中文
相关论文

相关论文: Differentiable Physics Simulations with Contacts: …

200 篇论文

Differentiable simulation enables gradients to be back-propagated through physics simulations. In this way, one can learn the dynamics and properties of a physics system by gradient-based optimization or embed the whole differentiable…

机器学习 · 计算机科学 2023-05-02 Yaofeng Desmond Zhong , Jiequn Han , Biswadip Dey , Georgia Olympia Brikis

Contact forces introduce discontinuities into robot dynamics that severely limit the use of simulators for gradient-based optimization. Penalty-based simulators such as MuJoCo, soften contact resolution to enable gradient computation.…

机器人学 · 计算机科学 2026-03-24 Anselm Paulus , A. René Geist , Pierre Schumacher , Vít Musil , Simon Rappenecker , Georg Martius

With the maturation of differentiable physics, its role in various downstream applications: such as model predictive control, robotic design optimization, and neural PDE solvers, has become increasingly important. However, the derivative…

机器人学 · 计算机科学 2025-09-26 Xiaohan Ye , Kui Wu , Zherong Pan , Taku Komura

Differentiable simulators promise to improve sample efficiency in robot learning by providing analytic gradients of the system dynamics. Yet, their application to contact-rich tasks like locomotion is complicated by the inherently…

Differentiable simulation establishes the mathematical foundation for solving challenging inverse problems in computer graphics and robotics, such as physical system identification and inverse dynamics control. However, rigor in frictional…

图形学 · 计算机科学 2026-05-19 Ziqiu Zeng , Gang Yang , Zhenhao Huang , Bingyang Zhou , Yulin Li , Jason Pho , Siyuan Luo , Fan Shi

Differentiable physics is a powerful approach to learning and control problems that involve physical objects and environments. While notable progress has been made, the capabilities of differentiable physics solvers remain limited. We…

机器学习 · 计算机科学 2020-07-07 Yi-Ling Qiao , Junbang Liang , Vladlen Koltun , Ming C. Lin

Differentiable simulators continue to push the state of the art across a range of domains including computational physics, robotics, and machine learning. Their main value is the ability to compute gradients of physical processes, which…

机器人学 · 计算机科学 2024-07-09 Rhys Newbury , Jack Collins , Kerry He , Jiahe Pan , Ingmar Posner , David Howard , Akansel Cosgun

In recent years, soft robotics simulators have evolved to offer various functionalities, including the simulation of different material types (e.g., elastic, hyper-elastic) and actuation methods (e.g., pneumatic, cable-driven, servomotor).…

机器人学 · 计算机科学 2025-02-03 Etienne Ménager , Louis Montaut , Quentin Le Lidec , Justin Carpentier

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…

机器学习 · 统计学 2022-07-04 Rika Antonova , Jingyun Yang , Krishna Murthy Jatavallabhula , Jeannette Bohg

We present a differentiable formulation of rigid-body contact dynamics for objects and robots represented as compositions of convex primitives. Existing optimization-based approaches simulating contact between convex primitives rely on a…

机器人学 · 计算机科学 2023-01-04 Simon Le Cleac'h , Mac Schwager , Zachary Manchester , Vikas Sindhwani , Pete Florence , Sumeet Singh

We present a novel, fast differentiable simulator for soft-body learning and control applications. Existing differentiable soft-body simulators can be classified into two categories based on their time integration methods: Simulators using…

机器学习 · 计算机科学 2021-10-12 Tao Du , Kui Wu , Pingchuan Ma , Sebastien Wah , Andrew Spielberg , Daniela Rus , Wojciech Matusik

Cloth simulation has wide applications in computer animation, garment design, and robot-assisted dressing. This work presents a differentiable cloth simulator whose additional gradient information facilitates cloth-related applications. Our…

图形学 · 计算机科学 2022-07-19 Yifei Li , Tao Du , Kui Wu , Jie Xu , Wojciech Matusik

Differentiable physics is a powerful tool in computer vision and robotics for scene understanding and reasoning about interactions. Existing approaches have frequently been limited to objects with simple shape or shapes that are known in…

计算机视觉与模式识别 · 计算机科学 2022-01-11 Michael Strecke , Joerg Stueckler

Physics simulation is ubiquitous in robotics. Whether in model-based approaches (e.g., trajectory optimization), or model-free algorithms (e.g., reinforcement learning), physics simulators are a central component of modern control pipelines…

机器人学 · 计算机科学 2024-07-23 Quentin Le Lidec , Wilson Jallet , Louis Montaut , Ivan Laptev , Cordelia Schmid , Justin Carpentier

Control techniques like MPC can realize contact-rich manipulation which exploits dynamic information, maintaining friction limits and safety constraints. However, contact geometry and dynamics are required to be known. This information is…

机器人学 · 计算机科学 2023-10-10 Kevin Haninger , Kangwagye Samuel , Filippo Rozzi , Sehoon Oh , Loris Roveda

We present a fast and feature-complete differentiable physics engine, Nimble (nimblephysics.org), that supports Lagrangian dynamics and hard contact constraints for articulated rigid body simulation. Our differentiable physics engine offers…

机器人学 · 计算机科学 2021-06-24 Keenon Werling , Dalton Omens , Jeongseok Lee , Ioannis Exarchos , C. Karen Liu

We present Jade, a differentiable physics engine for articulated rigid bodies. Jade models contacts as the Linear Complementarity Problem (LCP). Compared to existing differentiable simulations, Jade offers features including…

机器人学 · 计算机科学 2023-09-12 Gang Yang , Siyuan Luo , Lin Shao

We present a differentiable dynamics solver that is able to handle frictional contact for rigid and deformable objects within a unified framework. Through a principled mollification of normal and tangential contact forces, our method…

Collision detection plays an important role in simulation, control, and learning for robotic systems. However, no existing method is differentiable with respect to the configurations of the objects, greatly limiting the sort of algorithms…

机器人学 · 计算机科学 2022-07-04 Kevin Tracy , Taylor A. Howell , Zachary Manchester

We present DiffXPBD, a novel and efficient analytical formulation for the differentiable position-based simulation of compliant constrained dynamics (XPBD). Our proposed method allows computation of gradients of numerous parameters with…

图形学 · 计算机科学 2023-06-30 Tuur Stuyck , Hsiao-yu Chen
‹ 上一页 1 2 3 10 下一页 ›