With the growing popularity of autonomous unmanned aerial vehicles (UAVs), the improvement of safety for UAV operations has become increasingly important. In this paper, a landing trajectory optimization scheme is proposed to generate reference landing trajectories for a fixed-wing UAV with accidental engine failure. For a specific landing objective, two types of landing trajectory optimization algorithms are investigated: i) trajectory optimization algorithm with nonlinear UAV dynamics, and ii) trajectory optimization algorithm with linearized UAV dynamics. An initialization procedure that generates an initial guess is introduced to accelerate the convergence of the optimization algorithms. The effectiveness of the proposed scheme is verified in a high-fidelity UAV simulation environment, where the optimized landing trajectories are tracked by a UAV equipped with an L1 adaptive altitude controller in both the offline and online modes.
more »
« less
Trajectory Design for Unmanned Aerial Vehicles via Meta-Reinforcement Learning
This paper considers the trajectory design problem for unmanned aerial vehicles (UAVs) via meta-reinforcement learning. It is assumed that the UAV can move in different directions to explore a specific area and collect data from the ground nodes (GNs) located in the area. The goal of the UAV is to reach the destination and maximize the total data collected during the flight on the trajectory while avoiding collisions with other UAVs. In the literature on UAV trajectory designs, vanilla learning algorithms are typically used to train a task-specific model, and provide near-optimal solutions for a specific spatial distribution of the GNs. However, this approach requires retraining from scratch when the locations of the GNs vary. In this work, we propose a meta reinforcement learning framework that incorporates the method of Model-Agnostic Meta-Learning (MAML). Instead of training task-specific models, we train a common initialization for different distributions of GNs and different channel conditions. From the initialization, only a few gradient descents are required for adapting to different tasks with different GN distributions and channel conditions. Additionally, we also explore when the proposed MAML framework is preferred and can outperform the compared algorithms.
more »
« less
- Award ID(s):
- 2221875
- NSF-PAR ID:
- 10464774
- Date Published:
- Journal Name:
- IEEE INFOCOM 2023 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)
- Page Range / eLocation ID:
- 1 to 6
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Modern advances in unmanned aerial vehicle (UAV) technology have widened the scope of commercial and military applications. However, the increased dependency on wireless communications exposes UAVs to potential attacks and introduces new threats, especially from UAVs designed with the malicious intent of targeting vital infrastructures. Significant efforts have been made from researchers and other United States (U.S.) Department of Defense (DoD) agencies for developing countermeasures for detection, interception, or destruction of the malicious UAVs. One promising countermeasure is the use of a counter UAV (CUAV) swarm to detect, track, and neutralize the malicious UAV. This paper aims to recognize the state-of-the-art swarm intelligence algorithms for achieving cooperative capture of a mobile target UAV. The major design and implementation challenges for swarm control, algorithm architecture, and safety protocols are considered. A prime challenge for UAV swarms is a robust communication infrastructure to enable accurate data transfer between UAVs for efficient path planning. A multi-agent deep reinforcement learning approach is applied to train a group of CUAVs to intercept a faster malicious UAV, while avoiding collisions among other CUAVs and non-cooperating obstacles (i.e. other aerial objects maneuvering in the area). The impact of the latency incurred through UAV-to-UAV communications is showcased and discussed with preliminary numerical results.more » « less
-
null (Ed.)The problem of learning to generalize on unseen classes during the training step, also known as few-shot classification, has attracted considerable attention. Initialization based methods, such as the gradient-based model agnostic meta-learning (MAML) [1], tackle the few-shot learning problem by “learning to fine-tune”. The goal of these approaches is to learn proper model initialization so that the classifiers for new classes can be learned from a few labeled examples with a small number of gradient update steps. Few shot meta-learning is well-known with its fast-adapted capability and accuracy generalization onto unseen tasks [2]. Learning fairly with unbiased outcomes is another significant hallmark of human intelligence, which is rarely touched in few-shot meta-learning. In this work, we propose a novel Primal-Dual Fair Meta-learning framework, namely PDFM, which learns to train fair machine learning models using only a few examples based on data from related tasks. The key idea is to learn a good initialization of a fair model’s primal and dual parameters so that it can adapt to a new fair learning task via a few gradient update steps. Instead of manually tuning the dual parameters as hyperparameters via a grid search, PDFM optimizes the initialization of the primal and dual parameters jointly for fair meta-learning via a subgradient primal-dual approach. We further instantiate an example of bias controlling using decision boundary covariance (DBC) [3] as the fairness constraint for each task, and demonstrate the versatility of our proposed approach by applying it to classification on a variety of three real-world datasets. Our experiments show substantial improvements over the best prior work for this setting.more » « less
-
Motivated by concerns surrounding the fairness effects of sharing and transferring fair machine learning tools, we propose two algorithms: Fairness Warnings and Fair-MAML. The first is a model-agnostic algorithm that provides interpretable boundary conditions for when a fairly trained model may not behave fairly on similar but slightly different tasks within a given domain. The second is a fair meta-learning approach to train models that can be quickly fine-tuned to specific tasks from only a few number of sample instances while balancing fairness and accuracy. We demonstrate experimentally the individual utility of each model using relevant baselines and provide the first experiment to our knowledge of K-shot fairness, i.e. training a fair model on a new task with only K data points. Then, we illustrate the usefulness of both algorithms as a combined method for training models from a few data points on new tasks while using Fairness Warnings as interpretable boundary conditions under which the newly trained model may not be fair.more » « less
-
There has recently been an increasing interest in computationally-efficient learning methods for resource-constrained applications, e.g., pruning, quantization and channel gating. In this work, we advocate a holistic approach to jointly train the backbone network and the channel gating which can speed up subnet selection for a new task at the resource-limited node. In particular, we develop a federated meta-learning algorithm to jointly train good meta-initializations for both the backbone networks and gating modules, by leveraging the model similarity across learning tasks on different nodes. In this way, the learnt meta-gating module effectively captures the important filters of a good meta-backbone network, and a task-specific conditional channel gated network can be quickly adapted from the meta-initializations using data samples of the new task. The convergence of the proposed federated meta-learning algorithm is established under mild conditions. Experimental results corroborate the effectiveness of our method in comparison to related work.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/INFOCOMWKSHPS57453.2023.10226090
