Related papers: DROID: Minimizing the Reality Gap using Single-Sho…
Dynamically changing environments, unreliable state estimation, and operation under severe resource constraints are fundamental challenges that limit the deployment of small autonomous drones. We address these challenges in the context of…
Dexterous manipulation is physics-intensive and highly sensitive to modeling errors and perception noise, making sim-to-real transfer prohibitively challenging. Domain randomization (DR) is commonly used to improve the robustness of learned…
Deep reinforcement learning (DRL) has achieved groundbreaking successes in a wide variety of robotic applications. A natural consequence is the adoption of this paradigm for safety-critical tasks, where human safety and expensive hardware…
Deploying machine learning algorithms for robot tasks in real-world applications presents a core challenge: overcoming the domain gap between the training and the deployment environment. This is particularly difficult for visuomotor…
Humanoids have the potential to be the ideal embodiment in environments designed for humans. Thanks to the structural similarity to the human body, they benefit from rich sources of demonstration data, e.g., collected via teleoperation,…
Simulation-to-real transfer using domain randomization for robot control often relies on low-gear-ratio, backdrivable actuators, but these approaches break down when the sim-to-real gap widens. Inspired by the traditional PID controller, we…
Sim-to-real, a term that describes where a model is trained in a simulator then transferred to the real world, is a technique that enables faster deep reinforcement learning (DRL) training. However, differences between the simulator and the…
Sim-to-real transfer remains a major challenge in reinforcement learning (RL) for robotics, as policies trained in simulation often fail to generalize to the real world due to discrepancies in environment dynamics. Domain Randomization (DR)…
This paper proposes a simple strategy for sim-to-real in Deep-Reinforcement Learning (DRL) -- called Roll-Drop -- that uses dropout during simulation to account for observation noise during deployment without explicitly modelling its…
Behavior cloning has shown promise for robot manipulation, but real-world demonstrations are costly to acquire at scale. While simulated data offers a scalable alternative, particularly with advances in automated demonstration generation,…
Learning robot control policies from physics simulations is of great interest to the robotics community as it may render the learning process faster, cheaper, and safer by alleviating the need for expensive real-world experiments. However,…
Domain randomization in reinforcement learning is an established technique for increasing the robustness of control policies trained in simulation. By randomizing environment properties during training, the learned policy can become robust…
Deep reinforcement learning has recently seen huge success across multiple areas in the robotics domain. Owing to the limitations of gathering real-world data, i.e., sample inefficiency and the cost of collecting it, simulation environments…
Domain Randomization (DR) is known to require a significant amount of training data for good performance. We argue that this is due to DR's strategy of random data generation using a uniform distribution over simulation parameters, as a…
We consider the problem of transferring policies to the real world by training on a distribution of simulated scenarios. Rather than manually tuning the randomization of simulations, we adapt the simulation parameter distribution using a…
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,…
Physics simulators have shown great promise for conveniently learning reinforcement learning policies in safe, unconstrained environments. However, transferring the acquired knowledge to the real world can be challenging due to the reality…
Reinforcement Learning (RL) has been widely explored in Traffic Signal Control (TSC) applications, however, still no such system has been deployed in practice. A key barrier to progress in this area is the reality gap, the discrepancy that…
Synthetic data is a scalable alternative to manual supervision, but it requires overcoming the sim-to-real domain gap. This discrepancy between virtual and real worlds is addressed by two seemingly opposed approaches: improving the realism…
Deploying reinforcement learning (RL) safely in the real world is challenging, as policies trained in simulators must face the inevitable sim-to-real gap. Robust safe RL techniques are provably safe, however difficult to scale, while domain…