Related papers: Follow the Gradient: Crossing the Reality Gap usin…

End-to-end control for robot manipulation and grasping is emerging as an attractive alternative to traditional pipelined approaches. However, end-to-end methods tend to either be slow to train, exhibit little or no generalisability, or lack…

Deep reinforcement learning (DRL) has had success in virtual and simulated domains, but due to key differences between simulated and real-world environments, DRL-trained policies have had limited success in real-world applications. To…

Deep learning-based garment draping has emerged as a promising alternative to traditional Physics-Based Simulation (PBS), yet robust collision handling remains a critical bottleneck. Most existing methods enforce physical validity through…

In this paper, we deal with the reality gap from a novel perspective, targeting transferring Deep Reinforcement Learning (DRL) policies learned in simulated environments to the real-world domain for visual control tasks. Instead of adopting…

This paper presents a fully autonomous robotic system that performs sim-to-real transfer in complex long-horizon tasks involving navigation, recognition, grasping, and stacking in an environment with multiple obstacles. The key feature of…

The scalability of robotic learning is fundamentally bottlenecked by the significant cost and labor of real-world data collection. While simulated data offers a scalable alternative, it often fails to generalize to the real world due to…

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…

In the field of robotics many different approaches ranging from classical planning over optimal control to reinforcement learning (RL) are developed and borrowed from other fields to achieve reliable control in diverse tasks. In order to…

The purpose of this paper is to improve upon existing variants of gradient descent by solving two problems: (1) removing (or reducing) the plateau that occurs while minimizing the cost function, (2) continually adjusting the learning rate…

Generating feasible robot motions in real-time requires achieving multiple tasks (i.e., kinematic requirements) simultaneously. These tasks can have a specific goal, a range of equally valid goals, or a range of acceptable goals with a…

Accurate deformable object manipulation (DOM) is essential for achieving autonomy in robotic surgery, where soft tissues are being displaced, stretched, and dissected. Many DOM methods can be powered by simulation, which ensures realistic…

Interactive world models that simulate object dynamics are crucial for robotics, VR, and AR. However, it remains a significant challenge to learn physics-consistent dynamics models from limited real-world video data, especially for…

The motion of robots and objects in our world is often highly dependent upon contact. When contact is expected but does not occur or when contact is not expected but does occur, robot behavior diverges from plan, often disastrously. This…

Simulation based learning often provides a cost-efficient recourse to reinforcement learning applications in robotics. However, simulators are generally incapable of accurately replicating real-world dynamics, and thus bridging the sim2real…

Real-space grids are a powerful alternative for the simulation of electronic systems. One of the main advantages of the approach is the flexibility and simplicity of working directly in real space where the different fields are discretized…

Simulation can and should play a critical role in the development and testing of algorithms for autonomous agents. What might reduce its impact is the ``sim2real'' gap -- the algorithm response differs between operation in simulated versus…

Real2Sim2Real plays a critical role in robotic arm control and reinforcement learning, yet bridging this gap remains a significant challenge due to the complex physical properties of robots and the objects they manipulate. Existing methods…

Transferring the depth-based end-to-end policy trained in simulation to physical robots can yield an efficient and robust grasping policy, yet sensor artifacts in real depth maps like voids and noise establish a significant sim2real gap…

Although robotic applications increasingly demand versatile and dynamic object handling, most existing techniques are predominantly focused on grasp-based manipulation, limiting their applicability in non-prehensile tasks. To address this…

This work considers identifying parameters characterizing a physical system's dynamic motion directly from a video whose rendering configurations are inaccessible. Existing solutions require massive training data or lack generalizability to…