Search papers, labs, and topics across Lattice.
GASP is a novel GPU-Accelerated Safe Planner designed for real-time, collision-aware motion generation in known environments, utilizing a combination of clamped B-spline trajectory parameterization and a convolutional residual neural network to predict control points. The method incorporates a conditional variational autoencoder for sampling multiple trajectory candidates, enabling efficient parallel validation on the GPU, which results in near-millisecond inference times. Validation in robotic table tennis shows that GASP not only matches baseline performance but also significantly reduces training-time collisions, demonstrating its practical applicability in dynamic settings.
GASP achieves analytical-level success in collision-aware motion generation while cutting inference time to near milliseconds, revolutionizing real-time planning for robotics.
We present GASP, a GPU-Accelerated Safe Planner for real-time, collision-aware joint-space motion generation in known environments. GASP combines a clamped B-spline trajectory parameterization with a convolutional residual neural network that predicts the free interior control points, while analytically inserted boundary control points enforce initial and final derivative constraints for collision-aware planning under non-stationary conditions. A conditional variational autoencoder samples multiple trajectory candidates, which are decoded and validated in parallel on the GPU, yielding a batched planner for collision-aware coupled joint-space motion with near-millisecond inference. We validate GASP as an online motion-generation module, where it achieves analytical-level success rates with high collision-aware feasibility and substantially reduces inference time relative to GPU-based trajectory optimization. We further deploy GASP as a reinforcement-learning reset planner in competitive robotic table tennis, matching the baseline return rate while roughly halving training-time collisions.
