analiza aiqbench
This research introduces FARO, a framework combining kino-dynamic planning with Large Language Models to enhance the feasibility of humanoid robot motion in unseen scenarios. By integrating LLM-based contact plan sampling with reinforcement learning controllers, the method significantly improves trajectory generation for complex loco-manipulation tasks. The work addresses core challenges in scaling robotic autonomy through advanced machine learning techniques applied directly to physical execution.
FARO: Feasibility-Aware Robot Motion Optimization
arXiv:2607.18362v1 Announce Type: new Abstract: Fast planning of novel behaviors in unseen scenarios remains a fundamental challenge in robotics. The high-dimensional, hybrid, and underactuated nature of humanoid loco-manipulation continues to hinder the realization of this goal. In this paper, we address this challenge by proposing a nested kino-dynamic framework for rapid feasibility checking and dynamically consistent trajectory generation given a candidate contact sequence. By integrating this module with a feasibility-guided tree search and a Large Language Model (LLM)-based contact plan sampling strategy, we demonstrate that the proposed framework can substantially improve the search process. Furthermore, we show that the generated trajectories can be tracked using a reinforcement learning (RL)-based controller and show that the resulting trajectories are of sufficiently high quality for execution in real-world loco-manipulation scenarios. A supplementary video is available at: https://youtu.be/R6qCHoCormQ.
Abstract:Fast planning of novel behaviors in unseen scenarios remains a fundamental challenge in robotics. The high-dimensional, hybrid, and underactuated nature of humanoid loco-manipulation continues to hinder the realization of this goal. In this paper, we address this challenge by proposing a nested kino-dynamic framework for rapid feasibility checking and dynamically consistent trajectory generation given a candidate contact sequence. By integrating this module with a feasibility-guided tree search and a Large Language Model (LLM)-based contact plan sampling strategy, we demonstrate that the proposed framework can substantially improve the search process. Furthermore, we show that the generated trajectories can be tracked using a reinforcement learning (RL)-based controller and show that the resulting trajectories are of sufficiently high quality for execution in real-world loco-manipulation scenarios. A supplementary video is available at: this https URL.
Robotics (cs.RO)
arXiv:2607.18362 [cs.RO]
(or arXiv:2607.18362v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2607.18362 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 224 cuvinte
Subiecte conexe
Robot Learning to Communicate through Projected Visual Abstractions
arXiv · 28 iul. 2026
LieIPM: Lie Group Interior Point Method for Direct Trajectory Optimization of Rigid Bodies
arXiv · 10 iun. 2026
Risk-Sensitive Crowd Navigation with Adaptive Ellipsoidal Conformal Prediction
arXiv · 7 oct. 2026
OA-NBV: Occlusion-Aware Next-Best-View Planning for Human-Centered Active Perception on Mobile Robots
arXiv · 14 sept. 2026