Related papers: Intervention Design for Effective Sim2Real Transfe…

Deep Learning has seen an unprecedented increase in vision applications since the publication of large-scale object recognition datasets and introduction of scalable compute hardware. State-of-the-art methods for most vision tasks for…

Domain alignment is currently the most prevalent solution to unsupervised domain-adaptation tasks and are often being presented as minimizers of some theoretical upper-bounds on risk in the target domain. However, further works revealed…

Accurately manipulating articulated objects is a challenging yet important task for real robot applications. In this paper, we present a novel framework called Sim2Real$^2$ to enable the robot to manipulate an unseen articulated object to…

Most object manipulation strategies for robots are based on the assumption that the object is rigid (i.e., with fixed geometry) and the goal's details have been fully specified (e.g., the exact target pose). However, there are many tasks…

Various approaches have been proposed to learn visuo-motor policies for real-world robotic applications. One solution is first learning in simulation then transferring to the real world. In the transfer, most existing approaches need…

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,…

A practical approach to learning robot skills, often termed sim2real, is to train control policies in simulation and then deploy them on a real robot. Popular techniques to improve the sim2real transfer build on domain randomization (DR) --…

Deep neural networks have demonstrated impressive performance in various machine learning tasks. However, they are notoriously sensitive to changes in data distribution. Often, even a slight change in the distribution can lead to drastic…

Deep learning has raised hopes and expectations as a general solution for many applications; indeed it has proven effective, but it also showed a strong dependence on large quantities of data. Luckily, it has been shown that, even when data…

Sim-to-real gap has long posed a significant challenge for robot learning in simulation, preventing the deployment of learned models in the real world. Previous work has primarily focused on domain randomization and system identification to…

Data augmentation has been proven to be an effective technique for developing machine learning models that are robust to known classes of distributional shifts (e.g., rotations of images), and alignment regularization is a technique often…

Reliable autonomous navigation across the unstructured terrains of distant planetary surfaces is a critical enabler for future space exploration. However, the deployment of learning-based controllers is hindered by the inherent sim-to-real…

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…

A commercial robot, trained by its manufacturer to recognize a predefined number and type of objects, might be used in many settings, that will in general differ in their illumination conditions, background, type and degree of clutter, and…

We study the choice of action space in robot manipulation learning and sim-to-real transfer. We define metrics that assess the performance, and examine the emerging properties in the different action spaces. We train over 250 reinforcement…

Traditional place categorization approaches in robot vision assume that training and test images have similar visual appearance. Therefore, any seasonal, illumination and environmental changes typically lead to severe degradation in…

Designing reward functions that generalize beyond controlled laboratory settings remains a fundamental challenge in reinforcement learning for robotics. In open-world manipulation problems, a single task can appear in numerous variants…

Machine learning algorithms have revolutionized different fields, including natural language processing, computer vision, signal processing, and medical data processing. Despite the excellent capabilities of machine learning algorithms in…

We explore the zero-shot setting for day-night domain adaptation. The traditional domain adaptation setting is to train on one domain and adapt to the target domain by exploiting unlabeled data samples from the test set. As gathering…

Reinforcement learning (RL) has demonstrated great success in the past several years. However, most of the scenarios focus on simulated environments. One of the main challenges of transferring the policy learned in a simulated environment…