Jul 2026· Annual International Computer Software and Applications Conference· pp. 531-536· 0 citations· 23 references
Abstract
Indoor navigation systems for visually impaired (VI) users typically rely on continuous sonification over pre-built semantic maps, which leads to two compounding problems: auditory fatigue from constant audio output, and unsafe guidance when the map becomes stale due to environmental changes. We propose a multi-agent architecture that addresses both challenges. The system consists of three collaborating agents: an Environment Perception Agent that monitors spatial complexity and maintains per-object reliability scores that reflect the likelihood that mapped objects remain accurate, a User State Inference Agent that estimates user confidence from movement patterns, and a Sonification Planning Agent trained via reinforcement learning to decide when and how much audio feedback to provide. The system adapts its sonification not only to user state and spatial context, but also to map uncertainty, increasing audio support in areas where the map may be outdated. We evaluate the system in simulation with a literature-grounded user behavior model across varying levels of map staleness. Results across 5,000 episodes show that our approach reduces sonification volume by 53% compared to always-on sonification baselines while maintaining a 98.7% hazard notification rate under fresh maps. Under severely stale maps (one week old), our system degrades only 21% in navigation efficiency compared to 27-33% for the other baselines.
Assistive technologies for people with visual impairments increasingly use artificial intelligence to support object-finding and navigation in indoor environments. Yet fully autonomous perception remains unreliable in such settings, as indoor spaces are visually complex, only partially observable from the user’s current viewpoint, and subject to continuous change. Our work takes the position that effective assistive navigation is inherently collaborative; the system performs continuous perceptual processing, while the user provides occasional natural-language guidance when the search becomes uncertain or inefficient. To this end, we propose a human–AI collaboration framework that utilizes a Vision-Language Model (VLM) as the perceptual and semantic backbone of a navigation agent. A human user, modeled by a simulated intervention controller, provides sparse and structured guidance, which is integrated with the VLM to update its semantic search hypotheses toward the likely location of the target object. Evaluation is conducted in the Habitat simulator on photorealistic scenes from the Habitat-Matterport3D dataset. Experiments analyze how human guidance affects task success and navigation efficiency, showing that guidance is most effective when it corrects the VLM's misaligned semantic search hypotheses, providing insights into the role of minimal human input in VLM-based assistive navigation systems.
A. Ghita, Qiuyi Cao, Daniel Watzenig et al.· AHFE International· 0 citations
Safe operation of autonomous vehicles in dense urban traffic depends on perception and planning that remain reliable when onboard sensing is degraded. In real driving conditions, camera observations are frequently corrupted by occlusion, motion blur, illumination change, and sensor noise, and when such degraded observations are aggregated indiscriminately over time, trajectory planning becomes unstable and collision risk rises for both the ego vehicle and surrounding road users. Recent Bird's-Eye-View (BEV) approaches unify perception and planning through a shared spatial representation, but most fuse temporal information across frames without assessing the reliability of the underlying observations. We present a Reliable Context-Aware and Temporal Planning framework for Autonomous Driving (RCT-AD) that explicitly models feature quality and temporal consistency to support safer, more consistent planning. A Reliable Context Awareness module scores per-frame reliability and selectively retains trustworthy features through a quality-gated First-In-Last-Out (FILO) memory mechanism, reconstructing degraded observations from reliable historical context so that corrupted inputs do not destabilize the scene representation. A Temporal Trajectory Planner captures long-term dependencies and multi-agent interactions to produce smoother, safety-aware trajectories, while a joint detection-and-segmentation head injects semantic and motion cues into the shared BEV space to strengthen scene understanding. Experiments on the nuScenes autonomous driving benchmark show that RCT-AD improves perception accuracy, motion prediction, and planning robustness over recent end-to-end baselines, achieving 61.5 nuScenes Detection Score, 52.9 mean Average Precision, and 52.3 mean Intersection over Union, while maintaining competitive computational efficiency suitable for real-time deployment.
Argho Dey, Yunfei Yin, Swachha Ray et al.· 0 citations
Safe map-free multi-robot navigation requires robots to make real-time decisions from partial and noisy local observations in dynamic, unstructured environments. Existing approaches often depend on prior maps, computationally intensive perception pipelines, or carefully tuned interaction models, which limit their robustness on resource-constrained platforms. This paper proposes LSTP-Nav, a lightweight, decentralized navigation framework built on LSTP-Net that maps stacked 2D LiDAR observations, goal information, and velocity feedback directly to action. LSTP-Net combines GRU-based temporal modeling with attention to extract interaction-critical spatiotemporal cues at low computational cost. We further introduce an HS reward to provide smooth, heading-aware safety feedback, and develop PhysReplay-SimLab to improve training effectiveness through local replay of near-failure interactions. Extensive simulation and real-world experiments show that LSTP-Nav outperforms representative baselines, achieving 98.6%–100.0% success in single-robot settings and 97.8%–99.0% success in 10-robot settings with 5–35 obstacles. The policy also remains robust to LiDAR degradation, nonconvex layouts, random seeds, and large-scale density tests, while achieving over 40 Hz onboard inference on a Raspberry Pi 3 Model B with zero-shot sim-to-real transfer. Overall, LSTP-Nav provides a practical, deployable solution for real-time, map-free multi-agent navigation on computationally constrained mobile robots. Note to Practitioners—This study addresses a pressing practical need in large-scale site inspection and outdoor search-and-rescue: enabling mobile robots with limited onboard computation to navigate safely and efficiently in complex, previously unseen environments without relying on pre-built maps. In real deployments, robots must make decisions from partial and noisy sensor observations while interacting with moving objects (e.g., pedestrians or teammates), and conventional map-based pipelines or computationally heavy planners can become unreliable or infeasible. To tackle these constraints, we propose a lightweight spatiotemporal navigation policy that directly converts raw LiDAR observations into motion commands, combining temporal memory with attention to focus computation on interaction-critical cues. In addition, a heading-stability objective and a physics-based replay-assisted training workflow improve behavior smoothness and reduce failure cases such as oscillation, collisions, and getting trapped in cluttered areas. Extensive simulation and real-world tests show that the proposed approach improves navigation success and safety over representative baselines while maintaining real-time performance on CPU-only platforms, making it suitable for practical deployment on resource-constrained robots in dynamic, unstructured environments.
Xingrong Diao, Zhi-Qiang Sun, Jianwei Peng et al.· IEEE Transactions on Automat...· 0 citations
People with autism spectrum disorder (ASD) or dementia, young children, and visitors lost in crowded venues often need guidance back to a safe origin. Conventional map-based navigation serves this need poorly. We present a self-trained, map-free augmented-reality (AR) navigation system. It records a route as the user first walks it and later guides the user back with egocentric cues, with no pre-built map or installed infrastructure. Map-free means that the route is the user’s own recorded walk, not that the system avoids satellites. Two separate methods cover the two positioning regimes. Outdoors, where satellite fixes are corrupted by heavy multipath, we propose Confidence-Weighted Trajectory Reconstruction (CWTR), which scores each fix by reported accuracy, kinematic plausibility, and temporal spacing. A confidence-driven robust Kalman smoother then gates and down-weights outliers. In simulation, the proposed method reduces the reconstruction error by up to 78% over raw fixes and increasingly outperforms fixed-gain and adaptively gated robust Kalman baselines as multipath worsens. Recorded GPS shows that the gains are regime-dependent: under benign reception the method matches the simpler filters, while in a dense field campaign in Al-Madinah it flagged unusable traces instead of producing a fictitious route. Its main benefit is route stability—low trajectory jitter and hence stable AR cue placement—rather than better end-point accuracy. In indoor environments, where satellite reception fails, the deployed iPhone app uses only the camera and inertial sensors to record a route once and later guide the user along it with floor-registered cues. It reaches decimeter-level end-point accuracy without satellite positioning. A confidence-gated disorientation detector separates positioning-induced irregularities from behavior-induced irregularities. The evidence validates the reconstruction, detector, and deployed app on navigation data; human-subject evaluation with the motivating populations remains future work.
Mohammad Belayet Hossain, Omar Tayan· IEEE Access· 0 citations
Reliable navigation in GPS-denied environments remains a critical challenge for autonomous vehicles (AVs), particularly in complex indoor and urban settings. GPS-based localization systems often fail under these conditions, highlighting the need for resilient multimodal solutions. In this article, we present a radar-assisted tracking system that integrates LiDAR and inertial measurements within a sensor-fusion architecture to achieve robust navigation. The principal methodological contribution is a unified tracking and prediction framework that combines Bayesian state estimation with learning-based temporal prediction, enabling accurate tracking while continuously forecasting the slave robot’s short-term future state from mapping observations generated by the master robot, with a typical end-to-end perception-to-action latency of 20–60 ms. The communication and prediction forecasting module operates with an update interval below 35 ms, enabling real-time cooperative robotic operation. Sensor data are fused through a pipeline incorporating Gaussian Mixture Models (GMMs) for post-processing, which helps mitigate the limitations associated with individual sensors during edge processing. Moreover, Kalman filtering is employed to mitigate sensor noise and drift, thereby improving state estimation accuracy through trajectory smoothing. The fused spatiotemporal information is subsequently exploited by a Convolutional Recurrent Neural Network (CRNN) coupled with a Nonlinear Autoregressive model with eXogenous Inputs (NARX) to model the robot’s motion dynamics and provide short-horizon state prediction. Through simulations and real-world indoor experiments conducted in GPS-denied environments, we validate the system’s ability to provide accurate and continuous pose estimation with low localization errors. Experimental results show that the proposed framework achieves root-mean-square errors of 0.12 m, 0.15 m, and 0.28 m along the X, Y, and Z axes, respectively, while maintaining sub-meter maximum position deviations throughout the evaluated trajectories. These results confirm that the proposed framework provides reliable localization and predictive state estimation for cooperative robotic navigation in indoor GPS-denied environments. Future work will investigate outdoor validation and extend the framework to additional data-driven decision-making models for future robotic services.
Z. Ezzouine, Adil Salbi, Mohamed Abouzahir et al.· Entropy· 0 citations
Navigation is a critical challenge faced by people with visual impairment, often limiting their independence and safety in unfamiliar environments. This paper presents Aurora, a novel deep learning-based smartphone navigation assistant designed specifically to aid visually impaired users in real-time navigation and obstacle avoidance. Aurora leverages convolutional neural networks (CNNs) and recurrent neural networks (RNNs) to accurately interpret visual data captured through a smartphone camera, enabling robust scene understanding and path planning. The system integrates semantic segmentation to detect sidewalks, pedestrian crossings, obstacles, and signage, while simultaneously providing audio and haptic feedback to guide users safely and efficiently. In this study, we detail the architecture of Aurora, including the dataset preparation, model training, and optimization techniques applied to ensure real-time performance on mobile devices. The assistant also incorporates GPS data and inertial sensors to enhance localization accuracy and context awareness. Extensive experiments were conducted under various environmental conditions to validate the system’s effectiveness, achieving a high accuracy rate in obstacle detection and route guidance. Aurora’s user-centric design includes customizable feedback modes to cater to different user preferences and needs, ensuring accessibility and ease of use. This paper further discusses the usability evaluation involving visually impaired participants, highlighting improvements in navigation confidence and reduction in travel time. The results demonstrate that Aurora can significantly improve independent mobility for visually impaired individuals.
K. C, N. O, Shruthi et al.· International Journal of Res...· 0 citations