MPC-based Controller with Terrain Insight for Dynamic Legged Locomotion
This work addresses the problem of enabling legged robots to navigate complex environments autonomously, representing an incremental improvement in terrain-aware control.
The authors tackled dynamic legged locomotion on rough terrain by developing a control strategy combining a CNN for foothold selection and an MPC for force optimization, tested in simulations with the HyQReal quadruped robot under realistic on-board conditions.
We present a novel control strategy for dynamic legged locomotion in complex scenarios, that considers information about the morphology of the terrain in contexts when only on-board mapping and computation are available. The strategy is built on top of two main elements: first a contact sequence task that provides safe foothold locations based on a convolutional neural network to perform fast and continuous evaluation of the terrain in search of safe foothold locations; then a model predictive controller that considers the foothold locations given by the contact sequence task to optimize target ground reaction forces. We assess the performance of our strategy through simulations of the hydraulically actuated quadruped robot HyQReal traversing rough terrain under realistic on-board sensing and computing conditions.