Trans-Contextual Model Predicting Change in Out-of-School Physical Activity: A One-Year Longitudinal Study

The aim of the current study was to test the long-term predictive validity of the trans-contextual model in accounting for variance in adolescents’ out-of-school physical activity measured by self-report and accelerometer based-devices over a one-year period. Secondary school students ( N = 265) aged 11 to 15 years completed a three-wave survey on two occasions in time, spanning a one-year interval, measuring perceived autonomy support in physical education (PE), peer and parent autonomy support in leisure-time, autonomous and controlled motivation in PE and leisure-time, attitude, subjective norms, perceived behavioural control, intention, and out-of-school physical activity both by self-report and accelerometer-based devices. A variance-based structural equation model using residualized change scores revealed that perceived autonomy support from PE teachers predicted autonomous motivation in PE, and autonomous motivation in PE predicted autonomous motivation in leisure-time. In addition, peer and parent autonomy support predicted autonomous motivation in leisure-time. Autonomous motivation in leisure-time indirectly predicted physical activity intention mediated by attitude and perceived behavioural control. Intention predicted self-reported physical activity participation, although the effect was in the opposite direction to our prediction, but not physical activity measured by accelerometer-based devices. Results support some tenets of the trans-contextual model over a one-year time period, particularly the determinants of physical activity intentions. The introduction of COVID-19 restrictions may explain the negative relationship between intention and self-reported physical activity. Further longitudinal studies are needed to verify the results of the current study.

Fast Drivable Areas Estimation with Multi-Task Learning for Real-Time Autonomous Driving Assistant

Autonomous driving is a safety-critical application that requires a high-level understanding of computer vision with real-time inference. In this study, we focus on the computational efficiency of an important factor by improving the running time and performing multiple tasks simultaneously for practical applications. We propose a fast and accurate multi-task learning-based architecture for joint segmentation of drivable area, lane line, and classification of the scene. An encoder-decoder architecture efficiently handles input frames through shared representation. A comprehensive understanding of the driving environment is improved by generalization and regularization from different tasks. The proposed method learns end-to-end through multi-task learning on a very challenging Berkeley Deep Drive dataset and shows its robustness for three tasks in autonomous driving. Experimental results show that the proposed method outperforms other multi-task learning approaches in both speed and accuracy. The computational efficiency of the method was over 93.81 fps at inference, enabling execution in real-time.

ISACS

90% of retail sales occur in physical stores. In these physical stores 40% of shoppers leave the store based on the wait time. Autonomous stores can remove customer waiting time by providing a receipt without the need for scanning the items. Prior approaches use computer vision only, combine computer vision with weight sensors, or combine computer vision with sensors and human product recognition. These approaches, in general, suffer from low accuracy, up to hour long delays for receipt generation, or do not scale to store level deployments due to computation requirements and real-world multiple shopper scenarios. We present ISACS, which combines a physical store model (e.g. customers, shelves, and item interactions), multi-human 3D pose estimation, and live inventory monitoring to provide an accurate matching of multiple people to multiple products. ISACS utilizes only shelf weight sensors and does not require visual inventory monitoring which drastically reduces the computational requirements and thus is scalable to a store-level deployment. In addition, ISACS generates an instant receipt by not requiring human intervention during receipt generation. To fully evaluate the ISACS, we deployed and evaluated our approach in an operating convenience store covering 800 square feet with 1653 distinct products, and more than 20,000 items. Over the course of 13 months of operation, ISACS achieved a receipt daily accuracy of up to 96.4%. Which translates to a 3.5x reduction in error compared to self-checkout stations.

Hardware in the Loop Topology for an Omnidirectional Mobile Robot Using Matlab in a Robot Operating System Environment

The symmetry of the omnidirectional robot motion abilities around its central vertical axis is an important advantage regarding its driveability for the flexible interoperation with fixed conveyor systems. The paper illustrates a Hardware in the Loop architectural approach for integrated development of an Ominidirectional Mobile Robot that is designed to serve in a dynamic logistic environment. Such logistic environments require complex algorithms for autonomous navigation between different warehouse locations, that can be efficiently developed using Robot Operating System nodes. Implementing path planning nodes benefits from using Matlab-Simulink, which provides a large selection of algorithms that are easily integrated and customized. The proposed solution is deployed for validation on a NVIDIA Jetson Nano, the embedded computer hosted locally on the robot, that runs the autonomous navigation software. The proposed solution permits the live connection to the omnidirectional prototype platform, allowing to deploy algorithms and acquire data for debugging the location, path planning and the mapping information during real time autonomous navigation experiments, very useful in validating different strategies.