Primal-Dual iLQR for GPU-Accelerated Learning and Control in Legged Robots
By: Lorenzo Amatucci , João Sousa-Pinto , Giulio Turrisi and more
Potential Business Impact:
Robots walk and move much faster.
This paper introduces a novel Model Predictive Control (MPC) implementation for legged robot locomotion that leverages GPU parallelization. Our approach enables both temporal and state-space parallelization by incorporating a parallel associative scan to solve the primal-dual Karush-Kuhn-Tucker (KKT) system. In this way, the optimal control problem is solved in $\mathcal{O}(n\log{N} + m)$ complexity, instead of $\mathcal{O}(N(n + m)^3)$, where $n$, $m$, and $N$ are the dimension of the system state, control vector, and the length of the prediction horizon. We demonstrate the advantages of this implementation over two state-of-the-art solvers (acados and crocoddyl), achieving up to a 60\% improvement in runtime for Whole Body Dynamics (WB)-MPC and a 700\% improvement for Single Rigid Body Dynamics (SRBD)-MPC when varying the prediction horizon length. The presented formulation scales efficiently with the problem state dimensions as well, enabling the definition of a centralized controller for up to 16 legged robots that can be computed in less than 25 ms. Furthermore, thanks to the JAX implementation, the solver supports large-scale parallelization across multiple environments, allowing the possibility of performing learning with the MPC in the loop directly in GPU.
Similar Papers
Whole-Body Model-Predictive Control of Legged Robots with MuJoCo
Robotics
Robots walk and move more like humans.
Differentiable Model Predictive Control on the GPU
Optimization and Control
Makes robots learn to drive better, faster.
Parallel Branch Model Predictive Control on GPUs
Systems and Control
Makes self-driving cars react much faster.