A new method for marine robot navigation using sparse Gaussian Process TD learning.
problem Data efficiency and online prediction challenges in marine robot navigation.
method Sparse Gaussian Process Temporal Difference (SPGP-TD) learning with a sparse approximation.
result SPGP-SARSA outperforms state-of-the-art sparse methods and replicates exact prediction quality.
Novel hybrid model combines image feature discovery and topic modeling for marine robot mission data.
problem Insufficient analysis of robot mission data due to data complexity and lack of suitable models.
method Convolutional autoencoders for feature discovery in images and Bayesian nonparametric topic models for thematic structure.
result Hybrid model outperforms state-of-the-art approaches in unsupervised seafloor terrain characterization.
The paper improves marine buoy placement to detect ships robustly against disruptions.
problem Detecting fishing vessels in the presence of natural and man-made disruptions.
method Formulated as a clustering problem, used dropout k-means and k-median to improve buoy placement robustness.
result Improved ship detection probability with dropout k-means compared to classic methods.
The paper develops sampling methods for ocean phenomena based on temperature and salinity measurements.
problem Improving oceanographic sampling with limited resources.
method Design criterion based on uncertainty in excursions of vector-valued Gaussian random fields.
result Demonstrates effective exploration of ambiguous regions for data-driven sampling.
Deep learning model detects and classifies marine microfossils.
problem Manual identification of microfossils is time-consuming and error-prone.
method Transfer learning from ImageNet dataset to classify foraminifera.
result Proposed model achieves high accuracy on foraminifera classification.
ConvNet classifies whale vocalizations and ambient noise in acoustic recordings.
problem Automated detection and classification of marine mammal vocalizations in acoustic recordings.
method Convolutional Neural Network with a novel acoustic representation.
result Classifier accurately detects and classifies whale vocalizations and ambient noise.
Framework improves marine mammal monitoring in noisy underwater environments.
problem Underwater bioacoustic monitoring challenges due to overlapping calls and variable noise.
method Multi-step attention-guided framework with segmentation and mid-level fusion.
result Improved signal discrimination, reduced false positives, reliable representations.
A Deep Zero-Inflated Model for Detecting North Atlantic Right Whale Presence
problem Balancing marine conservation and blue economy management
method Deep Zero-Inflated Bernoulli model
result Improved model adequacy and predictive performance
New method predicts VIV in 3D currents for marine risers.
problem Uncertainty in predicting VIV due to 3D current effects.
method Data-driven modeling using random forest regression.
result Data-driven method outperforms traditional models in 3D current conditions.
Machine learning models predict bluebottles' presence on beaches, addressing class imbalance and unreliable absence data.
problem Predicting bluebottles' presence on beaches with machine learning, tackling class imbalance and unreliable absence data.
method Used Multilayer Perceptron, Random Forest, and XGBoost models; employed data augmentation techniques like SMOTE, Random Undersampling, and Synthetic Negative Approach.
result Random Forests combined with Synthetic Negative Approach provided the best predictive model, identifying wind direction as a key factor.
This paper compares supervised learning methods for identifying phytoplankton species.
problem Identifying phytoplankton species due to their variability and ambiguity.
method Proposed a new features type from raw signals and compared various classifiers.
result Random Forest using the proposed features gave the best classification results with 98.24% accuracy.
Hybrid AI methods optimize renewable energy and facilities management.
problem Optimizing renewable energy resources and facilities management in oceanic engineering and airports.
method Hybrid neuro-evolutionary algorithms and machine learning.
result Proposed methodologies for predicting key parameters in renewable energy and facilities management.
Completes results on complex braid group parabolic subgroups.
problem Proves properties of complex braid group parabolic subgroups.
method Uses Garside groupoid structure of B(G31) to extend results.
result Proves main theorems for B(G31) parabolic subgroups.
For a non-orientable closed surface standardly embedded in the 4-sphere, a diffeomorphism over this surface is extendable if and only if this diffeomorphism preserves the Guillou-Marin quadratic form of this embedded surface.
YOLOv3 detects ships in real-time with high accuracy.
problem Real-time target detection in maritime scenarios.
method YOLOv3 model trained on a large dataset of marine vessels.
result Average Precision up to 96% for IoU of 0.5.
This study uses RNNs to diagnose faults in underwater thrusters.
problem Fault detection and diagnosis of underwater thrusters in harsh marine environments.
method Data-driven fault detection using Recurrent Neural Networks (RNNs) with empirical data.
result RNNs outperform residual-based feature extraction for fault classification.
Extends Shifts dataset for MS lesion segmentation and marine vessel power estimation.
problem Distributional shift in training and deployment data for ML models.
method Develops new datasets for high-risk industrial applications.
result Demonstrates robustness and uncertainty estimation in new industrial tasks.
P. Arnoux and A. Marin showed that any triangulation of RPn contains more than 2(n+1)(n+2) vertices if n≥3. We construct some natural triangulation of RPn with 2n(n+5)−1 vertices for all n≥3. Previously, it was known that RPn has Z2n-e…
Automates decision-making for human operators managing multiple robots.
problem Limited human operator attention when controlling multiple robots.
method Learned model of user preferences from easy settings to automatically identify the most critical robot.
result Automated decision-making can assist human operators in managing more robots than their attention allows.
Machine learning monitors detect motor overheating, adapting to concept drift.
problem Early detection of motor overheating in ships' propulsion systems.
method Machine learning and statistical methods using historical data to adapt to concept drift.
result The proposed monitors provide early detection of overheating during and after concept drifts.
5 homogeneous convex foliations of degree 4 found on complex projective plane.
problem Classifying reduced convex foliations on complex projective plane.
method Analyzing homogeneous foliations of degree 4.
result 5 homogeneous convex foliations of degree four identified.
The paper studies embedding finite groups in specific quotient spaces.
problem Embedding finite groups in quotient spaces of Artin and pure braid groups.
method Analyzes conditions for embedding finite groups in Bn/Γk(Pn), proving necessary conditions and constructing explicit embeddings. result Finite groups of odd order embed in Bn/Γ2(Pn) and Bn/Γ3(Pn), extending previous results. Flexible XVAE model for efficient spatial extremes simulation.
problem Complex tail dependence structures in spatial extremes processes.
method Variational autoencoder (XVAE) for modeling flexible and non-stationary dependence.
result XVAE provides fast inference and outperforms traditional models in high dimensions.
Robotics: Rolling robots on a moving platform can be controlled.
problem Controlling the motion of rolling robots atop a moving platform.
method Developed a mathematical model and demonstrated simulations.
result Platform acceleration can control robot's heading and motion.
Robots learn to handle complex tasks creatively using DRL.
problem Robotic manipulation challenges and intelligence.
method Designing challenging manipulation tasks, applying DRL for robot training.
result Robots exhibit creative and non-intuitive problem-solving.
Robot learns sensorimotor relationships through exploration.
problem Autonomous acquisition of sensorimotor contingencies by robots.
method Developmental framework encoding predictive models of sensorimotor experience.
result Robot discovers the environment, objects, and visual field through internal encoding of sensorimotor contingencies.
ROBEL platform accelerates reinforcement learning with low-cost robots.
problem Accelerating reinforcement learning research in robotics.
method Open-source platform of cost-effective robots for real-world reinforcement learning.
result Robots D'Claw and D'Kitty facilitate learning dexterous manipulation and agile locomotion tasks.
Robot learns human interaction skills through multimodal deep reinforcement learning.
problem Developing robots with human-like social interaction skills.
method Multimodal Deep Q-Network (MDQN) for end-to-end reinforcement learning.
result Robot successfully learned basic interaction skills after 14 days of interaction.
New method improves smoothness of robot learning.
problem Jerky motion patterns on real robots from Deep RL exploration.
method Adapting state-dependent exploration to Deep RL algorithms with gSDE.
result Improved exploration and performance on real robots.
Dreaming model enables robots to learn policies from images.
problem Learning to control robots based on images is challenging.
method Learning a future representation/scene regressor conditioned on robot actions.
result Dreaming model enables policy learning that transfers to real-world.
This review assesses statistical and machine learning methods for coral bleaching.
problem Coral bleaching due to rising sea temperatures and environmental factors.
method Statistical and machine learning models for predicting and analyzing coral bleaching.
result Statistical and machine learning methods are crucial for effective reef management.
Robots learn to navigate rough terrain using reinforcement learning.
problem Generalizing robot behavior to new, unseen rough terrains.
method PPMC RL Training Algorithm
result Robots achieve 100% success rate in learning new rough terrain maps.
Robots gather information resiliently despite failures and attacks.
problem Resilient information gathering in adversarial or failure-prone environments.
method First scalable algorithm for minimal communication, system-wide resiliency, and provable approximation performance.
result Algorithm ensures optimal or near-optimal solutions for any number of failures and attacks.
A new framework for robot block-stacking tasks using causal probabilistic models.
problem Robots fail outside controlled environments due to uncertainty and lack of explicit design for all scenarios.
method Causal probabilistic framework combining causal models and probabilistic representations of noise.
result Robots can perceive, reason about, and explain their environment for block-stacking tasks.
Robot learns to interact naturally with humans through neural attention.
problem Developing a robot that can respond to complex human behaviors in a natural way.
method Multimodal Deep Attention Recurrent Q-Network trained using reinforcement learning.
result The robot learned to respond to human behaviors in a perceivable and socially acceptable manner.
This research evaluates learning models for bionic robots, focusing on transfer function identification.
problem Developers need guidance on selecting and constructing transfer functions for bionic robots.
method Comprehensive evaluation strategy including data collection, learning model selection, comparative analysis, and transfer function identification.
result A framework for effectively dealing with multi-input multi-output robotic data.
Study improves reliability of reinforcement learning with real-world robots.
problem Difficulty in setting up reinforcement learning tasks with real-world robots.
method Developed a learning task with a UR5 robotic arm to study task setup.
result Learning performance is highly sensitive to task setup details.
Robots learn conservatively from human corrections, avoiding unintended changes to their objectives.
problem Robots learn from human corrections but may not align with the intended objectives due to misspecified hypothesis spaces.
method Robots reason in real-time about the relevance of human corrections to their hypothesis space, learning more conservatively.
result Robots can avoid unintended learning from human corrections, improving alignment with intended objectives.
A new Q-learning controller improves line follower robot control.
problem Challenges in controlling line follower robots due to unknown mechanical characteristics and uncertainties.
method Simulated annealing based Q learning method to address controller performance issues.
result The proposed controller outperforms conventional P controllers in line follower robots.
Neuro-robotics model shows gestures improve counting ability.
problem Improving counting ability in robots and children.
method Introduces a neuro-robotics model trained with pointing data, tests various model and training conditions.
result Model's performance aligns with human children's learning to count.
Paper addresses hypothesis space misspecification in learning from human demonstrations and corrections.
problem Hypothesis space misspecification in learning from human demonstrations and corrections.
method Reason explicitly about how well the robot can explain human inputs given its hypothesis space.
result Demonstrates method on a 7 DOF robot manipulator.
Controller stabilizes spherical robot's position and line-of-sight.
problem Stabilizing a spherical robot's position and line-of-sight.
method Geometric control law with feedforward and proportional-derivative control.
result Controller performance validated through simulations.
Paper develops a neural-fuzzy controller for GPS-intelligent buoys.
problem Optimally track dynamically positioned marine buoys with unknown parameters.
method Dynamic system modeling using neural-fuzzy networks with backstepping technique.
result The controller minimizes position errors and adjusts buoy positions accurately.
Robot learns agile leg movements from simulations to real robots.
problem Training legged robots for dynamic maneuvers is challenging and expensive.
method Simulation-based reinforcement learning for real legged systems.
result ANYmal robot can follow high-level commands, run faster, and recover from falls.
This work tackles force control for contact-rich manipulation tasks with rigid robots using RL.
problem Challenges in working with real robotic hardware, especially position-controlled robots.
method Combines RL with traditional force control techniques, implementing parallel position/force control and admittance control.
result Validated methods on both simulation and real robot (UR3 e-series) for force control.
The paper learns robot skills from demonstrations without supervision.
problem Discovering robotic options from unlabelled demonstrations.
method Temporal variational inference for latent variable learning.
result The framework can learn options across multiple datasets.
Robot learns tool use from effects, detecting features of tools, objects, and actions.
problem Teaching robots to understand and manipulate objects using tools.
method Deep learning model trained on sensory-motor data from a robot performing a tool-use task.
result Robot can detect features of tools, objects, and actions from effects of object manipulation.
Study aims to develop a humanoid robot dialogue system.
problem Current dialogue systems lack attention to non-verbal cues.
method Participated in a competition to develop a system with facial expressions and gaze control.
result Developed a humanoid robot dialogue system.