atop a yoga ball.
arXiv Detail & Related papers (2024-06-04T04:53:05Z) - Robust Visual Sim-to-Real Transfer for Robotic Manipulation [79.66851068682779]
Learning visuomotor policies in simulation is much safer and cheaper than in the real world.
However, due to discrepancies between the simulated and real data, simulator-trained policies often fail when transferred to real robots.
One common approach to bridge the visual sim-to-real domain gap is domain randomization (DR)
arXiv Detail & Related papers (2023-07-28T05:47:24Z) - Understanding Domain Randomization for Sim-to-real Transfer [41.33483293243257]
We propose a theoretical framework for sim-to-real transfers, in which the simulator is modeled as a set of MDPs with tunable parameters.
We prove that sim-to-real transfer can succeed under mild conditions without any real-world training samples.
arXiv Detail & Related papers (2021-10-07T07:45:59Z) - TrafficSim: Learning to Simulate Realistic Multi-Agent Behaviors [74.67698916175614]
We propose TrafficSim, a multi-agent behavior model for realistic traffic simulation.
In particular, we leverage an implicit latent variable model to parameterize a joint actor policy.
We show TrafficSim generates significantly more realistic and diverse traffic scenarios as compared to a diverse set of baselines.
arXiv Detail & Related papers (2021-01-17T00:29:30Z) - Point Cloud Based Reinforcement Learning for Sim-to-Real and Partial
Observability in Visual Navigation [62.22058066456076]
Reinforcement Learning (RL) represents powerful tools to solve complex robotic tasks.
RL does not work directly in the real-world, which is known as the sim-to-real transfer problem.
We propose a method that learns on an observation space constructed by point clouds and environment randomization.
arXiv Detail & Related papers (2020-07-27T17:46:59Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.