Intelligent transportation systems (ITS) are pivotal in modern urban development by enhancing mobility and transit efficiency. However, the challenges of accurate short-term traffic prediction persist due to real-time traffic data’s dynamic, nonlinear, and non-stationary nature. In this study, the author addresses these challenges and proposes a novel approach to improve traffic flow prediction. Our research introduces a hybrid model, combining Long-Short Term Memory (LSTM) and the Kalman filter-based Rauch-Tung-Striebel (RTS) noise reduction technique, tailored to mitigate the limitations of low market penetration of connected vehicles and data availability. This paper aims to provide a robust traffic prediction solution with direct applications in smart cities and real-time traffic management. To evaluate our model’s efficacy, The author conducted an empirical case study using the Enhanced Next Generation Simulation (NGSIM) dataset, which offers highly granular vehicle trajectory data. The author rigorously analyses our methodology and algorithms to assess the quality of traffic predictions. Our results show that the proposed model outperforms traditional LSTM models. In particular, the Bi-LSTM/RTS model achieved a remarkable accuracy of 99% in predicting traffic patterns during sunny weather conditions, signifying a significant advancement in short-term traffic prediction accuracy. The evaluation metrics demonstrate that Bi-LSTM outperforms LSTM by a wide margin, with a coefficient of determination value of 0.99 against 0.97. The trend anticipated by Bi-LSTM (8.6%) is more in line with the actual trend than that projected by LSTM (8.9%), as seen by the smaller MAPE. In conclusion, Bi-LSTM outperforms LSTM at predicting traffic patterns.

Combining multiple sensors for environment sensing and self-positioning is significant for automatic driving. This paper proposes a novel simultaneous localization and mapping (SLAM) system framework that integrates the information ofmultiple sensors including camera, Light Detection and Ranging (LiDAR), Inertial Measurement Unit (IMU), and Global Positioning System (GPS) based on vision-LiDAR calibration. Different sensors are fused in a tightly coupled manner and finally optimized by a factor graph. The automatic vision-LiDAR calibration (AVLC) is proposed in this paper to reduce the error caused by the unexpected change in the sensor. Further, the semantic map is established by the target detection module, which provides convenience for navigation and obstacle avoidance. The proposed algorithm uses the Complex-YOLO for 3D object recognition and then combines the recognition results with the semi-dense point cloud map generated by the multi-sensor fusion positioning algorithm with AVLC to achieve the purpose of enriching map information. Extensive experiments on multiple datasets show that the proposed algorithm has higher accuracy and robustness than other existing algorithms.

Indoor scene classification plays a pivotal role in enabling social robots to seamlessly adapt to their environments, facilitating effective navigation and interaction within diverse indoor scenes. By accurately characterizing indoor scenes, robots can autonomously tailor their behaviors, making informed decisions to accomplish specific tasks. Traditional methods relying on manually crafted features encounter difficulties when characterizing complex indoor scenes. On the other hand, deep learning models address the shortcomings of traditional methods by autonomously learning hierarchical features from raw images. Despite the success of deep learning models, existing models still struggle to effectively characterize complex indoor scenes. This is because there is high degree of intra-class variability and inter-class similarity within indoor environments. To address this problem, we propose a dual-stream framework that harnesses both global contextual information and local features for enhanced recognition. The global stream captures high-level features and relationships across the scene. The local stream employs a fully convolutional network to extract fine-grained local information. The proposed dual-stream architecture effectively distinguishes scenes that share similar global contexts but contain different localized objects. We evaluate the performance of the proposed framework on a publicly available benchmark indoor scene dataset. From the experimental results, we demonstrate the effectiveness of the proposed framework.

The ability to classify rooms in a home is one of many attributes that are desired for social robots. In this paper, we address the problem of indoor room classification via several convolutional neural network (CNN) architectures, i.e., VGG16, VGG19, & Inception V3. The main objective is to recognize five indoor classes (bathroom, bedroom, dining room, kitchen, and living room) from a Places dataset. We considered 11600 images per class and subsequently fine-tuned the networks. The simulation studies suggest that cleaning the disparate data produced much better results in all the examined CNN architectures. We report that VGG16 & VGG19 fine-tuned models with training on all layers produced the best validation accuracy, with 93.29% and 93.61% on clean data, respectively. We also propose and examine a combination model of CNN and a multi-binary classifier referred to as error correcting output code (ECOC) with the clean data. The highest validation accuracy of 15 binary classifiers reached up to 98.5%, where the average of all classifiers was 95.37%. CNN and CNN-ECOC, and an alternative form called CNN-ECOC Regression, were evaluated in real-time implementation on a NAO humanoid robot. The results show the superiority of the combination model of CNN and ECOC over the conventional CNN. The implications and the challenges of real-time experiments are also discussed in the paper.

We present a SLAM with closed-loop controller method for navigation of NAO humanoid robot from Aldebaran. The method is based on the integration of laser and vision system. The camera is used to recognize the landmarks whereas the laser provides the information for simultaneous localization and mapping (SLAM ). K-means clustering method is implemented to extract data from different objects. In addition, the robot avoids the obstacles by the avoidance function. The closed-loop controller reduces the error between the real position and estimated position. Finally, simulation and experiments show that the proposed method is efficient and reliable for navigation in indoor environments.