Search papers, labs, and topics across Lattice.
This paper introduces a SIMD-accelerated manifold-constrained motion planner for robots, focusing on parallelizing projection-based constraint satisfaction. By restructuring the planning components for parallel execution, the method achieves 100-1000x speedups compared to existing approaches. The planner is demonstrated on a humanoid robot, enabling real-time whole-body quasi-static plan generation.
Real-time constrained motion planning for complex robots is now feasible, thanks to a 100-1000x speedup achieved through SIMD parallelization of projection-based constraint satisfaction.
Many robot planning tasks require satisfaction of one or more constraints throughout the entire trajectory. For geometric constraints, manifold-constrained motion planning algorithms are capable of planning collision-free path between start and goal configurations on the constraint submanifolds specified by task. Current state-of-the-art methods can take tens of seconds to solve these tasks for complex systems such as humanoid robots, making real-world use impractical, especially in dynamic settings. Inspired by recent advances in hardware accelerated motion planning, we present a CPU SIMD-accelerated manifold-constrained motion planner that revisits projection-based constraint satisfaction through the lens of parallelization. By transforming relevant components into parallelizable structures, we use SIMD parallelism to plan constraint satisfying solutions. Our approach achieves up to 100-1000x speed-ups over the state-of-the-art, making real-time constrained motion planning feasible for the first time. We demonstrate our planner on a real humanoid robot and show real-time whole-body quasi-static plan generation. Our work is available at https://commalab.org/papers/mcvamp/.
