Full-Scale Autonomous Highway Inspection with Quadruped Robot: Multi-Level Locomotion Learning in Complex Environments
Chenxiang Ma, Chengcheng Xu, Feng Wang
AI summary
Problem
Existing highway inspection methods lack adaptability to complex terrain and long endurance, while quadruped robots lack efficient, scalable locomotion learning for diverse scenarios without labor-intensive data collection.
Approach
The method uses a three-tier reinforcement learning framework that learns basic gaits via imitation from open-source robots, trains specialized skills in modular highway scenarios, and fuses them into a unified policy through multi-skill distillation.
Key results
- 100% coverage and hazard detection rates in simulation
- Inspected 14,400 m² in 0.4 hours at 2.37 m/s
- Eliminated animal motion data collection by imitating open-source robot trajectories
- Stable traversal of modular challenges (holes, hurdles, rough terrain, obstacles) via parametric scenario modeling
Why it matters
Enables efficient, terrain-adaptive full-scale highway monitoring, offering a scalable alternative to traditional vehicles and UAVs for intelligent infrastructure maintenance.
Abstract
This paper proposes an innovative approach of full-scale autonomous highway inspection in complex environments using quadruped robot to enhance the adaptability and coverage of inspection tasks. Considering adaptive locomotion control as the foundation of autonomous inspection, a multi-level locomotion learning framework based on reinforcement learning is developed, including primitive-level, skill-level and inspection-level. Primitive-level control policy built upon Vector Quantized Variational Autoencoder is trained through imitation learning from existing open-source robots locomotion models, thereby achieving discrete embedding and reusability of foundational locomotion knowledge. At skill-level, to support diverse inspection skills learning, parametric modular scenario modeling method of the highway environment is proposed. Each skill-level control network is trained in corresponding modular scenario while reusing primitive-level control network. Inspection-level control network is established through multi-skill distillation from trained skill control networks. Combined with coverage path generator, automatic inspection can be completed. In a simulated complex highway environment, inspection robot demonstrates diverse inspection skills, successfully completing inspection of 14,400m2 area in 0.4h, with speed of 2.37m/s. Coverage and hazard detection rates both reach 100%. Compared to the existing highway inspection forms, the proposed highway inspection framework with quadruped robot enables efficient, stable, and full-scale autonomous inspection in complex highway environments, which provides general deployment capability for intelligent inspection systems.