We present Kamino, a GPU-based physics solver for massively parallel simulations of heterogeneous highly-coupled mechanical systems. Implemented in Python using NVIDIA Warp and integrated into the Newton framework, it enables the application of data-driven methods, such as large-scale reinforcement learning, to complex robotic systems that exhibit strongly coupled kinematic and dynamic constraints such as kinematic loops. The latter are often circumvented by approximating the system's topology as a kinematic tree, and incorporating explicit loop-closure constraints or so-called mimic joints. Kamino aims at alleviating this burden by natively supporting these types of couplings. Moreover, Kamino supports heterogeneous worlds, allowing for batched simulation of structurally diverse robots on a single GPU. At its core lies a state-of-the-art constrained optimization algorithm based on ADMM, which computes constraint forces by solving the constrained rigid multi-body forward dynamics transcribed as a nonlinear complementarity problem. This leads to high-fidelity simulations that resolve contact dynamics without resorting to approximate models that simplify or convexify the problem. We demonstrate RL policy training on a biped with six nested kinematic loops, generating a feasible walking policy while simulating $4{,}096$ parallel environments on a single GPU.
CRESSim-MPM: A Material Point Method Library for Surgical Soft Body Simulation with Cutting and Suturing
Department of Electrical and Computer Engineering, University of Alberta(电气与计算机工程系,阿尔伯塔大学);Department of Biomedical Engineering, University of Alberta(生物医学工程系,阿尔伯塔大学)
S4R: Scaling for Rigid-Body Interpenetration Resolution
MIT CSAIL(麻省理工学院计算机科学与人工智能实验室);Xiamen University(厦门大学);The University of Hong Kong(香港大学);Macau University of Science and Technology(澳门科技大学);The Hong Kong University of Science and Technology(香港科技大学);The University of Texas at Dallas(德克萨斯大学达拉斯分校)