Track the frontier, from condensed matter to cosmology.
Search papers, labs, and topics across Lattice.
CQDC-Warp introduces a GPU-accelerated differentiable quasi-dynamic simulator for batched model predictive control, enabling efficient synthesis of contact-rich manipulation trajectories by jointly optimizing motion and contact decisions without explicit mode schedules. This approach achieves significantly higher success rates and drastically reduced computation times on complex manipulation benchmarks compared to existing methods. The framework demonstrates impressive throughput, processing millions of world-steps per second on a single GPU, and generalizes to various robotic hands and manipulation tasks.
A single GPU can now plan complex, contact-rich robotic manipulation trajectories for thousands of parallel worlds, achieving near-80% success on challenging in-hand rotation tasks with unprecedented speed.
Efficient synthesis of contact-rich manipulation trajectories is essential for downstream robot learning. Gradient-based planning offers a promising approach, but jointly optimizing motion and contact decisions remains challenging. Meanwhile, many existing planners run on CPUs with limited throughput. We present CQDC-Warp, a GPU-accelerated differentiable quasi-dynamic simulator for batched model predictive control (MPC). We use it to study contact-guided trajectory optimization, in which intended robot--object contacts are specified before planning and encouraged through soft costs, while the simulated dynamics determine contact geometry and frictional response without a prescribed contact-mode schedule. Across $17{,}408$ trials on the $17$-object Allegro in-hand rotation benchmark, our framework achieves $79.8\%$ success, compared with $73.7\%$ for CFree and $65.2\%$ for IMPACT, and reduces mean trajectory-generation time by factors of $27.0$ and $50.2$, respectively. On a single NVIDIA RTX 4090 with $2{,}048$ parallel worlds, forward and backward throughput reach $2.06\times10^5$ and $2.25\times10^5$ world-steps per second, respectively. Further experiments cover manipulation with LEAP and Shadow hands, environmental contact exploitation, bimanual manipulation, whole-body control, and real-world trajectory replay on a Sharpa hand.