paper-with-me

홈 › Papers

Learning a Vision-Based Footstep Planner for Hierarchical Walking Control

2025-08-09 · Minku Kim, Brian Acosta, Pratik Chaudhari, Michael Posa arxiv

Bipedal robots demonstrate potential in navigating challenging terrains through dynamic ground contact. However, current frameworks often depend solely on proprioception or use manually designed visual pipelines, which are fragile in real-world settings and complicate real-time footstep planning in unstructured environments. To address this problem, we present a vision-based hierarchical control framework that integrates a reinforcement learning high-level footstep planner, which generates footstep commands based on a local elevation map, with a low-level Operational Space Controller that tracks the generated trajectories. We utilize the Angular Momentum Linear Inverted Pendulum model to construct a low-dimensional state representation to capture an informative encoding of the dynamics while reducing complexity. We evaluate our method across different terrain conditions using the underactuated bipedal robot Cassie and investigate the capabilities and challenges of our approach through simulation and hardware experiments.

📄 PDF Abstract BibTeX arXiv:2508.06779

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

The Surprising Effectiveness of Linear Models for Whole-Body Model-Predictive Control

2025-09-22 · Arun L. Bishop, Juan Alvarez-Padilla, Sam Schoedel, Ibrahima Sory Sow 외 arxiv

When do locomotion controllers require reasoning about nonlinearities? In this work, we show that a whole-body model-predictive controller using a simple linear time-invariant approximation of the whole-body dynamics is …

Learning Bipedal Walking On Planned Footsteps For Humanoid Robots

2022-07-26 · Rohan Pratap Singh, Mehdi Benallegue, Mitsuharu Morisawa, Rafael Cisneros 외

Deep reinforcement learning (RL) based controllers for legged robots have demonstrated impressive robustness for walking in different environments for several robot platforms. To enable the application of RL policies for…

Deep Reinforcement LearningMuJoCoReinforcement Learning (RL)

Dual-MPC Footstep Planning for Robust Quadruped Locomotion

2025-11-11 · Byeong-Il Ham, Hyun-Bin Kim, Jeonguk Kang, Keun Ha Choi 외 arxiv

In this paper, we propose a footstep planning strategy based on model predictive control (MPC) that enables robust regulation of body orientation against undesired body rotations by optimizing footstep placement. Model-b…

Right Model, Right Time: Real-Time Cascaded-Fidelity MPC for Bipedal Walking

2026-05-06 · Franek Stark, Felix Wiebe, Shubham Vyas, Dennis Mronga 외 arxiv

This paper presents a multi-phase whole-body model predictive control (MPC) approach for bipedal walking, combining a detailed whole-body model in the near horizon with a simplified single-rigid-body model in the later p…

Perceptive Variable-Timing Footstep Planning for Humanoid Locomotion on Disconnected Footholds

2026-03-08 · Zhaoyang Xiang, Upama Pant, Ayonga Hereid arxiv

Many real-world walking scenarios contain obstacles and unsafe ground patches (e.g., slippery or cluttered areas), leaving a disconnected set of admissible footholds that can be modeled as stepping-stone-like regions. We…