We present Premier-TACO, a multitask feature representation learning approach designed to improve few-shot policy learning efficiency in sequential decision-making tasks. Premier-TACO leverages a subset of multitask offline datasets for pretraining a general feature representation, which captures critical environmental dynamics and is fine-tuned using minimal expert demonstrations. It advances the temporal action contrastive learning (TACO) objective, known for state-of-the-art results in visual control tasks, by incorporating a novel negative example sampling strategy. This strategy is crucial in significantly boosting TACO's computational efficiency, making large-scale multitask offline pretraining feasible. Our extensive empirical evaluation in a diverse set of continuous control benchmarks including Deepmind Control Suite, MetaWorld, and LIBERO demonstrate Premier-TACO's effectiveness in pretraining visual representations, significantly enhancing few-shot imitation learning of novel tasks. Our code, pretraining data, as well as pretrained model checkpoints will be released at https://github.com/PremierTACO/premier-taco.

Developing aerial robots that can both safely navigate and execute assigned mission without any human intervention - i.e., fully autonomous aerial mobility of passengers and goods - is the larger vision that guides the research, design, and development efforts in the aerial autonomy space. However, it is highly challenging to concurrently operationalize all types of aerial vehicles that are operating fully autonomously sharing the airspace. Full autonomy of the aerial transportation sector includes several aspects, such as design of the technology that powers the vehicles, operations of multi-agent fleets, and process of certification that meets stringent safety requirements of aviation sector. Thereby, Autonomous Advanced Aerial Mobility is still a vague term and its consequences for researchers and professionals are ambiguous. To address this gap, we present a comprehensive perspective on the emerging field of autonomous advanced aerial mobility, which involves the use of unmanned aerial vehicles (UAVs) and electric vertical takeoff and landing (eVTOL) aircraft for various applications, such as urban air mobility, package delivery, and surveillance. The article proposes a scalable and extensible autonomy framework consisting of four main blocks: sensing, perception, planning, and controls. Furthermore, the article discusses the challenges and opportunities in multi-agent fleet operations and management, as well as the testing, validation, and certification aspects of autonomous aerial systems. Finally, the article explores the potential of monolithic models for aerial autonomy and analyzes their advantages and limitations. The perspective aims to provide a holistic picture of the autonomous advanced aerial mobility field and its future directions.

One major barrier to advancing aerial autonomy has been collecting large-scale aerial datasets for training machine learning models. Due to costly and time-consuming real-world data collection through deploying drones, there has been an increasing shift towards using synthetic data for training models in drone applications. However, to increase widespread generalization and transferring models to real-world, increasing the diversity of simulation environments to train a model over all the varieties and augmenting the training data, has been proved to be essential. Current synthetic aerial data generation tools either lack data augmentation or rely heavily on manual workload or real samples for configuring and generating diverse realistic simulation scenes for data collection. These dependencies limit scalability of the data generation workflow. Accordingly, there is a major challenge in balancing generalizability and scalability in synthetic data generation. To address these gaps, we introduce a scalable Aerial Synthetic Data Augmentation (ASDA) framework tailored to aerial autonomy applications. ASDA extends a central data collection engine with two scriptable pipelines that automatically perform scene and data augmentations to generate diverse aerial datasets for different training tasks. ASDA improves data generation workflow efficiency by providing a unified prompt-based interface over integrated pipelines for flexible control. The procedural generative approach of our data augmentation is performant and adaptable to different simulation environments, training tasks and data collection needs. We demonstrate the effectiveness of our method in automatically generating diverse datasets and show its potential for downstream performance optimization.

For short-term solar irradiance forecasting, the traditional point forecasting methods are rendered less useful due to the non-stationary characteristic of solar power. The amount of operating reserves required to maintain reliable operation of the electric grid rises due to the variability of solar energy. The higher the uncertainty in the generation, the greater the operating-reserve requirements, which translates to an increased cost of operation. In this research work, we propose a unified architecture for multi-time-scale predictions for intra-day solar irradiance forecasting using recurrent neural networks (RNN) and long-short-term memory networks (LSTMs). This paper also lays out a framework for extending this modeling approach to intra-hour forecasting horizons thus, making it a multi-time-horizon forecasting approach, capable of predicting intra-hour as well as intra-day solar irradiance. We develop an end-to-end pipeline to effectuate the proposed architecture. The performance of the prediction model is tested and validated by the methodical implementation. The robustness of the approach is demonstrated with case studies conducted for geographically scattered sites across the United States. The predictions demonstrate that our proposed unified architecture-based approach is effective for multi-time-scale solar forecasts and achieves a lower root-mean-square prediction error when benchmarked against the best-performing methods documented in the literature that use separate models for each time-scale during the day. Our proposed method results in a 71.5% reduction in the mean RMSE averaged across all the test sites compared to the ML-based best-performing method reported in the literature. Additionally, the proposed method enables multi-time-horizon forecasts with real-time inputs, which have a significant potential for practical industry applications in the evolving grid.

The non-stationarity characteristic of the solar power renders traditional point forecasting methods to be less useful due to large prediction errors. This results in increased uncertainties in the grid operation, thereby negatively affecting the reliability and increased cost of operation. This research paper proposes a unified architecture for multi-time-horizon predictions for short and long-term solar forecasting using Recurrent Neural Networks (RNN). The paper describes an end-to-end pipeline to implement the architecture along with the methods to test and validate the performance of the prediction model. The results demonstrate that the proposed method based on the unified architecture is effective for multi-horizon solar forecasting and achieves a lower root-mean-squared prediction error compared to the previous best-performing methods which use one model for each time-horizon. The proposed method enables multi-horizon forecasts with real-time inputs, which have a high potential for practical applications in the evolving smart grid.