Deep RL drone trained to compete against classical path planning in drone racing.
problem Optimizing long-term drone racing strategies using reinforcement learning.
method Used PPO algorithm on a simulated quadrotor in a racing environment created with AirSim.
result Deep RL agent outperformed classical path planning in drone racing competitions.
Drone optimizes collaborative learning for neural networks.
problem Training a shared neural network with heterogeneous data from multiple devices.
method Drone collects and aggregates model parameters from devices, optimizing trajectory for best accuracy.
result Significant improvement in final accuracy and speedup in training time.
Deep Q-learning optimizes same-day delivery with vehicles and drones.
problem Optimizing same-day delivery with limited vehicle and drone capacities.
method Deep Q-learning approach to assign packages to vehicles or drones.
result Deep Q-learning policy outperforms benchmark policies and maintains effectiveness with changing fleet sizes.
Solves challenges of drone communication in cellular networks.
problem Interference from drones to base stations in cellular networks.
method Derived analytical models, formulated optimization problem, transformed into machine learning problem, solved using deep reinforcement learning.
result Optimal handover and resource management policies for drones in cellular networks.
A drone catches another agile drone using competitive reinforcement learning.
problem Intercepting an agile drone with another agile drone.
method Formulated as a Competitive Reinforcement Learning problem, trained with PPO, using a high-fidelity simulation environment.
result Trained policies outperform common heuristic baselines in catch rate, time to catch, and crash rate.
We present NAVREN-RL, an approach to NAVigate an unmanned aerial vehicle in an indoor Real ENvironment via end-to-end reinforcement learning RL. A suitable reward function is designed keeping in mind the cost and weight constraints for micro drone with minimum number of sensing modalities. Collection of small number of…
A drone-based MOT algorithm tracks vehicles using neural network detections and TPMBM filter.
problem Tracking multiple vehicles from drone-mounted cameras.
method Neural network for object detection, TPMBM filter for trajectory estimation, von-Mises Fisher distribution for DOA.
result TPMBM filter optimally estimates vehicle trajectories.
Paper presents a TL approach to reduce drone training time and energy consumption.
problem Limited power and compute capability of edge drones.
method Transfer Learning for deep neural network training via Deep Reinforcement Learning.
result 3.7x reduction in energy consumption and 1.8x reduction in training latency.
Augment small datasets with synthetic backgrounds to train lightweight CNNs for human pose estimation.
problem Training CNNs from limited real-world data for human pose estimation.
method Synthetic background substitution for data augmentation.
result Improves generalization to unseen environments.
Deep reinforcement learning controls drones without model knowledge.
problem Real-time robot control without engineered models.
method Learnt probabilistic model of drone dynamics, model-based reinforcement learning.
result Controller and value function optimized through generated latent trajectories.
A new method for drone-based geo-localization using style and spatial alignment.
problem Geo-localization of drone-view images with satellite-view images using pre-annotated GPS tags.
method Orientation-based method to align patterns, new branch to extract aligned partial features, style alignment strategy.
result The proposed method outperforms state-of-the-art alternatives in geo-localization accuracy.
This paper explores formal verification for autonomous systems, identifying limitations and proposing improvements.
problem Ensuring safety of autonomous systems like self-driving cars and drones.
method Formal verification techniques based on formal methods, analyzing three assumptions and their limitations.
result Preliminary work to improve the strength of evidence provided by formal verification.
Meta-learning improves drone trajectory design for dynamic wireless networks.
problem Designing optimal trajectories for energy-constrained drones in dynamic network environments.
method Proposes a meta-learning algorithm to adaptively tune a reinforcement learning solution for trajectory design.
result Meta-tuned RL yields faster convergence and improved communication performance compared to baseline algorithms.
Simple model predicts trajectory probabilities.
problem Forecasting trajectories from visual data.
method Spatio-temporal convolutional neural network.
result Achieves results on par with or better than existing methods.
The paper detects amateur drones using acoustic signals, overcoming interference.
problem Detection of unmonitored UAVs (amateur drones) for security and safety.
method Machine learning approach using Independent Component Analysis (ICA) for acoustic signal detection.
result The RMS values of PSD with KNN outperform other methods in detecting AmDr.
HighD dataset captures naturalistic vehicle behavior on German highways for automated driving validation.
problem Current measurement methods fail to meet requirements for scenario-based validation of highly automated vehicles.
method Aerial perspective data collection fulfilling naturalistic behavior, quantity, and variety requirements.
result 16.5 hours of measurements from six locations, 110,000 vehicles, 45,000 km driven, 5600 lane changes.
CitySim dataset captures vehicle trajectories for safety research.
problem Lack of fine-grain vehicle trajectories for safety-oriented research.
method Five-step procedure: video stabilization, object filtering, stitching, detection, and error filtering.
result CitySim dataset improves safety evaluations and facilitates digital-twin research.
Combines neural networks and STL for multi-class time-series classification.
problem Lack of interpretability in neural networks for time-series data.
method Proposes a method that uses neural networks to classify time-series data using STL specifications, introducing margin for multi-class classification and STL-based attributes for interpretability.
result Evaluations show improved interpretability and performance compared to state-of-the-art baselines.
3D point cloud attacks examine how neural networks can be fooled.
problem Understanding how 3D neural networks can be exploited by attackers.
method Examined two categories of attacks: distributional and shape attacks.
result Some shape attacks can fool 3D point cloud classification models even after preprocessing.
This dissertation uses deep reinforcement learning to improve drone flight control.
problem Inadequate traditional control methods for unpredictable CPS interactions.
method Developed a full solution stack for neuro-flight controllers using deep neural networks.
result Reinforcement learning enables training neural network controllers for stable and precise flight.
New method uses UAV imagery and ML to map crops and weeds.
problem Mapping crops and weeds at high resolution.
method Machine Learning algorithms trained on expert-masked images.
result Maps with >90% identification efficiency at 5m altitude.
Modern vision-based reinforcement learning techniques often use convolutional neural networks (CNN) as universal function approximators to choose which action to take for a given visual input. Until recently, CNNs have been treated like black-box functions, but this mindset is especially dangerous when used for control…
We introduce a Bayesian defect detector to facilitate the defect detection on the motion blurred images on rough texture surfaces. To enhance the accuracy of Bayesian detection on removing non-defect pixels, we develop a class of reflected non-local prior distributions, which is constructed by using the mode of a distr…
Riemannian batchnorm improves SPD matrix networks.
problem Learning SPD matrices in deep networks.
method Introduces a novel Riemannian batchnorm algorithm.
result Riemannian batchnorm outperforms existing methods.
UAVs learn to collect data from IoT sensors efficiently.
problem Efficient UAV path planning for wireless data collection.
method Deep reinforcement learning (DDQN) with experience replay and convolutional layers.
result UAV control policy generalizes over changing scenario parameters.
CF-VAE models capture multi-modal distributions for better structured sequence prediction.
problem Challenges in capturing multi-modality of future states in latent variable models.
method Conditional Flow Variational Autoencoders (CF-VAE) with conditional normalizing flows.
result CF-VAE achieves state-of-the-art results on multi-modal structured sequence prediction datasets.
A new ML framework for RF fingerprinting across various applications.
problem Extracting unique RF fingerprints for specific emitter identification.
method Generic machine learning framework for automatic RF fingerprinting.
result Framework achieves superior performance compared to traditional methods.
Single network with segmented training prevents forgetting in dynamic systems.
problem Catastrophic forgetting in continual learning for dynamic systems.
method Single Net with Progressive Segmented Training (PST). Model parameters are divided into frozen and secondary groups.
result Achieves state-of-the-art accuracy in single-head evaluation on CIFAR-10 and CIFAR-100 datasets.
Improved person detection in occluded conditions with AOS images.
problem Inaccurate classification of partially occluded people, animals, or objects.
method Combining multi-perspective images captured by Airborne Optical Sectioning (AOS) to achieve better precision and recall.
result Precision/recall of 96/93% for automated person detection.
Deep Neural Networks (DNNs) are increasingly deployed in highly energy-constrained environments such as autonomous drones and wearable devices while at the same time must operate in real-time. Therefore, reducing the energy consumption has become a major design consideration in DNN training. This paper proposes the fir…
Convolutional Neural Networks (CNNs) have become the method of choice for learning problems involving 2D planar images. However, a number of problems of recent interest have created a demand for models that can analyze spherical images. Examples include omnidirectional vision for drones, robots, and autonomous cars, mo…
A new method for learning policies in multiple environments.
problem Learning policies that work in different but related environments.
method Decentralized entropy-regularized policy gradient method.
result The method can learn effective policies in multiple environments.
Reinforcement learning (RL) has advanced greatly in the past few years with the employment of effective deep neural networks (DNNs) on the policy networks. With the great effectiveness came serious vulnerability issues with DNNs that small adversarial perturbations on the input can change the output of the network. Sev…
Research tackles safety of deep learning in safety-critical tasks.
problem Safety concerns of deep learning in perception tasks for autonomous agents.
method Technical enumeration and discussions on safety concerns and mitigation methods.
result Need for more mitigation methods to ensure safety of deep learning.
Decentralized TD learning converges linearly with linear function approximation.
problem Policy evaluation in fully decentralized multi-agent reinforcement learning.
method Temporal-difference learning with linear function approximation, analyzing i.i.d. and Markovian samples.
result Local estimates converge linearly to the optimum under both i.i.d. and Markovian samples.
Proposes a robust 3D classification method for sparse point clouds.
problem Invariance to rotation, positional shift, scaling, and robustness to point sparsity in point cloud classification.
method Introduces a graph-based feature learning approach with an end-to-end neural network.
result Significantly improves 3D object classification and retrieval tasks with sparse point clouds.
Smart Quantization adapts binary and ternary quantization for neural networks.
problem Resource constraints in deploying neural networks on devices with limited resources.
method Adaptive combination of binary and ternary quantization with a regularization function.
result Adapts quantization depth during training to maintain high model accuracy.
A novel approach for federated learning over-the-air computation to reduce latency and improve privacy.
problem Low-latency and privacy issues in edge machine learning for intelligent devices.
method Over-the-air computation and sparse-low-rank optimization for efficient global model aggregation.
result Efficient global model aggregation with low latency and improved privacy.
Abstract Neural Networks (ANNs) improve DNN verification efficiency.
problem Efficiently verify safety-critical DNNs without slowing exponentially.
method Introduces ANNs that use abstract domains and activation functions to overapproximate DNNs.
result ANNs can soundly overapproximate DNNs with fewer nodes, improving verification efficiency.
Bayesian fusion improves radar target recognition for UAVs.
problem Improving radar target recognition for UAVs using multistatic radar configurations.
method Proposes a fully Bayesian RATR framework using Optimal Bayesian Fusion (OBF) to aggregate classification probability vectors from multiple radars.
result Empirical results show that the OBF method significantly enhances classification accuracy compared to other fusion methods and single radar configurations.
Dual frame-rate system improves real-time perception for autonomous vehicles.
problem Conflicting requirement of safety and efficiency in real-time perception systems.
method Proposes a dual frame-rate system with a modulator stream for robust features and a prediction stream for transient signals.
result Consistent improvements across various backbone architectures and input resolutions.
Paper proposes a method to learn and exceed expert demonstrations in unknown reward environments.
problem Learning to outperform expert demonstrations in unknown reward environments.
method A novel concurrent reward and action policy learning approach with a stereo utility definition.
result The proposed method can outperform expert demonstrations in various environments.
Recent advances in adversarial Deep Learning (DL) have opened up a largely unexplored surface for malicious attacks jeopardizing the integrity of autonomous DL systems. With the wide-spread usage of DL in critical and time-sensitive applications, including unmanned vehicles, drones, and video surveillance systems, onli…
Paper presents a statistical method for detecting adversarial inputs.
problem Adversarial attacks on deep learning models.
method Statistical approach based on per-class feature distribution comparison.
result Approach achieves good adversarial detection performance on MNIST and CIFAR-10 datasets.
The densification of small-cell base stations in a 5G architecture is a promising approach to enhance the coverage area and facilitate the ever increasing capacity demand of end users. However, the bottleneck is an intelligent management of a backhaul/fronthaul network for these small-cell base stations. This involves …
AMS improves video inference on edge devices by adapting a small model with online knowledge distillation.
problem High computation cost of Deep Neural Networks for real-time video inference on edge devices.
method AMS uses a remote server to continually train and adapt a small model on edge devices, using online knowledge distillation from a large model.
result 0.4--17.8 percent mean Intersection-over-Union improvement in video semantic segmentation.
End-to-end multi-object tracking learns object interactions.
problem Object tracking ignores interactions between objects.
method End-to-end relational reasoning model MOHART.
result Relational reasoning improves tracking and prediction.
New method recovers compressed crack images for automatic segmentation.
problem Recover crack images from compressed data for SHM systems.
method Generative model-based CS method for crack images.
result Generative model effectively captures crack features for segmentation.