Paper accepted at IEEE-RAS 20th International Conference on Humanoid Robots (Humanoids 2021)
Congratulations to Jiayi Wang, Sanghyun Kim, Sethu Vijayakumar and Steve Tonneau
- Jiayi Wang, Sanghyun Kim, Sethu Vijayakumar and Steve Tonneau, Multi-Fidelity Receding Horizon Planning for Multi-Contact Locomotion, Proc. IEEE-RAS 20th International Conference on Humanoid Robots (Humanoids 2021), Munich, Germany (2021).
When traversing uneven terrain, humans consider their future steps for choosing the best location and timing of their current step. Likewise, when planning multi-contact motions for legged robots (e.g. humanoids), a “prediction horizon” has to be considered. However, this increases the dimensionality and non-linearity of an already challenging problem, which makes online planning intractable. We propose to reduce the problem complexity by using convex relaxations in the prediction horizon. We realize this idea within a Receding Horizon Planning (RHP) framework to plan dynamically consistent centroidal trajectories of humanoid walking on uneven terrain. This results in a novel formulation that combines an accurate non-convex model with a relaxed convex model, which we call RHP with multiple levels of model fidelity. We evaluate three candidate multi-fidelity RHPs and the best is 1.4x-3.0x (average 2.4x) faster than the traditional single-fidelity RHP. Further, we find that incorporating angular dynamics in the prediction horizon is important to the success of multi-fidelity RHP.