Sim-to-real transfer of robotic control with dynamics randomization

How Should a Simulation-to-Reality Transfer Budget Be Spent?

arXiv:2606. 22062v2 Announce Type: replace-cross Abstract: Simulation-to-reality transfer, often called sim-to-real transfer, is a central challenge in robot learning.

A Survey of Robotic Navigation and Manipulation with Physics Simulators in the Era of Embodied AI

arXiv:2505. 01458v2 Announce Type: replace-cross Abstract: Navigation and manipulation are core capabilities in Embodied AI, but training agents to perform them directly in the real world is costly, time-consuming, and unsafe.

Generalizing from simulation

Our latest robotics techniques allow robot controllers, trained entirely in simulation and deployed on physical robots, to react to unplanned changes in the environment as they solve simple tasks. That is, we’ve used these techniques to build closed-loop systems rather than open-loop ones as before.

TAM: Torque Adaptation Module for Robust Motion Transfer in Manipulation

arXiv:2606. 06218v1 Announce Type: cross Abstract: A policy tuned for one robot often behaves differently on another, whether due to the sim-to-real gap, unknown payloads, or the differing dynamics of two instances of the same robot.

Sim-to-Real Transfer for Muscle-Actuated Robots via Generalized Actuator Networks

arXiv:2604. 09487v2 Announce Type: replace-cross Abstract: Tendon drives paired with soft muscle actuation enable faster and safer robots while potentially accelerating skill acquisition.

Domain randomization and generative models for robotic grasping

Support-Constrained RL Enables Real-World Policy Improvement without Real-World Experience

arXiv:2606. 27475v1 Announce Type: cross Abstract: Robots trained on real world data tend to be imprecise, slow, and brittle to perturbations.

Too Much of a Good Thing: When sim2real Efforts Impede Policy Learning (And What to Do About It)

arXiv:2606. 02636v1 Announce Type: cross Abstract: While sim2real efforts are necessary for effective policy transfer to hardware, there is such a thing as too much of a good thing.

Sample from What You See: Visuomotor Policy Learning via Diffusion Bridge with Observation-Embedded Stochastic Differential Equation

arXiv:2512. 07212v3 Announce Type: replace Abstract: Imitation learning with diffusion models has advanced robotic control by capturing the multi-modal action distributions.

Lagrangian Perturbation Diffusion Steering: Latent Reinforcement Learning for Generative Policies

arXiv:2606. 01151v1 Announce Type: new Abstract: Behavior cloning with high-capacity generative policies achieves strong imitation performance, but is often limited by demonstration coverage and distribution shift.

SoMA: A Real-to-Sim Neural Simulator for Robotic Soft-body Manipulation

arXiv:2602. 02402v2 Announce Type: replace-cross Abstract: Simulating deformable objects under rich interactions remains a fundamental challenge for real-to-sim robot manipulation, with dynamics jointly driven by environmental effects and robot actions.

VINE: Taming Generative Control Policies for Reinforcement Learning

arXiv:2607. 10369v1 Announce Type: cross Abstract: Flow-matching policies have emerged as an effective policy parameterization for robot learning.