Obstacle-Avoidant Leader Following with a Quadruped Robot

2024-10-01

arXiv.org

AI Summary

To address challenges in narrow, dynamic environments—including unnatural operator following, poor obstacle-avoidance robustness, and high teleoperation fatigue—this paper proposes a virtual-leash-based leader-follower navigation method for quadrupedal robots. We innovatively design a legged-platform-specific local obstacle-avoidance planner that fuses RF beacons, RGB cameras, and LiDAR for heterogeneous sensor cooperative localization and tracking. Integrating model predictive control with terrain-adaptive local path planning, the system achieves end-to-end deployment on the ANYmal platform. Experiments in real-world scenarios demonstrate sub-meter following accuracy (mean error < 0.3 m), millisecond-level response latency, and real-time avoidance of highly dynamic obstacles. The approach significantly enhances human-robot collaborative mobility efficiency and operational safety.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• 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
• Security and Privacy: Large-scale security measurements

Abstract

Personal mobile robotic assistants are expected to find wide applications in industry and healthcare. For example, people with limited mobility can benefit from robots helping with daily tasks, or construction workers can have robots perform precision monitoring tasks on-site. However, manually steering a robot while in motion requires significant concentration from the operator, especially in tight or crowded spaces. This reduces walking speed, and the constant need for vigilance increases fatigue and, thus, the risk of accidents. This work presents a virtual leash with which a robot can naturally follow an operator. We use a sensor fusion based on a custom-built RF transponder, RGB cameras, and a LiDAR. In addition, we customize a local avoidance planner for legged platforms, which enables us to navigate dynamic and narrow environments. We successfully validate on the ANYmal platform the robustness and performance of our entire pipeline in real-world experiments.

Problem

• Develops a virtual leash for robot following.
• Enables navigation in dynamic, narrow environments.
• Reduces operator fatigue and accident risks.

Innovation

• Virtual leash enables natural robot following.
• Sensor fusion combines RF, RGB, and LiDAR.
• Custom avoidance planner for legged robots.