HeLoM: Hierarchical Learning for Whole-Body Loco-Manipulation in Hexapod Robot

2025-09-28

AI Summary

Hexapod robots face significant challenges in simultaneously ensuring manipulation force and whole-body stability when pushing heavy (≥ self-weight) or irregular objects in unstructured real-world environments. Method: This paper proposes an insect-inspired hierarchical learning framework that decouples high-level behavioral planning from low-level dynamic control. It integrates hierarchical reinforcement learning, multi-limb redundant contact coordination, real-time dynamic force modulation, and holistic stability assurance. By optimizing foot-ground contact distribution and whole-body torque allocation, the framework achieves robust pose regulation for objects with unknown physical properties and varying geometries. Contribution/Results: The method enables efficient sim-to-real transfer without extensive hyperparameter tuning. It successfully accomplishes high-difficulty box-pushing tasks in both simulation and on a physical robot platform, demonstrating strong generalization, robustness against environmental and object uncertainties, and practical engineering applicability.

Technology Category

• Intelligent Robots: Manipulation
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Machine Learning: Imitation Learning & Inverse Reinforcement Learning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Robots in real-world environments are often required to move/manipulate objects comparable in weight to their own bodies. Compared to grasping and carrying, pushing provides a more straightforward and efficient non-prehensile manipulation strategy, avoiding complex grasp design while leveraging direct contact to regulate an object's pose. Achieving effective pushing, however, demands both sufficient manipulation forces and the ability to maintain stability, which is particularly challenging when dealing with heavy or irregular objects. To address these challenges, we propose HeLoM, a learning-based hierarchical whole-body manipulation framework for a hexapod robot that exploits coordinated multi-limb control. Inspired by the cooperative strategies of multi-legged insects, our framework leverages redundant contact points and high degrees of freedom to enable dynamic redistribution of contact forces. HeLoM's high-level planner plans pushing behaviors and target object poses, while its low-level controller maintains locomotion stability and generates dynamically consistent joint actions. Our policies trained in simulation are directly deployed on real robots without additional fine-tuning. This design allows the robot to maintain balance while exerting continuous and controllable pushing forces through coordinated foreleg interaction and supportive hind-leg propulsion. We validate the effectiveness of HeLoM through both simulation and real-world experiments. Results show that our framework can stably push boxes of varying sizes and unknown physical properties to designated goal poses in the real world.

Problem

• Enables hexapod robots to push heavy objects while maintaining stability
• Uses hierarchical learning for coordinated multi-limb whole-body manipulation
• Achieves dynamic force redistribution for pushing unknown objects to goals

Innovation

• Hierarchical learning framework for hexapod robots
• Coordinated multi-limb control for object pushing
• Simulation-trained policies directly deployed without fine-tuning