Robot Learning from Randomized Simulations: A Review

2021/11/01 by Fabio Muratore, Muratore, Fabio, Fábio Ramos +9 · 12 citations
Computer Science · #Adversarial Robustness in Machine Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Algorithms #Machine Learning and Data Classification #Robotics (cs.RO)

paper · pdf · doi:10.48550/arxiv.2111.00956

openalex publication_date 2021/11/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

The rise of deep learning has caused a paradigm shift in robotics research, favoring methods that require large amounts of data. Unfortunately, it is prohibitively expensive to generate such data sets on a physical platform. Therefore, state-of-the-art approaches learn in simulation where data generation is fast as well as inexpensive and subsequently transfer the knowledge to the real robot (sim-to-real). Despite becoming increasingly realistic, all simulators are by construction based on models, hence inevitably imperfect. This raises the question of how simulators can be modified to facilitate learning robot control policies and overcome the mismatch between simulation and reality, often called the 'reality gap'. We provide a comprehensive review of sim-to-real research for robotics, focusing on a technique named 'domain randomization' which is a method for learning from randomized simulations.

Cited by

• Bridging Simulation and Reality: Cross-Domain Transfer with Semantic 2D Gaussian Splatting
• ReGen: Generative Robot Simulation via Inverse Design
• Heuristic Adaptation of Potentially Misspecified Domain Support for Likelihood-Free Inference in Stochastic Dynamical Systems
• Towards Trustworthy Embodied Intelligence: A Systems Framework and Graded Trustworthiness Levels
• Control Synthesis with Reinforcement Learning: A Modeling Perspective
• Distributionally Robust Optimization via Diffusion Ambiguity Modeling
• The Reality Gap in Robotics: Challenges, Solutions, and Best Practices
• RM-RL: Role-Model Reinforcement Learning for Precise Robot Manipulation
• Sim-to-Real Transfer for Muscle-Actuated Robots via Generalized Actuator Networks
• SoK: Cybersecurity Assessment of Humanoid Ecosystem
• Towards bridging the gap: Systematic sim-to-real transfer for diverse legged robots
• Whole-Body Bilateral Teleoperation with Multi-Stage Object Parameter Estimation for Wheeled Humanoid Locomanipulation

Related

• Facilitating Sim-to-real by Intrinsic Stochasticity of Real-Time Simulation in Reinforcement Learning for Robot Manipulation
• Distilled Domain Randomization
• Domain Randomization for Transferring Deep Neural Networks from\n Simulation to the Real World
• Validate on Sim, Detect on Real -- Model Selection for Domain Randomization
• The Reality Gap in Robotics: Challenges, Solutions, and Best Practices