Search papers, labs, and topics across Lattice.
CRESSim-Neo is a novel batched GPU simulation engine designed for surgical robotics and robot learning, integrating position-based simulation of various physical elements with advanced rendering and sensing capabilities. This engine enables high-performance simulations, achieving up to 2.03 million environment steps per second while supporting complex tasks such as tissue manipulation and ultrasound image synthesis. The direct access to physics and rendering buffers facilitates GPU-resident robot learning and seamless integration with PyTorch, marking a significant advancement in the efficiency and scalability of surgical simulations.
Achieving over 2 million environment steps per second, CRESSim-Neo revolutionizes surgical robotics simulation with unprecedented efficiency and scalability.
We introduce CRESSim-Neo, a batched GPU simulation engine for surgical robotics and robot learning. CRESSim-Neo combines position-based simulation of rigid bodies, deformable tissues, fluids, and strands with batched rendering, surgery-specific sensing, and a GPU-resident data pipeline. The engine supports applications including tissue manipulation, fluid suction, suturing, cable-driven robots, and ultrasound image synthesis. Direct access to physics and rendering buffers enables GPU-resident robot learning and zero-copy PyTorch integration using DLPack. We demonstrate CRESSim-Neo across rigid-body, deformable-body, and fluid simulation tasks, including vision-based and surgical robot-learning scenarios. On an NVIDIA RTX 4090, the engine achieves up to 2.03 million environment steps per second for 8192 parallel CartPole environments, and scales to batched surgical scenarios involving tissue deformation, fluid interaction, and ultrasound sensing. Overall, CRESSim-Neo provides a unified and scalable platform for surgical simulation, synthetic data generation, and surgical robot learning.
