Jul 2026· IEEE transactions on intelligent transportation systems (Print)· Vol 27, pp. 7882-7892· 0 citations· 44 references
Computer Science
TL;DR
This work proposes a novel deep learning framework that leverages the powerful spatiotemporal information processing capabilities of Transformers and the strong multi-task learning abilities of Mixture of Experts to generate real-time, context-aware audio instructions for TBT driving navigation.
Abstract
Turn-by-turn (TBT) navigation systems are integral to modern driving experiences, providing real-time audio instructions to guide drivers safely to destinations. However, existing audio instruction policy often relies on rule-based approaches that struggle to balance informational content with cognitive load, potentially leading to driver confusion or missed turns in complex environments. To overcome these difficulties, we first model the generation of navigation instructions as a multi-task learning problem by decomposing the audio content into combinations of modular elements. Then, we propose a novel deep learning framework that leverages the powerful spatiotemporal information processing capabilities of Transformers and the strong multi-task learning abilities of Mixture of Experts (MoE) to generate real-time, context-aware audio instructions for TBT driving navigation. A cloud-edge collaborative architecture is implemented to handle the computational demands of the model, ensuring scalability and real-time performance for practical applications. Experimental results in the real world demonstrate that the proposed method significantly reduces the yaw rate (the proportion of vehicles deviating from navigation routes) compared to traditional methods, delivering clearer and more effective audio instructions. This is the first large-scale application of deep learning in driving audio navigation, marking a substantial advancement in intelligent transportation and driving assistance technologies.
Multitask perception has emerged as a critical technology for autonomous driving systems. Despite significant progress, current systems remain vulnerable to environmental variations, particularly challenging lighting conditions (e.g., low-light scenarios, sudden illumination changes) and adverse weather (e.g., rain, fo...
Chong-Jun Liu, Hao-Bo Zuo, Jia-Jing Yao et al.· Computers· 0 citations
The article comprehensively outlines the development trajectory of visual semantic perception technology for mobile vehicles, providing a systematic theoretical reference for the design and embedded deployment optimization of visual algorithms for mobile robots in warehousing and inspection tasks.
Jia-Wei Sun· Applied and Computational En...· 0 citations
SV-WAM is proposed, a surround-view world-action model (WAM) that preserves full six-camera observations while maintaining efficient inference and introduces a differentiable drivable-area compliance regularizer that penalizes vehicle-footprint corners approaching or crossing drivable boundaries, improving planning saf...
Jin-Yang Wang, Shi-Wei Li, Jun-Jian Wang et al.· 1 citation
Mapless deep reinforcement learning (DRL) navigation in dynamic indoor environments is difficult under single-frame 2D LiDAR, which reports where an obstacle is but not whether it is approaching. We introduce the Positional-Velocity Spatio-Temporal Attention Module (PV-STAM), a compact perception block (19,968 trainabl...
Anas Mahyoub Naji Saeed Alqadhi, Munef El Muhammed, M. A. M. S. Bajhaw et al.· Applied Sciences· 0 citations
Learning embodied urban navigation policies from real-world data is constrained by the cost of task-specific data collection and the limited coverage of rare yet safety-critical scenarios. To address these challenges, we present a scalable framework for learning point-goal urban navigation from web-scale in-the-wild eg...
Bingyi Xia, Han Bao, Zhe-Wei Chen et al.· 0 citations
Autonomous driving systems have become a central focus of intelligent transportation research, with End-to-End Learning and Modular Architectures offering two prominent design paradigms for their implementation. E2E Learning uses deep learning algorithms to map raw sensory inputs directly to driving actuators, providin...