Year: 2025
Type: article
Abstract: We address the problem of humanoid locomotion in a 3D environment composed of planar regions with arbitrary inclination and elevation, which includes staircases, ramps, and multi‑floor layouts. The proposed framework couples an off‑line randomized footstep planner with an on‑line control pipeline comprising a model predictive controller and a whole‑body controller which provides the robot torque commands. The planner efficiently explores the environment without predefined motion primitives and returns the highest-quality plan it can find within a user‑specified time budget, while the control layer ensures dynamic balance and adequate ground friction. The complete pipeline is evaluated in MuJoCo using the JVRC1 humanoid across four scenarios of increasing complexity.
Source: Robotics
Institution: Sapienza University of Rome
Language: English
Subfield: Biomedical Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $2,172
Award: G5371376445
OpenAlex ID: W4411338157