aiqbench analysis
This research addresses the open challenge of quadruped robot manipulation by introducing a hierarchical reinforcement learning framework that autonomously selects interaction points and base poses, eliminating the need for pre-designed trajectories. Validated in both simulation and real-world settings, the approach enables effective object-centric alignment and end-effector planning without human guidance. The work represents a significant step toward fully autonomous quadruped operation in complex physical environments.
Affordance-Based Hierarchical Reinforcement Learning for Quadruped Pedipulation
arXiv:2606.07506v1 Announce Type: new Abstract: The object manipulation capabilities of quadruped robots is an open research challenge. While previous studies have focused on low-level policy learning, task execution still relies on expert-designed high-level trajectories. Autonomous selection of both an affordable interaction point on the target object and an affordable robot base pose removes the need for pre-designed trajectories. This study proposes a three-level hierarchical reinforcement learning (RL) framework that utilizes pose affordances to guide the navigation policy, while the navigation policy drives the locomotion policy. In addition, the pedipulation policy is guided by interaction-point affordances, enabling object-centric pose alignment of the quadruped robot and effective end-effector manipulation planning. We train the proposed framework in the IsaacSim ecosystem and evaluate it in both simulation and real-world settings. We investigate the effectiveness of pose affordance across multiple scenarios in simulation while various object interaction tasks are validated on real-world setting forming an object-interaction dataset. The results show that the proposed framework can autonomously identify candidate poses based on their affordance and successfully execute object manipulation tasks in the real world without human guidance.
Abstract:The object manipulation capabilities of quadruped robots is an open research challenge. While previous studies have focused on low-level policy learning, task execution still relies on expert-designed high-level trajectories. Autonomous selection of both an affordable interaction point on the target object and an affordable robot base pose removes the need for pre-designed trajectories. This study proposes a three-level hierarchical reinforcement learning (RL) framework that utilizes pose affordances to guide the navigation policy, while the navigation policy drives the locomotion policy. In addition, the pedipulation policy is guided by interaction-point affordances, enabling object-centric pose alignment of the quadruped robot and effective end-effector manipulation planning. We train the proposed framework in the IsaacSim ecosystem and evaluate it in both simulation and real-world settings. We investigate the effectiveness of pose affordance across multiple scenarios in simulation while various object interaction tasks are validated on real-world setting forming an object-interaction dataset. The results show that the proposed framework can autonomously identify candidate poses based on their affordance and successfully execute object manipulation tasks in the real world without human guidance.
Robotics (cs.RO)
arXiv:2606.07506 [cs.RO]
(or arXiv:2606.07506v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2606.07506 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.
Full text under the publisher's open licence · 269 words
Related coverage
Training and Simulation of Quadrupedal Robot in Adaptive Stair Climbing and Descending for Indoor Firefighting: An End-to-End Reinforcement Learning Approach
arXiv · Jul 23, 2026
SOMA: Stack-of-Objects Manipulation using a Quadruped Robot
arXiv · Oct 17, 2026
Energy-Efficient Gait Adaptation via Hierarchical Reinforcement Learning for Quadrupedal Locomotion Across Diverse Terrains
arXiv · Oct 8, 2026
GUIDE: Goal-Initialized Directional Understanding for End-to-End Visual Navigation
arXiv · Jun 10, 2026