English
Related papers

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

200 papers

Humans manipulate various kinds of fluids in their everyday life: creating latte art, scooping floating objects from water, rolling an ice cream cone, etc. Using robots to augment or replace human labors in these daily settings remain as a…

Robotics · Computer Science 2023-03-07 Zhou Xian , Bo Zhu , Zhenjia Xu , Hsiao-Yu Tung , Antonio Torralba , Katerina Fragkiadaki , Chuang Gan

In this letter, the authors propose a two-step approach to evaluate and verify a true system's capacity to satisfy its operational objective. Specifically, whenever the system objective has a quantifiable measure of satisfaction, i.e. a…

Systems and Control · Electrical Eng. & Systems 2022-01-06 Prithvi Akella , Wyatt Ubellacker , Aaron D. Ames

Identifying predictive world models for robots in novel environments from sparse online observations is essential for robot task planning and execution in novel environments. However, existing methods that leverage differentiable…

Robotics · Computer Science 2025-05-13 Yifan Zhu , Tianyi Xiang , Aaron Dollar , Zherong Pan

The robotics field is evolving towards data-driven, end-to-end learning, inspired by multimodal large models. However, reliance on expensive real-world data limits progress. Simulators offer cost-effective alternatives, but the gap between…

Robotics · Computer Science 2025-12-23 Hongwei Fan , Hang Dai , Jiyao Zhang , Jinzhou Li , Qiyang Yan , Yujie Zhao , Mingju Gao , Jinghang Wu , Hao Tang , Hao Dong

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…

Robotics · Computer Science 2025-08-01 Yuta Kawachi

In recent years, fully differentiable rigid body physics simulators have been developed, which can be used to simulate a wide range of robotic systems. In the context of reinforcement learning for control, these simulators theoretically…

Machine Learning · Computer Science 2022-03-08 Sean Gillen , Katie Byl

Existing imitation learning (IL) methods such as inverse reinforcement learning (IRL) usually have a double-loop training process, alternating between learning a reward function and a policy and tend to suffer long training time and high…

Machine Learning · Computer Science 2022-06-13 Siwei Chen , Xiao Ma , Zhongwen Xu

We consider the problem of estimating an object's physical properties such as mass, friction, and elasticity directly from video sequences. Such a system identification problem is fundamentally ill-posed due to the loss of information…

The capability to transfer mastered skills to accomplish a range of similar yet novel tasks is crucial for intelligent robots. In this work, we introduce $\textit{Diff-Transfer}$, a novel framework leveraging differentiable physics…

Robotics · Computer Science 2023-10-11 Yuqi Xiang , Feitong Chen , Qinsi Wang , Yang Gang , Xiang Zhang , Xinghao Zhu , Xingyu Liu , Lin Shao

We present a differentiable simulation architecture for articulated rigid-body dynamics that enables the augmentation of analytical models with neural networks at any point of the computation. Through gradient-based optimization,…

Robotics · Computer Science 2020-07-14 Eric Heiden , David Millard , Erwin Coumans , Gaurav S. Sukhatme

Recent advances in deep reinforcement learning (RL) based techniques combined with training in simulation have offered a new approach to developing robust controllers for legged robots. However, the application of such approaches to real…

Robotics · Computer Science 2023-08-08 Rohan Pratap Singh , Zhaoming Xie , Pierre Gergondet , Fumio Kanehiro

Simulation provides a cost-effective and flexible platform for data generation and policy learning to develop robotic systems. However, bridging the gap between simulation and real-world dynamics remains a significant challenge, especially…

Traversing through a tilted narrow gap is previously an intractable task for reinforcement learning mainly due to two challenges. First, searching feasible trajectories is not trivial because the goal behind the gap is difficult to reach.…

Robotics · Computer Science 2021-08-31 Chenxi Xiao , Peng Lu , Qizhi He

Robots can learn to do complex tasks in simulation, but often, learned behaviors fail to transfer well to the real world due to simulator imperfections (the reality gap). Some existing solutions to this sim-to-real problem, such as Grounded…

Robotics · Computer Science 2020-08-05 Haresh Karnan , Siddharth Desai , Josiah P. Hanna , Garrett Warnell , Peter Stone

Despite the substantial progress in deep learning, its adoption in industrial robotics projects remains limited, primarily due to challenges in data acquisition and labeling. Previous sim2real approaches using domain randomization require…

Computer Vision and Pattern Recognition · Computer Science 2024-07-18 Kaixin Bai , Lei Zhang , Zhaopeng Chen , Fang Wan , Jianwei Zhang

Numerical simulations provide key insights into many physical, real-world problems. However, while these simulations are solved on a full 3D domain, most analysis only require a reduced set of metrics (e.g. plane-level concentrations). This…

Computational Physics · Physics 2025-11-27 Tingkai Xue , Chin Chun Ooi , Zhengwei Ge , Fong Yew Leong , Hongying Li , Chang Wei Kang

Training control policies in simulation is more appealing than on real robots directly, as it allows for exploring diverse states in an efficient manner. Yet, robot simulators inevitably exhibit disparities from the real-world…

Robotics · Computer Science 2023-10-23 Peide Huang , Xilun Zhang , Ziang Cao , Shiqi Liu , Mengdi Xu , Wenhao Ding , Jonathan Francis , Bingqing Chen , Ding Zhao

Differentiable simulation is a promising toolkit for fast gradient-based policy optimization and system identification. However, existing approaches to differentiable simulation have largely tackled scenarios where obtaining smooth…

Machine Learning · Statistics 2022-07-04 Rika Antonova , Jingyun Yang , Krishna Murthy Jatavallabhula , Jeannette Bohg

Calibrating a robot simulator's physics parameters (friction, damping, material stiffness) to match real hardware is often done by hand or with black-box optimizers that reduce error but cannot explain which physical discrepancies drive the…

Robotics · Computer Science 2026-02-24 Kevin Qiu , Yu Zhang , Marek Cygan , Josie Hughes

Using the policy gradient algorithm, we train a single-hidden-layer neural network to balance a physically accurate simulation of a single inverted pendulum. The trained weights and biases can then be transferred to a physical agent, where…

Machine Learning · Computer Science 2021-02-17 Dylan Bates