Walking on Rough Terrain with Any Number of Legs

2026-03-09

AI Summary

This work addresses the challenges of computationally intensive control strategies and limited adaptability commonly faced by multi-legged robots navigating complex, uneven terrain. The authors propose a lightweight, modular control architecture for hexapod to 16-legged robots, wherein each module—comprising two legs—shares three actuators and operates under a unified state machine. Modules communicate via feedforward connections, receiving inputs from preceding segments, and integrate an event-triggered cascade mechanism with a central pattern generator (CPG) to achieve contact-aware adaptive gaiting: tightly coupling with the ground upon contact and generating virtual stepping patterns when ungrounded. This approach balances robustness and computational efficiency, demonstrating stable locomotion over rough terrain in simulation and establishing an effective baseline for lightweight adaptive control and training of learning-based controllers.

Technology Category

• Intelligent Robots: Behavior Learning & Control
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior

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

Robotics would gain by replicating the remarkable agility of arthropods in navigating complex environments. Here we consider the control of multi-legged systems which have 6 or more legs. Current multi-legged control strategies in robots include large black-box machine learning models, Central Pattern Generator (CPG) networks, and open-loop feed-forward control with stability arising from mechanics. Here we present a multi-legged control architecture for rough terrain using a segmental robot with 3 actuators for every 2 legs, which we validated in simulation for robots with 6 to 16 legs. Segments have identical state machines, and each segment also receives input from the segment in front of it. Our design bridges the gap between WalkNet-like event cascade controllers and CPG-based controllers: it tightly couples to the ground when contact is present, but produces fictive locomotion when ground contact is missing. The approach may be useful as an adaptive and computationally lightweight controller for multi-legged robots, and as a baseline capability for scaffolding the learning of machine learning controllers.

Problem

• multi-legged robots
• rough terrain
• locomotion control
• legged locomotion
• robotic agility

Innovation

• multi-legged control
• segmental robot
• state machine
• fictive locomotion
• rough terrain navigation