Organizations: Department of Computer Engineering, Amirkabir University of Technology (Tehran Polytechnic), Tehran, Iran · University of Toronto, Toronto, Canada · York University, Toronto, Canada · Department of Mathematics and Informatics, Al-Khwarizmi University, Urgench, 220100, Uzbekistan
Independent mobility is a foundational requirement for the autonomy of blind and low-vision (BLV) individuals, yet the assistive technologies that support it have historically evolved slowly. This survey systematically reviews 108 peer-reviewed studies published between 2008 and 2026, organizing the field into four technological eras: (i) a foundational era of passive mechanical aids, namely the white cane and the guide dog; (ii) a hardware era of electronic travel aids built on ultrasonic, infrared, and satellite positioning sensors that alert users to proximity but lack semantic understanding; (iii) a deep learning era in which convolutional and transformer-based detectors introduced context-aware scene understanding, initially tethered to cloud infrastructure; and (iv) a contemporary edge-native era defined by model compression, quantization, hardware acceleration, and multi-sensor fusion that relocate intelligence onto resource-constrained wearable and mobile devices. For each era we analyze representative systems, sensing modalities, computational architectures, and reported performance, and we consolidate the field's model-optimization techniques into a single technical reference spanning four detector families and twelve compression strategies. Across the corpus, we find a persistent mismatch between rapid algorithmic progress and slow real-world adoption, driven by cognitive overload in user interfaces, fragmented evaluation protocols, and the scarcity of studies involving BLV participants. We conclude with open challenges, including seamless indoor-outdoor transition, standardized benchmarks, privacy-preserving perception, and the emerging role of multimodal foundation models, and outline a roadmap for socially acceptable, user-centered assistive navigation.
Figures & tables
Figure 1: PRISMA flow diagram of the study selection process [ 18 ] , from initial identification through to the 108 studies synthesized in this survey.
Figure 2: The four-era genealogy of BLV assistive navigation technologies used to organize this survey. Each era is defined by its dominant sensing substrate, computational paradigm, and connectivity assumption; representative systems for each era are compared in Table 4.5 .
Figure 3: Pham et al. ’s Kinect-based pipeline: an RGB-D camera feeds obstacle detection via RANSAC floor-plane fitting, with output routed to audio or a sensory-substitution device. Redrawn after Pham et al. [ 42 ] .
Figure 4: Evolution of the four object-detection families used across the corpus, positioned by publication year (x-axis, 2014–2025). YOLOv8 (via [ 57 , 23 , 32 ] and others), R-CNN (as a comparison baseline [ 1 ] ), SSD/MobileNet-SSD [ 58 , 52 , 59 ] , and DETR [ 56 ] are the specific versions with direct assistive-system adoptions documented in this survey; the remaining nodes mark the family’s technical lineage. Edge-mobility verdicts for each family are summarized in Table 4.3.5 .
\tablecaptionfont \tablenumfont Table 1. Representative assistive navigation systems across the four eras. US = ultrasonic; TTS = text-to-speech; RPi = Raspberry Pi; “BLV study” = evaluation with blind or low-vision participants; n.r. = no such evaluation reported in the source consulted. The column was assigned by a full-text keyword search of each source for participant- and user-study-related language. Five of the 22 systems listed report testing with confirmed BLV participants, and one further system reports a single-participant pilot of unconfirmed BLV status.
Visual impairment affects over 2.2 billion people worldwide, yet conventional white canes cannot detect elevated hazards or provide semantic environmental context. Existing AI-assisted navigation systems typically rely on expensive hardware or cloud connectivity, limiting accessibility in resource-constrained settings. This paper presents an affordable ($88 USD), fully offline AI-integrated smart cane designed for multimodal mobility assistance on an ultra-low-power Raspberry Pi Zero 2W. The system fuses RGB vision sensing with Time-of-Flight (ToF) distance estimation, pairing an INT8-quantized SSD MobileNet V1 model with distance-aware vibrotactile feedback and real-time audio alerts. To ensure operational robustness on constrained hardware, a multiprocessing architecture isolates sensor acquisition, neural inference, and haptic feedback into independent processes with fail-safe sensing support. Experimental evaluation across indoor mobility scenarios demonstrates a macro-averaged F1-score of 0.82 (precision: 0.85, recall: 0.81), a mean end-to-end latency of 330,ms, and a peak power draw of 2.8,W. A preliminary usability study with 12 participants (SUS: 78.5, NASA-TLX) demonstrated positive user perception and enhanced obstacle awareness. The proposed prototype validates the feasibility of deploying privacy-preserving, edge-native assistive intelligence for cost-sensitive mobility assistance.
Ali Akarma, Adeel Ahmad, Toqeer Ali Syed
AI Center, Faculty of Computer and Information Systems, Islamic University of Madinah, Madinah 42351, Saudi Arabia · AI V&V Lab, King Fahd University of Petroleum and Minerals, Dhahran 31261, Saudi Arabia
Blindness and low vision limit many people's ability to complete daily tasks, motivating AI assistants that provide useful guidance. Yet, existing benchmarks do not adequately test whether vision models can provide effective everyday assistance. In particular, i) existing benchmarks primarily rely on visual and textual inputs, with limited support for other modalities that are increasingly available in egocentric wearable devices such as gaze, inertial measurements, spatial trajectories, and others; and ii) existing evaluations emphasize scene understanding and question answering, with limited coverage of goal-conditioned guidance for blind and low-vision users across everyday tasks. To bridge this gap, we introduce VISTA (Visually Impaired Scene and Task Annotations), a multimodal egocentric benchmark for goal-oriented assistance for blind and low-vision users. VISTA contains ∼1,000 egocentric recordings captured with Project Aria glasses; each recording provides synchronized sensor streams, six of which serve as model inputs, and three different types of annotation, covering ten task categories (TC), from object localization to hazard detection. We evaluate 14 representative vision-language models zero-shot on VISTA and design a lightweight multimodal model baseline that integrates all six modalities. Experimental results show that, although existing models can often describe egocentric scenes, they remain limited in generating goal-directed assistive guidance. VISTA thus provides a benchmark for evaluating multimodal models that could improve everyday accessibility.
Noé Mosca, Mohamed Rayan Barhdadi, Muhammad Hamza +11
Harvard AI and Robotics Lab, Harvard University · Télécom Paris, Institut Polytechnique de Paris · Texas A&M University +2
Blind and low-vision users often face challenges when locating and physically acquiring objects in unfamiliar indoor environments. Existing vision-language-model-based assistants can provide semantic descriptions but may introduce latency, hallucinations, and guidance that is poorly aligned with embodied action. We present Touvigation, a hands-free object acquisition system that combines vision-language understanding with persistent local spatial modeling to provide low-latency, body-relative guidance. Drawing on formative interviews with eight blind and low-vision participants, we design a multi-stage guidance framework that adapts spatial references as users transition from orienting, to walking, to reaching and tactile verification. We evaluated Touvigation with 12 blind and low-vision participants against a multimodal large-language-model assistant and unassisted search. Touvigation achieved 100% task success, compared with 58% for the multimodal assistant and 85% for unassisted search, while reducing completion time and cognitive workload. Our findings demonstrate how persistent spatial grounding and adaptive embodied guidance can improve object acquisition for blind and low-vision users.
George Xi Wang, Xiangyu Li, Shaoyue Wen +8
Stony Brook University, United States · New York University, United States · Brown University, United States +6