Transforming a Quadruped into a Guide Robot for the Visually Impaired: Formalizing Wayfinding, Interaction Modeling, and Safety Mechanism

TL;DR

This work addresses enabling visually impaired users to navigate with a robotic guide by formalizing the wayfinding task as an MDP, deriving a data-driven interaction model called the Delayed Harness, and enhancing safety through action shielding. It introduces a subject-customized interaction model, demonstrates substantial navigation performance gains in simulation, and validates a complete hardware pipeline on an AlienGo quadruped guiding users over long indoor routes with robust handling of orientation and timing errors. Key contributions include formalizing the task, releasing interaction data and a tunable model, integrating action shielding to reduce collisions, and showcasing real-world deployment over routes exceeding 100 meters. The results suggest a practical pathway toward safe, scalable guide robots for the visually impaired, addressing both user experience and safety requirements in real-world environments.

Abstract

This paper explores the principles for transforming a quadrupedal robot into a guide robot for individuals with visual impairments. A guide robot has great potential to resolve the limited availability of guide animals that are accessible to only two to three percent of the potential blind or visually impaired (BVI) users. To build a successful guide robot, our paper explores three key topics: (1) formalizing the navigation mechanism of a guide dog and a human, (2) developing a data-driven model of their interaction, and (3) improving user safety. First, we formalize the wayfinding task of the human-guide robot team using Markov Decision Processes based on the literature and interviews. Then we collect real human-robot interaction data from three visually impaired and six sighted people and develop an interaction model called the ``Delayed Harness'' to effectively simulate the navigation behaviors of the team. Additionally, we introduce an action shielding mechanism to enhance user safety by predicting and filtering out dangerous actions. We evaluate the developed interaction model and the safety mechanism in simulation, which greatly reduce the prediction errors and the number of collisions, respectively. We also demonstrate the integrated system on a quadrupedal robot with a rigid harness, by guiding users over $100+$~m trajectories.

Figures (8)

• Figure 1: We develop a robot guide dog by formalizing the wayfinding task, developing an interaction model from the collected data (Left), and employing action shielding, to guide a user (Right).
• Figure 2: Delayed Harness Model.
• Figure 3: Examples of Shielding Zones.
• Figure 4: (Left) Different trajectories of interaction models optimized using the collected motion capture data on each individual subject. (Right) Each subject's base positions derived from the optimized results of the delayed harness model.
• Figure 5: Hardware Platform