Granular Loco-Manipulation: Repositioning Rocks Through Strategic Sand Avalanche

2025-05-19

AI Summary

To address locomotion challenges faced by legged robots on steep, granular slopes obstructed by rocks and similar terrain irregularities, this paper proposes an indirect obstacle repositioning method inspired by the “sand-flow avalanche” mechanism. The core innovation is the first-ever diffusion-model-driven joint prediction framework that unifies modeling of granular environment evolution—specifically, obstacle displacement induced by localized sand avalanches—and robot state dynamics—namely, multi-legged loco-manipulation coordination. Integrating granular dynamics, legged motion planning, and closed-loop control, the method enables autonomous, environment-aware interaction in unstructured loose-media terrains. Evaluated in 90 field experiments on sandy slopes, it successfully relocated densely packed rocks to designated target positions with an average success rate exceeding 65%, thereby significantly enhancing autonomous mobility and physical interaction capability in complex granular environments.

Technology Category

• Intelligent Robots: Motion and Path Planning
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Legged robots have the potential to leverage obstacles to climb steep sand slopes. However, efficiently repositioning these obstacles to desired locations is challenging. Here we present DiffusiveGRAIN, a learning-based method that enables a multi-legged robot to strategically induce localized sand avalanches during locomotion and indirectly manipulate obstacles. We conducted 375 trials, systematically varying obstacle spacing, robot orientation, and leg actions in 75 of them. Results show that the movement of closely-spaced obstacles exhibits significant interference, requiring joint modeling. In addition, different multi-leg excavation actions could cause distinct robot state changes, necessitating integrated planning of manipulation and locomotion. To address these challenges, DiffusiveGRAIN includes a diffusion-based environment predictor to capture multi-obstacle movements under granular flow interferences and a robot state predictor to estimate changes in robot state from multi-leg action patterns. Deployment experiments (90 trials) demonstrate that by integrating the environment and robot state predictors, the robot can autonomously plan its movements based on loco-manipulation goals, successfully shifting closely located rocks to desired locations in over 65% of trials. Our study showcases the potential for a locomoting robot to strategically manipulate obstacles to achieve improved mobility on challenging terrains.

Problem

• Repositioning rocks via sand avalanches using legged robots
• Modeling interference in closely-spaced obstacle movement
• Integrating locomotion and manipulation planning for granular terrains

Innovation

• Learning-based method for sand avalanche manipulation
• Diffusion-based predictor for multi-obstacle movement modeling
• Integrated planning of locomotion and obstacle manipulation