Complex Real-world Environments Research Articles

MT-RSL: A multitasking-oriented robot skill learning framework based on continuous dynamic movement primitives for improving efficiency and quality in robot-based intelligent operation

Robot skill learning is one of the international advanced directions in the field of robot-based intelligent manufacturing, which makes it possible for robots to learn and operate autonomously in complex real-world environments. In this paper, we propose a multitasking-oriented robot skill learning framework named MT-RSL to improve the efficiency and robustness of multi-task robot skill learning in complex real-world environments, and present the detailed design steps of three key sub-modules included in MT-RSL, namely, sub-task segmentation module, robot skill learning module, and robot configuration optimization module. Firstly, we design a novel sub-task segmentation module based on a coarse-to-fine sub-task segmentation (CF-STS) strategy, in which the Finite State Machine (FSM) is used to analyze complex robot behaviors to obtain a coarse robot sub-task sequence, and the Beta Process Autoregressive Hidden Markov Model (BP-AR-HMM) is used to establish the connection and dependence between multiple demonstration trajectories and encode these trajectories, so as to obtain a finer robot action sequence. Secondly, we extend the basic DMPs system to a continuous dynamic movement primitives (CDMPs) system to construct a novel robot skill learning module, which improves the efficiency of the robot to learn skills and perform actions by orderly coordinating sub-parts such as the activation signals, motion actuator, DMPs-based learning module, and robot configuration optimization module. Then, we design a novel robot configuration optimization module, which introduces the velocity directional manipulability measure (VDM) as the evaluation index of robot kinematic performance to establish the robot configuration optimization model, and proposes an improved probabilistic adaptive particle swarm optimization (Pro-APSO) algorithm to solve this optimization model, so as to obtain the optimal robot configuration. Finally, we develop an experimental testing platform based on the Robot Operating System (ROS) and conduct a series of prototype experiments in complex real-world scenarios. The experimental results demonstrate that our proposed MT-RSL can significantly improve the effectiveness and robustness of multi-task robot skill learning, and can outperform existing robot skill learning methods in terms of both learning efficiency, VDM, and success rate.

A MXene Hydrogel-Based Versatile Microrobot for Controllable Water Pollution Management.

The urgent demand for addressing dye contaminants in water necessitates the development of microrobots that exhibit remote navigation, rapid removal, and molecular identification capabilities. The progress of microrobot development is currently hindered by the scarcity of multifunctional materials. In this study, a plasmonic MXene hydrogel (PM-Gel) is synthesized by combining bimetallic nanocubes and Ti3C2Tx MXene through the rapid gelation of degradable alginate. The hydrogel can efficiently adsorb over 60% of dye contaminants within 2 min, ultimately achieving a removal rate of >90%. Meanwhile, the hydrogel exhibits excellent sensitivity in surface enhanced Raman scattering (SERS) detection, with a limit of detection (LOD) as low as 3.76 am. The properties of the plasmonic hydrogel can be further adjusted for various applications. As a proof-of-concept experiment, thermosensitive polymers and superparamagnetic particles are successfully integrated into this hydrogel to construct a versatile, light-responsive microrobot for dye contaminants. With magnetic and optical actuation, the robot can remotely sample, identify, and remove pollutants in maze-like channels. Moreover, light-driven hydrophilic-hydrophobic switch of the microrobots through photothermal effect can further enhance the adsorption capacity and reduced the dye residue by up to 58%. These findings indicate of a broad application potential in complex real-world environments.

Actively learning costly reward functions for reinforcement learning

Transfer of recent advances in deep reinforcement learning to real-world applications is hindered by high data demands and thus low efficiency and scalability. Through independent improvements of components such as replay buffers or more stable learning algorithms, and through massively distributed systems, training time could be reduced from several days to several hours for standard benchmark tasks. However, while rewards in simulated environments are well-defined and easy to compute, reward evaluation becomes the bottleneck in many real-world environments, e.g. in molecular optimization tasks, where computationally demanding simulations or even experiments are required to evaluate states and to quantify rewards. When ground-truth evaluations become orders of magnitude more expensive than in research scenarios, direct transfer of recent advances would require massive amounts of scale, just for evaluating rewards rather than training the models. We propose to alleviate this problem by replacing costly ground-truth rewards with rewards modeled by neural networks, counteracting non-stationarity of state and reward distributions during training with an active learning component. We demonstrate that using our proposed method, it is possible to train agents in complex real-world environments orders of magnitudes faster than would be possible when using ground-truth rewards. By enabling the application of RL methods to new domains, we show that we can find interesting and non-trivial solutions to real-world optimization problems in chemistry, materials science and engineering. We demonstrate speed-up factors of 50–3000 when applying our approach to challenges of molecular design and airfoil optimization.

Utilizing Deep Reinforcement Learning, EGO-Swarm Parameter Control determines the path of the drone

The recent attention garnered by the EGO-Swarm system is due to its successful generation of smooth drone flight paths in complex real-world environments. Among the various parameter values utilized by EGO-Swarm for path generation, the maximum speed and maximum acceleration of the drone play a critical role in enhancing flight performance. However, in the current EGO-Swarm setup, these parameter values remain fixed during path creation, despite the potential need for real-time adjustments in dynamic environments. Therefore, there is a need to dynamically adapt these values to the evolving real-time environment. This paper proposes a novel algorithm that dynamically adjusts the maximum speed and maximum acceleration using hierarchical deep reinforcement learning in response to real-time environmental changes. To assess the effectiveness of the proposed method, a comparative experiment is conducted between the existing EGO-Swarm algorithm and the proposed algorithm in a ROS simulation. The experimental results reveal that the proposed algorithm surpasses the existing EGO-Swarm algorithm in terms of average speed improvement and path length.(Zhou et al., 2021)

Fully convolutional video prediction network for complex scenarios

<p>Traditional predictive models, often used in simpler settings, face issues like high latency and computational demands, especially in complex real-world environments. Recent progress in deep learning has advanced spatiotemporal prediction research, yet challenges persist in general scenarios: (ⅰ) Latency and computational load of models; (ⅱ) dynamic nature of real-world environments; (ⅲ) complex motion and monitoring scenes. To overcome these challenges, we introduced a novel spatiotemporal prediction framework. It replaced high-latency recurrent models with fully convolutional ones, improving inference speed. Furthermore, it addressed the dynamic nature of environments with multilevel frequency domain encoders and decoders, facilitating spatial and temporal learning. For complex monitoring scenarios, a large receptive field token mixer spatial-frequency attention units (SAU) and time attention units (TAU) ensured temporal and spatial continuity. This framework outperformed current methods in accuracy and speed on public datasets, showing promising practical applications beyond electricity monitoring.</p>

OoD-Control: Generalizing Control in Unseen Environments.

Generalizing out-of-distribution (OoD) is critical but challenging in real applications such as unmanned aerial vehicle (UAV) flight control. Previous machine learning-based control has shown promise in dealing with complex real-world environments but suffers huge performance degradation facing OoD scenarios, posing risks to the stability and safety of UAVs. In this paper, we found that the introduced random noises during training surprisingly yield theoretically guaranteed performances via a proposed functional optimization framework. More encouragingly, this framework does not involve common Lyapunov assumptions used in this field, making it more widely applicable. With this framework, the upperbound for control error is induced. We also proved that the induced random noises can lead to lower OoD control errors. Based on our theoretical analysis, we further propose OoD-Control to generalize control in unseen environments. Numerical experiments demonstrate the superiority of the proposed algorithm, surpassing previous state-of-the-art by 65% under challenging unseen environments. We further extend to outdoor real-world experiments and found that the control error is reduced by 50% approximately.

Robust Shape Fitting for 3D Scene Abstraction.

Humans perceive and construct the world as an arrangement of simple parametric models. In particular, we can often describe man-made environments using volumetric primitives such as cuboids or cylinders. Inferring these primitives is important for attaining high-level, abstract scene descriptions. Previous approaches for primitive-based abstraction estimate shape parameters directly and are only able to reproduce simple objects. In contrast, we propose a robust estimator for primitive fitting, which meaningfully abstracts complex real-world environments using cuboids. A RANSAC estimator guided by a neural network fits these primitives to a depth map. We condition the network on previously detected parts of the scene, parsing it one-by-one. To obtain cuboids from single RGB images, we additionally optimise a depth estimation CNN end-to-end. Naively minimising point-to-primitive distances leads to large or spurious cuboids occluding parts of the scene. We thus propose an improved occlusion-aware distance metric correctly handling opaque scenes. Furthermore, we present a neural network based cuboid solver which provides more parsimonious scene abstractions while also reducing inference time. The proposed algorithm does not require labour-intensive labels, such as cuboid annotations, for training. Results on the NYU Depth v2 dataset demonstrate that the proposed algorithm successfully abstracts cluttered real-world 3D scene layouts.

트랜스포머 기반의 다중 시점 3차원 인체자세추정

The technology of Three-dimensional human posture estimation is used in sports, motion recognition, and special effects of video media. Among various methods for this, multi-view 3D human pose estimation is essential for precise estimation even in complex real-world environments. But Existing models for multi-view 3D human posture estimation have the disadvantage of high order of time complexity as they use 3D feature maps. This paper proposes a method to extend an existing monocular viewpoint multi-frame model based on Transformer with lower time complexity to 3D human posture estimation for multi-viewpoints. To expand to multi-viewpoints our proposed method first generates an 8-dimensional joint coordinate that connects 2-dimensional joint coordinates for 17 joints at 4-vieiwpoints acquired using the 2-dimensional human posture detector, CPN(Cascaded Pyramid Network). This paper then converts them into 17×32 data with patch embedding, and enters the data into a transformer model, finally. Consequently, the MLP(Multi-Layer Perceptron) block that outputs the 3D-human posture simultaneously updates the 3D human posture estimation for 4-viewpoints at every iteration. Compared to Zheng[5]'s method the number of model parameters of the proposed method was 48.9%, MPJPE(Mean Per Joint Position Error) was reduced by 20.6 mm (43.8%) and the average learning time per epoch was more than 20 times faster.

AdaStreamLite

Streaming speech recognition aims to transcribe speech to text in a streaming manner, providing real-time speech interaction for smartphone users. However, it is not trivial to develop a high-performance streaming speech recognition system purely running on mobile platforms, due to the complex real-world acoustic environments and the limited computational resources of smartphones. Most existing solutions lack the generalization to unseen environments and have difficulty to work with streaming speech. In this paper, we design AdaStreamLite, an environment-adaptive streaming speech recognition tool for smartphones. AdaStreamLite interacts with its surroundings to capture the characteristics of the current acoustic environment to improve the robustness against ambient noise in a lightweight manner. We design an environment representation extractor to model acoustic environments with compact feature vectors, and construct a representation lookup table to improve the generalization of AdaStreamLite to unseen environments. We train our system using large speech datasets publicly available covering different languages. We conduct experiments in a large range of real acoustic environments with different smartphones. The results show that AdaStreamLite outperforms the state-of-the-art methods in terms of recognition accuracy, computational resource consumption and robustness against unseen environments.

CNTs/PVA Composite Aerogel for Efficient Microwave and Acoustic Absorption

The lightweight three-dimensional (3D) carbon nanotubes (CNTs) aerogel has garnered significant interest due to their exceptional characteristics, including high porosity, large specific surface area, and a 3D conductive network. These characteristics make it as a promising candidate for various applications in microwave absorption. However, to construct a multifunctional framework, that can swiftly adapt to complex real-world environments, remains a large challenge. In this study, we fabricated a multifunctional CNTs/polyvinyl alcohol composite aerogel (CPA). Integrating polyvinyl alcohol (PVA) into CNTs aerogel could effectively prevent CNTs aggregation, thus obtaining the remarkable electromagnetic absorption, acoustic, mechanical, and thermal properties. The minimum reflection loss (RL) of CPA achieved an outstanding value of -39.77 dB, measured with a thickness of 2 mm. In addition, CPA showed excellent sound absorption performance, with the highest sound absorption coefficient (SAC) of 0.981. Sound transmission loss (STL) could be improved by adjusting the ratio of CPA, the improvement of STL was 5-8 dB at the mid-high frequencies. Finally, CPA also exhibited excellent thermal insulation performance with the lowest thermal conductivity of 0.0297 W/m·k. The multifunctional capabilities of CPA position it as a highly promising material for various applications, such as microwave absorption, noise reduction, and heat preservation.

RealTHASC—a cyber-physical XR testbed for AI-supported real-time human autonomous systems collaborations

Today’s research on human-robot teaming requires the ability to test artificial intelligence (AI) algorithms for perception and decision-making in complex real-world environments. Field experiments, also referred to as experiments “in the wild,” do not provide the level of detailed ground truth necessary for thorough performance comparisons and validation. Experiments on pre-recorded real-world data sets are also significantly limited in their usefulness because they do not allow researchers to test the effectiveness of active robot perception and control or decision strategies in the loop. Additionally, research on large human-robot teams requires tests and experiments that are too costly even for the industry and may result in considerable time losses when experiments go awry. The novel Real-Time Human Autonomous Systems Collaborations (RealTHASC) facility at Cornell University interfaces real and virtual robots and humans with photorealistic simulated environments by implementing new concepts for the seamless integration of wearable sensors, motion capture, physics-based simulations, robot hardware and virtual reality (VR). The result is an extended reality (XR) testbed by which real robots and humans in the laboratory are able to experience virtual worlds, inclusive of virtual agents, through real-time visual feedback and interaction. VR body tracking by DeepMotion is employed in conjunction with the OptiTrack motion capture system to transfer every human subject and robot in the real physical laboratory space into a synthetic virtual environment, thereby constructing corresponding human/robot avatars that not only mimic the behaviors of the real agents but also experience the virtual world through virtual sensors and transmit the sensor data back to the real human/robot agent, all in real time. New cross-domain synthetic environments are created in RealTHASC using Unreal Engine™, bridging the simulation-to-reality gap and allowing for the inclusion of underwater/ground/aerial autonomous vehicles, each equipped with a multi-modal sensor suite. The experimental capabilities offered by RealTHASC are demonstrated through three case studies showcasing mixed real/virtual human/robot interactions in diverse domains, leveraging and complementing the benefits of experimentation in simulation and in the real world.

Robust Epileptic Seizure Detection Using Long Short-Term Memory and Feature Fusion of Compressed Time–Frequency EEG Images

Epilepsy is a prevalent neurological disorder with considerable risks, including physical impairment and irreversible brain damage from seizures. Given these challenges, the urgency for prompt and accurate seizure detection cannot be overstated. Traditionally, experts have relied on manual EEG signal analyses for seizure detection, which is labor-intensive and prone to human error. Recognizing this limitation, the rise in deep learning methods has been heralded as a promising avenue, offering more refined diagnostic precision. On the other hand, the prevailing challenge in many models is their constrained emphasis on specific domains, potentially diminishing their robustness and precision in complex real-world environments. This paper presents a novel model that seamlessly integrates the salient features from the time–frequency domain along with pivotal statistical attributes derived from EEG signals. This fusion process involves the integration of essential statistics, including the mean, median, and variance, combined with the rich data from compressed time–frequency (CWT) images processed using autoencoders. This multidimensional feature set provides a robust foundation for subsequent analytic steps. A long short-term memory (LSTM) network, meticulously optimized for the renowned Bonn Epilepsy dataset, was used to enhance the capability of the proposed model. Preliminary evaluations underscore the prowess of the proposed model: a remarkable 100% accuracy in most of the binary classifications, exceeding 95% accuracy in three-class and four-class challenges, and a commendable rate, exceeding 93.5% for the five-class classification.

Decoding Eye Blink and Related EEG Activity in Realistic Working Environments.

Accurately evaluating cognitive load during work-related tasks in complex real-world environments is challenging, leading researchers to investigate the use of eye blinking as a fundamental pacing mechanism for segmenting EEG data and understanding the neural mechanisms associated with cognitive workload. Yet, little is known about the temporal dynamics of eye blinks and related visual processing in relation to the representation of task-specific information. Therefore, we analyzed EEG responses from two experiments involving simulated driving (re-active and pro-active) with three levels of task load for each, as well as operating a steam engine (active vs. passive), to decode the temporal dynamics of eye blink activity and the subsequent neural activity that follows blinking. As a result, we successfully decoded the binary representation of difficulty levels for pro-active driving using multivariate pattern analysis. However, the decoding level varied for different re-active driving conditions, which could be attributed to the required level of alertness. Furthermore, our study revealed that it was possible to decode both driving types as well as steam engine operating conditions, with the most significant decoding activity observed approximately 200 ms after a blink. Additionally, our findings suggest that eye blinks have considerable potential for decoding various cognitive states that may not be discernible through neural activity, particularly near the peak of the blink. The findings demonstrate the potential of blink-related measures alongside EEG data to decode cognitive states during complex tasks, with implications for improving evaluations of cognitive and behavioral states during tasks, such as driving and operating machinery.

Pest recognition based on multi-image feature localization and adaptive filtering fusion.

Accurate recognition of pest categories is crucial for effective pest control. Due to issues such as the large variation in pest appearance, low data quality, and complex real-world environments, pest recognition poses challenges in practical applications. At present, many models have made great efforts on the real scene dataset IP102, but the highest recognition accuracy is only 75%. To improve pest recognition in practice, this paper proposes a multi-image fusion recognition method. Considering that farmers have easy access to data, the method performs fusion recognition on multiple images of the same pest instead of the conventional single image. Specifically, the method first uses convolutional neural network (CNN) to extract feature maps from these images. Then, an effective feature localization module (EFLM) captures the feature maps outputted by all blocks of the last convolutional stage of the CNN, marks the regions with large activation values as pest locations, and then integrates and crops them to obtain the localized features. Next, the adaptive filtering fusion module (AFFM) learns gate masks and selection masks for these features to eliminate interference from useless information, and uses the attention mechanism to select beneficial features for fusion. Finally, the classifier categorizes the fused features and the soft voting (SV) module integrates these results to obtain the final pest category. The principle of the model is activation value localization, feature filtering and fusion, and voting integration. The experimental results indicate that the proposed method can train high-performance feature extractors and classifiers, achieving recognition accuracy of 73.9%, 99.8%, and 99.7% on IP102, D0, and ETP, respectively, surpassing most single models. The results also show that thanks to the positive role of each module, the accuracy of multi-image fusion recognition reaches the state-of-the-art level of 96.1%, 100%, and 100% on IP102, D0, and ETP using 5, 2, and 2 images, respectively, which meets the requirements of practical applications. Additionally, we have developed a web application that applies our research findings in practice to assist farmers in reliable pest identification and drive the advancement of smart agriculture.

SCD: A Detection System for DDoS Attacks based on SAE-CNN Networks

The pervasive application of network technology has given rise to a numerous of network attacks, including Distributed Denial of Service (DDoS) attacks. DDoS attacks can lead to the collapse of network resources, making the target server unable to support legitimate users, which is a critical issue in cyberspace security. In complex real-world network environments, differentiating DDoS attack traffic from normal traffic is a challenging task, making it significant to effectively distinguish between attack types in order to resist DDoS attacks. However, traditional DDoS attack detection methods have certain limitations in terms of data preprocessing and detection efficiency. In this paper, we propose a lightweight framework based on deep learning called SAE-CNN-Detection (SCD), which combines stacked autoencoder network (SAE) and convolutional neural network (CNN) for DDoS attacks detection. The CIC-DDoS2019 dataset is used to simulate network traffic that has suffered from DDoS attacks, and this system employs adaptive preprocessing techniques for the dataset. The results demonstrate that multi-classification experiment achieves an accuracy of 97.2% for DDoS attack types, while the binary classification experiment achieves an accuracy of 99.1%.

Biomineralization-Inspired Copper Sulfide Decorated Aramid Textiles via In Situ Anchoring toward Versatile Wearable Thermal Management.

Designing smart textiles for personal thermal management (PTM) is an effective strategy for thermoregulation and energy saving. However, the manufacture of versatile high-performance thermal management textiles for complex real-world environments remains a challenge due to the limitations of functional integration, material properties, and preparation procedures. In this study, an aramid fabric based on in situ anchored copper sulfide nanostructure is developed. The textile with excellent solar and Joule heating properties can effectively keep the body warm even at low energy inputs. Meanwhile, the reduced infrared emissivity of the textile decreases the thermal radiation losses and helps to maintain a constant body temperature. Impressively, the textile integrates superb electromagnetic shielding, near-complete UV protection properties, and ideal resistance to fire and bacteria. This work provides a simple strategy for fabricating multi-functional integrated wearable devices with flexibility and breathability, which is highly promising in versatile PTM applications.

Lagrange programming neural network for robust passive elliptic positioning

This contribution studies passive elliptic positioning (PEP) with unknown transmitter locations, a localization technique having great potential applicability ranging from underwater wireless sensor networks to intelligent transportation systems. Specifically, we aim to address the challenge of employing PEP in complex real-world environments where outliers may exist, by using the concept of robust statistics. To achieve such a goal, we replace the ℓ2 loss in the traditional nonlinear least squares formulation by a differentiable cost function that possesses outlier-resistance. The neurodynamic approach of Lagrange programming neural network is then adopted to solve the resultant nonconvex statistically robustified PEP problem in a computationally efficient manner. Simulations and acoustic positioning experiments demonstrate the performance superiority of our proposal over its competitors.

Interframe Saliency Transformer and Lightweight Multidimensional Attention Network for Real-Time Unmanned Aerial Vehicle Tracking

UAV visual-object-tracking technology based on Siamese neural networks has great scientific research and practical application value, and it is widely used in geological surveying, reconnaissance monitoring, and environmental monitoring. Due to the limited onboard computational resources and complex real-world environments of drones, most of the existing tracking systems based on Siamese neural networks struggle to combine excellent performance with high efficiency. Therefore, the key issue is to study how to improve the accuracy of target tracking under the challenges of real-time performance and the above factors. In response to this problem, this paper proposes a real-time UAV tracking system based on interframe saliency transformer and lightweight multidimensional attention network (SiamITL). Specifically, interframe saliency transformer is used to continuously perceive spatial and temporal information, making the network more closely related to the essence of the tracking task. Additionally, a lightweight multidimensional attention network is used to better capture changes in both target appearance and background information, improving the ability of the tracker to distinguish between the target and background. SiamITL is effective and efficient: extensive comparative experiments and ablation experiments have been conducted on multiple aerial tracking benchmarks, demonstrating that our algorithm can achieve more robust feature representation and more accurate target state estimation. Among them, SiamITL achieved success and accuracy rates of 0.625 and 0.818 in the UAV123 benchmark, respectively, demonstrating a certain level of leadership in this field. Furthermore, SiamITL demonstrates the potential for real-time operation on the embedded platform Xavier, highlighting its potential for practical application in real-world scenarios.

Pseudo-Mono for Monocular 3D Object Detection in Autonomous Driving

Current monocular 3D object detection algorithms generally suffer from inaccurate depth estimation, which leads to reduction of detection accuracy. The depth error from image-to-image generation for the stereo view is insignificant compared with the gap in single-image generation. Therefore, a novel pseudo-monocular 3D object detection framework is proposed, which is called Pseudo-Mono. Particularly, stereo images are brought into monocular 3D detection. Firstly, stereo images are taken as input, then a lightweight depth predictor is used to generate the depth map of input images. Secondly, the left input images obtained from stereo camera are used as subjects, which generate enhanced visual feature and multi-scale depth feature by depth indexing and feature matching probabilities, respectively. Finally, sparse anchors set by the foreground probability maps and the multi-scale feature maps are used as reference points to find the suitable initialization approach of object query. The encoded visual feature is adopted to enhance object query for enabling deep interaction between visual feature and depth feature. Compared with popular monocular 3D object detection methods, Pseudo-Mono is able to achieve richer fine-grained information without additional data input. Extensive experimental results on the datasets of KITTI, NuScenes, and MS-COCO demonstrate the generalizability and portability of the proposed method. The effectiveness and efficiency of Pseudo-Mono have been demonstrated by extensive ablation experiments. Experiments on a real vehicle platform have shown that the proposed method maintains high performance in complex real-world environments.

Technical Concept for sensor-based Traffic Flow Optimization on connected real-world intersections via a SUMO Feature Gap Analysis

Traffic within cities has increased in the last decades due to increasing mobility, changing mobility behavior and new mobility offerings. These accelerating changes make it increasingly difficult for responsible authorities or other stakeholders to predict mobility behavior, to configure traffic rules or to size roads, bridges and parking lots. Traffic simulations are a powerful tool for estimating and evaluating current and future mobility, upcoming traffic services and automated functionalities in the domain of traffic management. For being able to simulate a complex real-world traffic environment and traffic incidents, the simulation environment needs to fulfill requirements from real-world scenarios related to sensor-based data processing. In addition, it must be possible to include latest advancements of technology in the simulation environment, for instance, (1) connected intersections that communicate with each other, (2) a complex and flexible set of rules for traffic sign control and traffic management or a well-defined data processing of relevant sensor data. In this paper we therefore define requirements for a traffic simulation based on a complex real-world scenario in Germany. The project addresses major urban challenges and aims at demonstrating the contribution that the upcoming 5G mobile generation can make to solving real-time traffic flow optimization. In a second step, we investigate in detail if the simulation environment SUMO (Simulation of Urban Mobility) fulfills the postulated requirements. Thirdly, we propose a technical concept to close the gap of the uncovered requirements for later implementation.