MOBIUS: A Multi-Modal Bipedal Robot that can Walk, Crawl, Climb, and Roll

2025-11-03

AI Summary

To address the limited locomotion modalities and obstacle traversal capability of bipedal robots on complex unstructured terrain, this paper introduces MOBIUS—a multimodal bipedal robot. Methodologically, MOBIUS integrates a quadruped-inspired limb configuration with a tightly coupled morphology–planning–control architecture, enabling seamless transitions among walking, crawling, climbing, and rolling gaits. It employs a hierarchical framework: mixed-integer quadratic constrained programming (MIQCP) for high-level gait selection and reinforcement learning for low-level motion control. Furthermore, it combines model predictive control, admittance modulation, and reference compliance mechanisms to enhance contact robustness and whole-body load-bearing capacity. Hardware experiments demonstrate dynamic climbing, full-body support, and highly reliable gait transitions—significantly expanding operational workspace, traversability, and task adaptability in challenging environments.

Technology Category

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

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: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

This article presents a Multi-Modal Bipedal Intelligent Urban Scout robot (MOBIUS) capable of walking, crawling, climbing, and rolling. MOBIUS features four limbs--two 6-DoF arms with two-finger grippers for manipulation and climbing, and two 4-DoF legs for locomotion--enabling smooth transitions across diverse terrains without reconfiguration. A hybrid control architecture combines reinforcement learning-based locomotion with model-based predictive and admittance control enhanced for safety by a Reference Governor toward compliant contact interactions. A high-level MIQCP planner autonomously selects locomotion modes to balance stability and energy efficiency. Hardware experiments demonstrate robust gait transitions, dynamic climbing, and full-body load support via pinch grasp. Overall, MOBIUS demonstrates the importance of tight integration between morphology, high-level planning, and control to enable mobile loco-manipulation and grasping, substantially expanding its interaction capabilities, workspace, and traversability.

Problem

• Developing a multi-modal robot for diverse locomotion tasks
• Integrating hybrid control for safe and compliant interactions
• Enhancing robot mobility and manipulation across varied terrains

Innovation

• Multi-modal robot with limbs for diverse locomotion
• Hybrid control combining learning and model-based methods
• Autonomous planner selecting modes for efficiency stability