SF-TIM: A Simple Framework for Enhancing Quadrupedal Robot Jumping Agility by Combining Terrain Imagination and Measurement

2024-08-01

arXiv.org

AI Summary

To address the limitations of quadrupedal robots in agile high-platform ascents and gap-crossing jumps, as well as the difficulty in simultaneously achieving blind locomotion and effective sim-to-real transfer, this paper proposes a unified single-policy control framework. Methodologically, it integrates proprioceptive sensing with real-time high-precision terrain estimation, introducing a lightweight “terrain imagination–measurement fusion” architecture. A terrain-guided sparse reward design enables concurrent blind navigation and explosive jumping, while sim-to-real co-training ensures zero-shot deployment. Contributions include: (i) the first demonstration of unified multimodal locomotion control under a single policy; (ii) significantly enhanced robustness in traversing complex gaps and height-discontinuity terrains; and (iii) real-time, zero-fine-tuning deployment on both small- and large-scale quadrupeds in physical environments, validating strong generalizability and engineering practicality.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Multi-modal Vision
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments

Abstract

Dynamic jumping on high platforms and over gaps differentiates legged robots from wheeled counterparts. Compared to walking on rough terrains, dynamic locomotion on abrupt surfaces requires fusing proprioceptive and exteroceptive perception for explosive movements. In this paper, we propose SF-TIM (Simple Framework combining Terrain Imagination and Measurement), a single-policy method that enhances quadrupedal robot jumping agility, while preserving their fundamental blind walking capabilities. In addition, we introduce a terrain-guided reward design specifically to assist quadrupedal robots in high jumping, improving their performance in this task. To narrow the simulation-to-reality gap in quadrupedal robot learning, we introduce a stable and high-speed elevation map generation framework, enabling zero-shot simulation-to-reality transfer of locomotion ability. Our algorithm has been deployed and validated on both the small-/large-size quadrupedal robots, demonstrating its effectiveness in real-world applications: the robot has successfully traversed various high platforms and gaps, showing the robustness of our proposed approach. A demo video has been made available at https://flysoaryun.github.io/SF-TIM.

Problem

• Enhancing quadrupedal robot jumping agility
• Integrating terrain imagination and measurement
• Narrowing simulation-to-reality gap in locomotion

Innovation

• Combines terrain imagination with measurement
• Uses terrain-guided reward for high jumping
• Enables zero-shot simulation-to-reality transfer