This paper presents LEVIOSA, a novel framework for text- and speech-based uncrewed aerial vehicle (UAV) trajectory generation. By leveraging multimodal large language models (LLMs) to interpret natural language commands, the system converts text and audio inputs into executable flight paths for UAV swarms. The approach aims to simplify the complex task of multi-UAV trajectory generation, which has significant applications in fields such as search and rescue, agriculture, infrastructure inspection, and entertainment. The framework involves two key innovations: a multi-critic consensus mechanism to evaluate trajectory quality and a hierarchical prompt structuring for improved task execution. The innovations ensure fidelity to user goals. The framework integrates several multimodal LLMs for high-level planning, converting natural language inputs into 3D waypoints that guide UAV movements and per-UAV low-level controllers to control each UAV in executing its assigned 3D waypoint path based on the high-level plan. The methodology was tested on various trajectory types with promising accuracy, synchronization, and collision avoidance results. The findings pave the way for more intuitive human–robot interactions and advanced multi-UAV coordination.

Nozzles are ubiquitous in agriculture: they are used to spray and apply nutrients and pesticides to crops. The properties of droplets sprayed from nozzles are vital factors that determine the effectiveness of the spray. Droplet size and other characteristics affect spray retention and drift, which indicates how much of the spray adheres to the crop and how much becomes chemical runoff that pollutes the environment. There is a critical need to measure these droplet properties to improve the performance of crop spraying systems. This paper establishes a deep learning methodology to detect droplets moving across a camera frame to measure their size. This framework is compatible with embedded systems that have limited onboard resources and can operate in real time. The method leverages a combination of techniques including resizing, normalization, pruning, detection head, unified feature map extraction via a feature pyramid network, non-maximum suppression, and optimization-based training. The approach is designed with the capability of detecting droplets of various sizes, shapes, and orientations. The experimental results demonstrate that the model designed in this study, coupled with the right combination of dataset and augmentation, achieved a 97% precision and 96.8% recall in droplet detection. The proposed methodology outperformed previous models, marking a significant advancement in droplet detection for precision agriculture applications.

Landing a multi-rotor uncrewed aerial vehicle (UAV) on a moving target in the presence of partial observability, due to factors such as sensor failure or noise, represents an outstanding challenge that requires integrative techniques in robotics and machine learning. In this paper, we propose embedding a long short-term memory (LSTM) network into a variation of proximal policy optimization (PPO) architecture, termed robust policy optimization (RPO), to address this issue. The proposed algorithm is a deep reinforcement learning approach that utilizes recurrent neural networks (RNNs) as a memory component. Leveraging the end-to-end learning capability of deep reinforcement learning, the RPO-LSTM algorithm learns the optimal control policy without the need for feature engineering. Through a series of simulation-based studies, we demonstrate the superior effectiveness and practicality of our approach compared to the state-of-the-art proximal policy optimization (PPO) and the classical control method Lee-EKF, particularly in scenarios with partial observability. The empirical results reveal that RPO-LSTM significantly outperforms competing reinforcement learning algorithms, achieving up to 74% more successful landings than Lee-EKF and 50% more than PPO in flicker scenarios, maintaining robust performance in noisy environments and in the most challenging conditions that combine flicker and noise. These findings underscore the potential of RPO-LSTM in solving the problem of UAV landing on moving targets amid various degrees of sensor impairment and environmental interference.

This paper discusses nonprehensile manipulation of an asymmetric object using a robotic manipulator from a motion planning point of view. Four different aspects of the problem will be analyzed: object stability, motion planning, manipulator control, and experimental validation. Specifically, via an analysis of marginal stability of an object resting on a moving tray, the work establishes the critical accelerations of the manipulator's end-effector, below which the object's stability is guaranteed. These critical accelerations guide the design of the end-effector's motion for successful nonprehensile manipulation of the object. In particular, we propose two methods to formulate polynomial asymmetric s-curve trajectories such that the end- effector completes its motion in minimum time. In one method, the trajectory is divided into segments whose time intervals are then computed via a recursive algorithm. In the other method, we formulate an optimization problem and design the minimum-time trajectory by balancing the trade-off between the travel time and actuator effort. A series of experiments with a robotic arm is designed to validate and compare these motion planning methods in the context of nonprehensile manipulation. In addition, the experimental results demonstrate the advantages of the asymmetric s-curve motion profiles over the traditional symmetric s-curves.