[Paper Review] SLAM for Visually Impaired People: a Survey

Marziyeh Bamdad, Davide Scaramuzza+1 more|arXiv (Cornell University)|Dec 9, 2022

Tactile and Sensory Interactions119 references4 citations

TL;DR

This systematic literature review analyzes 54 recent SLAM-based studies (2017–present) for visually impaired navigation, evaluating visual SLAM techniques like ORB-SLAM3 for real-time localization and mapping. It identifies key challenges in dynamic environments, obstacle detection, and semantic integration, while highlighting opportunities for deep learning, cross-environment navigation, and industry-academia collaboration to advance practical assistive technologies.

ABSTRACT

In recent decades, several assistive technologies have been developed to improve the ability of blind and visually impaired (BVI) individuals to navigate independently and safely. At the same time, simultaneous localization and mapping (SLAM) techniques have become sufficiently robust and efficient to be adopted in developing these assistive technologies. We present the first systematic literature review of 54 recent studies on SLAM-based solutions for blind and visually impaired people, focusing on literature published from 2017 onward. This review explores various localization and mapping techniques employed in this context. We systematically identified and categorized diverse SLAM approaches and analyzed their localization and mapping techniques, sensor types, computing resources, and machine-learning methods. We discuss the advantages and limitations of these techniques for blind and visually impaired navigation. Moreover, we examine the major challenges described across studies, including practical challenges and considerations that affect usability and adoption. Our analysis also evaluates the effectiveness of these SLAM-based solutions in real-world scenarios and user satisfaction, providing insights into their practical impact on BVI mobility. The insights derived from this review identify critical gaps and opportunities for future research activities, particularly in addressing the challenges presented by dynamic and complex environments. We explain how SLAM technology offers the potential to improve the ability of visually impaired individuals to navigate effectively. Finally, we present future opportunities and challenges in this domain.

Motivation & Objective

• To analyze the state of the art in SLAM-based assistive technologies for blind and visually impaired (BVI) individuals since 2017.
• To identify the dominant SLAM techniques, sensor modalities, and system architectures used in BVI navigation research.
• To evaluate the advantages and limitations of SLAM in real-world BVI navigation scenarios, including obstacle detection and environmental adaptability.
• To uncover persistent challenges such as performance in dynamic, cluttered, or low-light environments and the lack of real-world deployment.
• To identify future research opportunities, including semantic SLAM, unified indoor-outdoor navigation, and collaboration between academia and industry.

Proposed method

• Conducted a systematic literature review (SLR) of 54 studies published from 2017 onward, following PRISMA guidelines for selection and analysis.
• Classified studies based on SLAM technique (e.g., visual SLAM, RGB-D, LiDAR, hybrid), sensor types (cameras, IMUs, UWB, LiDAR), and application context (indoor/outdoor).
• Extracted data on localization accuracy, real-time performance, obstacle detection capabilities, and user feedback mechanisms.
• Evaluated SLAM components—front-end (feature extraction, sensor fusion) and back-end (optimization, loop closure)—for robustness in BVI contexts.
• Mapped challenges across studies, including lighting variability, dynamic obstacles, and system reliability under real-world conditions.
• Identified gaps in semantic understanding, long-term navigation stability, and integration of deep learning for context-aware feedback.

Experimental results

Research questions

• RQ1 Which SLAM techniques and sensor combinations are most commonly used in assistive navigation systems for visually impaired users?
• RQ2 What are the primary advantages and limitations of SLAM-based navigation in real-world environments for BVI individuals?
• RQ3 How do current SLAM systems handle obstacle detection, especially in dynamic or complex environments?
• RQ4 What challenges hinder the transition from research prototypes to practical, deployable assistive devices for BVI users?
• RQ5 What future research directions—such as semantic SLAM, unified indoor-outdoor navigation, or deep learning integration—hold the most promise for improving BVI mobility?

Key findings

• The majority of reviewed studies (especially post-2017) rely on visual SLAM techniques, with ORB-SLAM3 being the most frequently used framework due to its accuracy and real-time performance.
• Most systems are prototype-stage and lack long-term robustness, especially in dynamic or low-light environments, indicating a gap between research and real-world deployment.
• Obstacle detection remains a challenge, with limited depth and semantic understanding—many systems fail to detect small or head-level obstacles reliably.
• Only a minority of studies integrate semantic information (e.g., doorways, stairs, furniture) into SLAM maps, despite its potential to improve localization and navigation safety.
• There is a strong need for unified indoor-outdoor navigation solutions, as most reviewed systems are limited to indoor environments, restricting user independence.
• Collaboration between academia and industry is minimal, and no standardized platform exists, which hinders product development and scalability of assistive SLAM systems.