Manabu Tsukada

Yun Li, Simon Thompson, Yidu Zhang et al.

Diffusion-based motion planners have achieved state-of-the-art results on benchmarks such as nuPlan, yet their evaluation within closed-loop production autonomous driving stacks remains largely unexplored. Existing evaluations abstract away ROS 2 communication latency and real-time scheduling constraints, while monolithic ONNX deployment freezes all solver parameters at export time. We present an open-source modular benchmark that addresses both gaps: using ONNX GraphSurgeon, we decompose a monolithic 18,398 node diffusion planner into three independently executable modules and reimplement the DPM-Solver++ denoising loop in native C++. Integrated as a ROS 2 node within Autoware, the open-source AD stack deployed on real vehicles worldwide, the system enables runtime-configurable solver parameters without model recompilation and per-step observability of the denoising process, breaking the black box of monolithic deployment. Unlike evaluations in standalone simulators such as CARLA, our benchmark operates within a production-grade stack and is validated through AWSIM closed-loop simulation. Through systematic comparison of DPM-Solver++ (first- and second-order) and DDIM across six step-count configurations (N in {3, 5, 7, 10, 15, 20}), we show that encoder caching yields a 3.2x latency reduction, and that second-order solving reduces FDE by 41% at N=3 compared to first-order. The complete codebase will be released as open-source, providing a direct path from simulation benchmarks to real-vehicle deployment.

Yun Li, Kai Katsumata, Ehsan Javanmardi et al.

Large Language Models (LLMs), AI models trained on massive text corpora with remarkable language understanding and generation capabilities, are transforming the field of Autonomous Driving (AD). As AD systems evolve from rule-based and optimization-based methods to learning-based techniques like deep reinforcement learning, they are now poised to embrace a third and more advanced category: knowledge-based AD empowered by LLMs. This shift promises to bring AD closer to human-like AD. However, integrating LLMs into AD systems poses challenges in real-time inference, safety assurance, and deployment costs. This survey provides a comprehensive and critical review of recent progress in leveraging LLMs for AD, focusing on their applications in modular AD pipelines and end-to-end AD systems. We highlight key advancements, identify pressing challenges, and propose promising research directions to bridge the gap between LLMs and AD, thereby facilitating the development of more human-like AD systems. The survey first introduces LLMs' key features and common training schemes, then delves into their applications in modular AD pipelines and end-to-end AD, respectively, followed by discussions on open challenges and future directions. Through this in-depth analysis, we aim to provide insights and inspiration for researchers and practitioners working at the intersection of AI and autonomous vehicles, ultimately contributing to safer, smarter, and more human-centric AD technologies.

Yuze Jiang, Ehsan Javanmardi, Manabu Tsukada et al.

Recent advancements in LiDAR technology have significantly lowered costs and improved both its precision and resolution, thereby solidifying its role as a critical component in autonomous vehicle localization. Using sophisticated 3D registration algorithms, LiDAR now facilitates vehicle localization with centimeter-level accuracy. However, these high-precision techniques often face reliability challenges in environments devoid of identifiable map features. To address this limitation, we propose a novel approach that utilizes road side units (RSU) with vehicle-to-infrastructure (V2I) communications to assist vehicle self-localization. By using RSUs as stationary reference points and processing real-time LiDAR data, our method enhances localization accuracy through a cooperative localization framework. By placing RSUs in critical areas, our proposed method can improve the reliability and precision of vehicle localization when the traditional vehicle self-localization technique falls short. Evaluation results in an end-to-end autonomous driving simulator AWSIM show that the proposed method can improve localization accuracy by up to 80% under vulnerable environments compared to traditional localization methods. Additionally, our method also demonstrates robust resistance to network delays and packet loss in heterogeneous network environments.

Yun Li, Yidu Zhang, Simon Thompson et al.

Vision-Language-Action (VLA) models for autonomous driving must integrate diverse textual inputs, including navigation commands, hazard warnings, and traffic state descriptions, yet current systems often present these as disconnected fragments, forcing the model to discover on its own which environmental constraints are relevant to the current maneuver. We introduce Causal Scene Narration (CSN), which restructures VLA text inputs through intent-constraint alignment, quantitative grounding, and structured separation, at inference time with zero GPU cost. We complement CSN with Simplex-based runtime safety supervision and training-time alignment via Plackett-Luce DPO with negative log-likelihood (NLL) regularization. A multi-town closed-loop CARLA evaluation shows that CSN improves Driving Score by +31.1% on original LMDrive and +24.5% on the preference-aligned variant. A controlled ablation reveals that causal structure accounts for 39.1% of this gain, with the remainder attributable to information content alone. A perception noise ablation confirms that CSN's benefit is robust to realistic sensing errors. Semantic safety supervision improves Infraction Score, while reactive Time-To-Collision monitoring degrades performance, demonstrating that intent-aware monitoring is needed for VLA systems.

Hanlin Wu, Pengfei Lin, Ehsan Javanmardi et al.

As autonomous driving moves toward full scene understanding, 3D semantic occupancy prediction has emerged as a crucial perception task, offering voxel-level semantics beyond traditional detection and segmentation paradigms. However, such a refined representation for scene understanding incurs prohibitive computation and memory overhead, posing a major barrier to practical real-time deployment. To address this, we propose SUG-Occ, an explicit Semantics and Uncertainty Guided Sparse Learning Enabled 3D Occupancy Prediction Framework, which exploits the inherent sparsity of 3D scenes to reduce redundant computation while maintaining geometric and semantic completeness. Specifically, we first utilize semantic and uncertainty priors to suppress projections from free space during view transformation while employing an explicit unsigned distance encoding to enhance geometric consistency, producing a structurally consistent sparse 3D representation. Secondly, we design an cascade sparse completion module via hyper cross sparse convolution and generative upsampling to enable efficiently coarse-to-fine reasoning. Finally, we devise an object contextual representation (OCR) based mask decoder that aggregates global semantic context from sparse features and refines voxel-wise predictions via lightweight query-context interactions, avoiding expensive attention operations over volumetric features. Extensive experiments on SemanticKITTI benchmark demonstrate that the proposed approach outperforms the baselines, achieving a 7.34/% improvement in accuracy and a 57.8\% gain in efficiency.

Changhe Liu, Ehsan Javanmardi, Naren Bao et al.

Ray tracing 3D Gaussian particles enables realistic effects such as depth of field, refractions, and flexible camera modeling for novel-view synthesis. However, existing methods trace Gaussians through proxy geometry, which requires constructing complex intermediate meshes and performing costly intersection tests. This limitation arises because Gaussian-based particles are not well suited as unified primitives for both ray tracing and rasterization. In this work, we propose a differentiable triangle-based ray tracing pipeline that directly treats triangles as rendering primitives without relying on any proxy geometry. Our results show that the proposed method achieves significantly higher rendering quality than existing ray tracing approaches while maintaining real-time rendering performance. Moreover, our pipeline can directly render triangles optimized by the rasterization-based method Triangle Splatting, thus unifying the primitives used in novel-view synthesis.

Seyed Amir Hosseini, Maryam Abdolali, Amirhosein Tavakkoli et al.

Preference-based reinforcement learning (PBRL) offers a promising alternative to explicit reward engineering by learning from pairwise trajectory comparisons. However, real-world preference data often comes from heterogeneous annotators with varying reliability; some accurate, some noisy, and some systematically adversarial. Existing PBRL methods either treat all feedback equally or attempt to filter out unreliable sources, but both approaches fail when faced with adversarial annotators who systematically provide incorrect preferences. We introduce TriTrust-PBRL (TTP), a unified framework that jointly learns a shared reward model and expert-specific trust parameters from multi-expert preference feedback. The key insight is that trust parameters naturally evolve during gradient-based optimization to be positive (trust), near zero (ignore), or negative (flip), enabling the model to automatically invert adversarial preferences and recover useful signal rather than merely discarding corrupted feedback. We provide theoretical analysis establishing identifiability guarantees and detailed gradient analysis that explains how expert separation emerges naturally during training without explicit supervision. Empirically, we evaluate TTP on four diverse domains spanning manipulation tasks (MetaWorld) and locomotion (DM Control) under various corruption scenarios. TTP achieves state-of-the-art robustness, maintaining near-oracle performance under adversarial corruption while standard PBRL methods fail catastrophically. Notably, TTP outperforms existing baselines by successfully learning from mixed expert pools containing both reliable and adversarial annotators, all while requiring no expert features beyond identification indices and integrating seamlessly with existing PBRL pipelines.

Xiaoyang He, Manabu Tsukada

Timely channel information is necessary for vehicles to determine both the serving base station (BS) and the beamforming vector, but frequent estimation of fast-fading mmWave channels incurs significant overhead. To address this challenge, we propose a Beam-aware Kernelized Contextual Upper Confidence Bound (BKC-UCB) algorithm that estimates instantaneous transmission rates without additional channel measurements by exploiting historical contexts such as vehicle location and velocity, together with past observed transmission rates. Specifically, BKC-UCB leverages kernel methods to capture the nonlinear relationship between context and transmission rate by mapping contexts into a reproducing kernel Hilbert space (RKHS), where linear learning becomes feasible. Rather than treating each beam as an independent arm, the beam index is embedded into the context, enabling BKC-UCB to exploit correlations among beams to accelerate convergence. Furthermore, an event-triggered information sharing mechanism is incorporated into BKC-UCB, enabling information exchange only when significant explorations are conducted to improve learning efficiency with limited communication overhead.

Mai Hirata, Manabu Tsukada, Keisuke Okumura et al.

Cooperative intelligent transportation systems (ITS) are used by autonomous vehicles to communicate with surrounding autonomous vehicles and roadside units (RSU). Current C-ITS applications focus primarily on real-time information sharing, such as cooperative perception. In addition to real-time information sharing, self-driving cars need to coordinate their action plans to achieve higher safety and efficiency. For this reason, this study defines a vehicle's future action plan/path and designs a cooperative path-planning model at intersections using future path sharing based on the future path information of multiple vehicles. The notion is that when the RSU detects a potential conflict of vehicle paths or an acceleration opportunity according to the shared future paths, it will generate a coordinated path update that adjusts the speeds of the vehicles. We implemented the proposed method using the open-source Autoware autonomous driving software and evaluated it with the LGSVL autonomous vehicle simulator. We conducted simulation experiments with two vehicles at a blind intersection scenario, finding that each car can travel safely and more efficiently by planning a path that reflects the action plans of all vehicles involved. The time consumed by introducing the RSU is 23.0 % and 28.1 % shorter than that of the stand-alone autonomous driving case at the intersection.

Masaya Mizutani, Manabu Tsukada, Hiroshi Esaki

A cooperative intelligent transport system (C-ITS) uses vehicle-to-everything (V2X) technology to make self-driving vehicles safer and more efficient. Current C-ITS applications have mainly focused on real-time information sharing, such as for cooperative perception. In addition to better real-time perception, self-driving vehicles need to achieve higher safety and efficiency by coordinating action plans. This study designs a maneuver coordination (MC) protocol that uses seven messages to cover various scenarios and an abstracted MC support service. We implement our proposal as AutoMCM by extending two open-source software tools: Autoware for autonomous driving and OpenC2X for C-ITS. The results show that our system effectively reduces the communication bandwidth by limiting message exchange in an event-driven manner. Furthermore, it shows that the vehicles run 15% faster when the vehicle speed is 30 km/h and 28% faster when the vehicle speed is 50 km/h using our scheme. Our system shows robustness against packet loss in experiments when the message timeout parameters are appropriately set.

Wencan Mao, Quanxi Zhou, Tomas Couso Coddou et al.

Unmanned aerial vehicles (UAVs) have emerged as a promising auxiliary platform for smart agriculture, capable of simultaneously performing weed detection, recognition, and data collection from wireless sensors. However, trajectory planning for UAV-based smart agriculture is challenging due to the high uncertainty of the environment, partial observations, and limited battery capacity of UAVs. To address these issues, we formulate the trajectory planning problem as a Markov decision process (MDP) and leverage multi-agent reinforcement learning (MARL) to solve it. Furthermore, we propose a novel imitation-based triple deep Q-network (ITDQN) algorithm, which employs an elite imitation mechanism to reduce exploration costs and utilizes a mediator Q-network over a double deep Q-network (DDQN) to accelerate and stabilize training and improve performance. Experimental results in both simulated and real-world environments demonstrate the effectiveness of our solution. Moreover, our proposed ITDQN outperforms DDQN by 4.43\% in weed recognition rate and 6.94\% in data collection rate.

Quanxi Zhou, Wencan Mao, Yilei Liang et al.

The widespread application of wireless communication technology has promoted the development of smart agriculture, where unmanned aerial vehicles (UAVs) play a multifunctional role. We target a multi-UAV smart agriculture system where UAVs cooperatively perform data collection, image acquisition, and communication tasks. In this context, we model a Markov decision process to solve the multi-UAV trajectory planning problem. Moreover, we propose a novel Elite Imitation Actor-Shared Ensemble Critic (EIA-SEC) framework, where agents adaptively learn from the elite agent to reduce trial-and-error costs, and a shared ensemble critic collaborates with each agent's local critic to ensure unbiased objective value estimates and prevent overestimation. Experimental results demonstrate that EIA-SEC outperforms state-of-the-art baselines in terms of reward performance, training stability, and convergence speed.

Quanxi Zhou, Wencan Mao, Manabu Tsukada et al.

Model-based reinforcement learning (MBRL) and model-free reinforcement learning (MFRL) evolve along distinct paths but converge in the design of Dyna-Q [1]. However, modern RL methods still struggle with effective transferability across tasks and scenarios. Motivated by this limitation, we propose a generalized algorithm, Feature Model-Based Enhanced Actor-Critic (FM-EAC), that integrates planning, acting, and learning for multi-task control in dynamic environments. FM-EAC combines the strengths of MBRL and MFRL and improves generalizability through the use of novel feature-based models and an enhanced actor-critic framework. Simulations in both urban and agricultural applications demonstrate that FM-EAC consistently outperforms many state-of-the-art MBRL and MFRL methods. More importantly, different sub-networks can be customized within FM-EAC according to user-specific requirements.

Wei Luo, Yiting Lu, Xin Li et al.

This paper reports on the LoViF 2026 PhyScore challenge, a competition on holistic quality assessment of world-model-generated videos across both 2D and 4D generation settings. The challenge is motivated by a central gap in current evaluation practice: perceptual quality alone is insufficient to judge whether generated dynamics are physically plausible, temporally coherent, and consistent with input conditions. Participants are required to build a metric that jointly predicts four dimensions, i.e., Video Quality, Physical Realism, Condition-Video Alignment, and Temporal Consistency. Depart from that, participants also need to localize physical anomaly timestamps for fine-grained diagnosis. The benchmark dataset contains 1,554 videos generated by seven representative world generative models, organized into three tracks (text-2D, image-to-4D, and video-to-4D) and spanning 26 categories. These categories explicitly cover physics-relevant scenarios, including dynamics, optics, and thermodynamics, together with diverse real-world and creative content. To ensure label reliability, scores and anomaly timestamps are produced through trained human annotation with an additional automated quality-control pass. Evaluation is based on both score prediction and anomaly localization, with a composite protocol that combines TimeStamp_IOU and SRCC/PLCC. This report summarizes the challenge design and provides method-level insights from submitted solutions.

Shuhong Liu, Chenyu Bao, Ziteng Cui et al.

This paper presents a comprehensive review of the NTIRE 2026 3D Restoration and Reconstruction (3DRR) Challenge, detailing the proposed methods and results. The challenge seeks to identify robust reconstruction pipelines that are robust under real-world adverse conditions, specifically extreme low-light and smoke-degraded environments, as captured by our RealX3D benchmark. A total of 279 participants registered for the competition, of whom 33 teams submitted valid results. We thoroughly evaluate the submitted approaches against state-of-the-art baselines, revealing significant progress in 3D reconstruction under adverse conditions. Our analysis highlights shared design principles among top-performing methods and provides insights into effective strategies for handling 3D scene degradation.

Hanlin Wu, Pengfei Lin, Ehsan Javanmardi et al.

3D semantic occupancy prediction is an emerging perception paradigm in autonomous driving, providing a voxel-level representation of both geometric details and semantic categories. However, the perception capability of a single vehicle is inherently constrained by occlusion, restricted sensor range, and narrow viewpoints. To address these limitations, collaborative perception enables the exchange of complementary information, thereby enhancing the completeness and accuracy. In the absence of a dedicated dataset for collaborative 3D semantic occupancy prediction, we augment an existing collaborative perception dataset by replaying it in CARLA with a high-resolution semantic voxel sensor to provide dense and comprehensive occupancy annotations. In addition, we establish benchmarks with varying prediction ranges designed to systematically assess the impact of spatial extent on collaborative prediction. We further develop a baseline model that performs inter-agent feature fusion via spatial alignment and attention aggregation. Experimental results demonstrate that our baseline model consistently outperforms single-agent models, with increasing gains observed as the prediction range expands.

Hao Si, Ehsan Javanmardi, Manabu Tsukada

Collaborative perception enables vehicles to overcome individual perception limitations by sharing information, allowing them to see further and through occlusions. In real-world scenarios, models on different vehicles are often heterogeneous due to manufacturer variations. Existing methods for heterogeneous collaborative perception address this challenge by fine-tuning adapters or the entire network to bridge the domain gap. However, these methods are impractical in real-world applications, as each new collaborator must undergo joint training with the ego vehicle on a dataset before inference, or the ego vehicle stores models for all potential collaborators in advance. Therefore, we pose a new question: Can we tackle this challenge directly during inference, eliminating the need for joint training? To answer this, we introduce Progressive Heterogeneous Collaborative Perception (PHCP), a novel framework that formulates the problem as few-shot unsupervised domain adaptation. Unlike previous work, PHCP dynamically aligns features by self-training an adapter during inference, eliminating the need for labeled data and joint training. Extensive experiments on the OPV2V dataset demonstrate that PHCP achieves strong performance across diverse heterogeneous scenarios. Notably, PHCP achieves performance comparable to SOTA methods trained on the entire dataset while using only a small amount of unlabeled data.

Mohammad Ali Rezaei, Fardin Ayar, Ehsan Javanmardi et al.

Accurate prediction of pedestrian trajectories is crucial for enhancing the safety of autonomous vehicles and reducing traffic fatalities involving pedestrians. While numerous studies have focused on modeling interactions among pedestrians to forecast their movements, the influence of environmental factors and scene-object placements has been comparatively underexplored. In this paper, we present a novel trajectory prediction model that integrates both pedestrian interactions and environmental context to improve prediction accuracy. Our approach captures spatial and temporal interactions among pedestrians within a sparse graph framework. To account for pedestrian-scene interactions, we employ advanced image enhancement and semantic segmentation techniques to extract detailed scene features. These scene and interaction features are then fused through a cross-attention mechanism, enabling the model to prioritize relevant environmental factors that influence pedestrian movements. Finally, a temporal convolutional network processes the fused features to predict future pedestrian trajectories. Experimental results demonstrate that our method significantly outperforms existing state-of-the-art approaches, achieving ADE and FDE values of 0.252 and 0.372 meters, respectively, underscoring the importance of incorporating both social interactions and environmental context in pedestrian trajectory prediction.

Minoo Dolatabadi, Fardin Ayar, Ehsan Javanmardi et al.

LiDAR-based localization and SLAM often rely on iterative matching algorithms, particularly the Iterative Closest Point (ICP) algorithm, to align sensor data with pre-existing maps or previous scans. However, ICP is prone to errors in featureless environments and dynamic scenes, leading to inaccurate pose estimation. Accurately predicting the uncertainty associated with ICP is crucial for robust state estimation but remains challenging, as existing approaches often rely on handcrafted models or simplified assumptions. Moreover, a few deep learning-based methods for localizability estimation either depend on a pre-built map, which may not always be available, or provide a binary classification of localizable versus non-localizable, which fails to properly model uncertainty. In this work, we propose a data-driven framework that leverages deep learning to estimate the registration error covariance of ICP before matching, even in the absence of a reference map. By associating each LiDAR scan with a reliable 6-DoF error covariance estimate, our method enables seamless integration of ICP within Kalman filtering, enhancing localization accuracy and robustness. Extensive experiments on the KITTI dataset demonstrate the effectiveness of our approach, showing that it accurately predicts covariance and, when applied to localization using a pre-built map or SLAM, reduces localization errors and improves robustness.

Soroush Mahdi, Fardin Ayar, Ehsan Javanmardi et al.

Streaming visual transformers like StreamVGGT achieve strong 3D perception but suffer from unbounded growth of key value (KV) memory, which limits scalability. We propose a training-free, inference-time token eviction policy that bounds memory by discarding redundant tokens while keeping the most informative ones. Our method uses significantly less memory with little to no drop in accuracy: on 7-Scenes with long sequences it reduces peak memory from 18.63 GB to 9.39 GB while accuracy and completeness drop by only 0.003. Under strict memory budgets, eviction enables denser frame sampling, which improves reconstruction accuracy compared to the baseline. Experiments across video depth estimation (Sintel, KITTI), 3D reconstruction (7-Scenes, NRGBD), and camera pose estimation (Sintel, TUM-dynamics) show that our approach closely matches StreamVGGT at a fraction of the memory and makes long-horizon streaming inference more practical.

Minoo Dolatabadi, Fardin Ayar, Ehsan Javanmardi et al.

Autonomous vehicles have gained significant attention due to technological advancements and their potential to transform transportation. A critical challenge in this domain is precise localization, particularly in LiDAR-based map matching, which is prone to errors due to degeneracy in the data. Most sensor fusion techniques, such as the Kalman filter, rely on accurate error covariance estimates for each sensor to improve localization accuracy. However, obtaining reliable covariance values for map matching remains a complex task. To address this challenge, we propose a neural network-based framework for predicting localization error covariance in LiDAR map matching. To achieve this, we introduce a novel dataset generation method specifically designed for error covariance estimation. In our evaluation using a Kalman filter, we achieved a 2 cm improvement in localization accuracy, a significant enhancement in this domain.

Fardin Ayar, Ehsan Javanmardi, Manabu Tsukada et al.

Panoptic segmentation, which combines instance and semantic segmentation, has gained a lot of attention in autonomous vehicles, due to its comprehensive representation of the scene. This task can be applied for cameras and LiDAR sensors, but there has been a limited focus on combining both sensors to enhance image panoptic segmentation (PS). Although previous research has acknowledged the benefit of 3D data on camera-based scene perception, no specific study has explored the influence of 3D data on image and video panoptic segmentation (VPS).This work seeks to introduce a feature fusion module that enhances PS and VPS by fusing LiDAR and image data for autonomous vehicles. We also illustrate that, in addition to this fusion, our proposed model, which utilizes two simple modifications, can further deliver even more high-quality VPS without being trained on video data. The results demonstrate a substantial improvement in both the image and video panoptic segmentation evaluation metrics by up to 5 points.

Manabu Tsukada, Shimpei Arii, Hideya Ochiai et al.

In cooperative ITS, security and privacy protection are essential. Cooperative Awareness Message (CAM) is a basic V2V message standard, and misbehavior detection is critical for protection against attacking CAMs from the inside system, in addition to node authentication by Public Key Infrastructure (PKI). On the contrary, pseudonym IDs, which have been introduced to protect privacy from tracking, make it challenging to perform misbehavior detection. In this study, we improve the performance of misbehavior detection using observation data of other vehicles. This is referred to as collective perception message (CPM), which is becoming the new standard in European countries. We have experimented using realistic traffic scenarios and succeeded in reducing the rate of rejecting valid CAMs (false positive) by approximately 15 percentage points while maintaining the rate of correctly detecting attacks (true positive).

Yichuan Chen, Manabu Tsukada, Hiroshi Esaki

Exploring the most task-friendly camera setting -- optimal camera placement (OCP) problem -- in tasks that use multiple cameras is of great importance. However, few existing OCP solutions specialize in depth observation of indoor scenes, and most versatile solutions work offline. To this problem, an OCP online solution to depth observation of indoor scenes based on reinforcement learning is proposed in this paper. The proposed solution comprises a simulation environment that implements scene observation and reward estimation using shadow maps and an agent network containing a soft actor-critic (SAC)-based reinforcement learning backbone and a feature extractor to extract features from the observed point cloud layer-by-layer. Comparative experiments with two state-of-the-art optimization-based offline methods are conducted. The experimental results indicate that the proposed system outperforms seven out of ten test scenes in obtaining lower depth observation error. The total error in all test scenes is also less than 90% of the baseline ones. Therefore, the proposed system is more competent for depth camera placement in scenarios where there is no prior knowledge of the scenes or where a lower depth observation error is the main objective.

Manabu Tsukada, Keiko Ogawa, Masahiro Ikeda et al.

Internet-native audio-visual services are witnessing rapid development. Among these services, object-based audio-visual services are gaining importance. In 2014, we established the Software Defined Media (SDM) consortium to target new research areas and markets involving object-based digital media and Internet-by-design audio-visual environments. In this paper, we introduce the SDM architecture that virtualizes networked audio-visual services along with the development of smart buildings and smart cities using Internet of Things (IoT) devices and smart building facilities. Moreover, we design the SDM architecture as a layered architecture to promote the development of innovative applications on the basis of rapid advancements in software-defined networking (SDN). Then, we implement a prototype system based on the architecture, present the system at an exhibition, and provide it as an SDM API to application developers at hackathons. Various types of applications are developed using the API at these events. An evaluation of SDM API access shows that the prototype SDM platform effectively provides 3D audio reproducibility and interactiveness for SDM applications.