Robot navigation allows mobile robots to navigate among obstacles without hitting them and reaching the specified goal point. In addition to preventing collisions, it is also essential for mobile robots to sense and maintain an appropriate battery power level at all times to avoid failures and non-fulfillment with their scheduled tasks. Therefore, selecting the proper time to recharge the batteries is crucial to address the navigation algorithm design for the robot’s prolonged autonomous operation. In this paper, a machine learning algorithm is used to ensure the extended robot autonomy based on a reinforcement learning method combined with a fuzzy inference system. The proposal enables a mobile robot to learn whether to continue through its path toward the destination or modify its course on the fly, if necessary, to proceed toward the battery charging station, based on its current state. The proposal performs a flexible behavior to choose an action that allows a robot to move from a starting to a destination point, guaranteeing battery charge availability. This paper shows the obtained results using an approach with thirty-six states and its reduction with twenty states. The conducted simulations show that the robot requires fewer training epochs to achieve ten consecutive successes in the fifteen proposed scenarios than traditional reinforcement learning methods exhibit. Moreover, in four scenarios, the robot ends up with a battery level above 80%, that value is higher than the obtained results with two deterministic methods.

In computer vision, human action recognition is a hot topic, popularized by the development of deep learning. Deep learning models typically accept video input without prior processing and train them to achieve recognition. However, conducting preliminary motion analysis can be beneficial in directing the model training to prioritize the motion of individuals with less priority for the environment in which the action occurs. This paper puts forth a novel methodology for human action recognition based on motion information that employs transfer-learning techniques. The proposed method comprises four stages: (1) human detection and tracking, (2) motion estimation, (3) feature extraction, and (4) action recognition using a two-stream model. In order to develop this work, a customized dataset was utilized, comprising videos of diverse actions (e.g., walking, running, cycling, drinking, and falling) extracted from multiple public sources and websites, including Pexels and MixKit. This realistic and diverse dataset allowed for a comprehensive evaluation of the proposed method, demonstrating its effectiveness in different scenarios and conditions. Furthermore, the performance of seven pre-trained models for feature extraction was evaluated. The models analyzed were Inception-v3, MobileNet-v2, MobileNet-v3-L, VGG-16, VGG-19, Xception, and ConvNeXt-L. The results demonstrated that the ConvNeXt-L model yielded the most optimal outcomes. Furthermore, using pre-trained models for feature extraction facilitated the training process on a personal computer with a single graphics processing unit, achieving an accuracy of 94.9%. The experimental findings and outcomes suggest that integrating motion information enhances action recognition performance.

In computer vision, human action recognition is a hot topic, popularized by the development of deep learning. Current models have achieved high accuracy results on public datasets. Despite this success, they require significant computational resources for training. Given that transfer learning based techniques allow reusing what other models have already learned and training models with less computational resources, in this work we propose using a transfer learning based approach for action recognition in videos. We describe a methodology for human action recognition using transfer learning techniques in a custom dataset. The proposed method consists of four stages: 1) human detection and tracking, 2) video preprocessing, 3) feature extraction (using pretrained models with ImageNet), and 4) action recognition using a two-stream model consisting of TCNs, LSTMs, and CNNs layers. The custom dataset is imbalanced with 189, 390, 490, 854, and 890 videos per class, respectively. For feature extraction, we analyzed the performance of seven pretrained models: Inception-v3, MobileNet-v2, MobileNet-v3-L, VGG-16, VGG-19, Xception, and ConvNeXt-L. We show that the best results were obtained with the last one. Finally, using pretrained models for feature extraction allowed training in a PC with a single GPU with an accuracy of 94.9%.