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.
Deep learning enables a robot to navigate autonomously within a perimeter.
problem Autonomous path planning for space exploration robots.
method Deep reinforcement learning with randomized reward function parameters.
result Trained robot can navigate to any point within a perimeter without prior knowledge.
Paper estimates area covered by a line-sweep sensor in robotics.
problem Accurately estimating the area covered by a line-sweep sensor.
method Relies on coverage measure and topological degree in the plane.
result Guaranteed characterization of the explored area using interval analysis.
A decentralized routing framework for lunar exploration robots.
problem Routing data in intermittent connectivity lunar networks.
method Graph Attention-based Multi-Agent Reinforcement Learning (GAT-MARL).
result Higher delivery rates, no duplications, fewer packet losses.
Robots adapt to damage with a single policy and diagnosis.
problem Robotic failure due to damage during mission-critical tasks.
method Damage-aware control architecture using supervised learning for diagnosis and policy adaptation.
result Single-shot diagnosis and adaptation achieved with a single policy.
Framework allows organizations to collaborate on learning tasks securely.
problem Limited collaboration due to security constraints.
method Assisted Learning framework for supervised learning tasks.
result Near-oracle learning performance achieved without revealing sensitive information.
MISSION selects features for large datasets efficiently and interpretably.
problem Feature selection challenges in ultra large-scale datasets.
method MISSION uses Count-Sketch data structure for stochastic gradient descent.
result MISSION accurately and efficiently selects features on large-scale datasets.
Defines data science as a natural ecosystem with challenges and missions.
problem Challenges and missions in data science due to 5D complexities and data life cycle phases.
method Systemic and data-centric view of data science as a fusion of data universe and its challenges, formalizing a general-purpose architecture.
result Essential data science as a natural ecosystem integrating specific disciplines and high-impact applications.
Cyber-physical systems, such as mobile robots, must respond adaptively to dynamic operating conditions. Effective operation of these systems requires that sensing and actuation tasks are performed in a timely manner. Additionally, execution of mission specific tasks such as imaging a room must be balanced against the n…
New method disentangles sources of different timescales in planetary seismic data.
problem Unsupervised source separation of multi-scale seismic data from planetary missions.
method Wavelet scattering spectra for multi-scale clustering and variational autoencoder for source separation.
result Disentangles sources with different timescales in InSight mission seismic data.
Optimizes variational autoencoder for detecting missing data in Mars rover transmissions.
problem Detecting missing data in Mars rover transmissions to prevent volume loss and corruption.
method Applies derivative-free optimization to tune variational autoencoder.
result Improves variational autoencoder's ability to detect missing data, aiding GDSA team.
Python tool creates machine-learning-ready solar dataset.
problem Creating a usable dataset for space weather forecasting.
method Python tool generates dataset from SoHO and SDO images, applying pre-processing.
result Dataset is machine-learning ready, free of missing data, and temporally synced.
This research integrates human interaction into reinforcement learning to improve sample efficiency and real-time learning.
problem Current reinforcement learning requires thousands of samples to converge, and is prone to catastrophic failures.
method Integrates human interaction modalities (demonstrations, interventions, evaluations) into the reinforcement learning loop.
result Human interaction accelerates learning and improves sample efficiency.
Machine learning improves planetary space physics by incorporating physical knowledge.
problem Improving performance and interpretability of machine learning models for planetary space physics.
method Building on a previous semi-supervised physics-based classification, the team used varying data and physical information to improve machine learning performance and interpretability.
result Incorporating physical knowledge improves machine learning performance and interpretability, essential for deriving scientific meaning.
MC-pix2pix generates high-quality synthetic sonar data for ATR systems.
problem Generating realistic synthetic sonar data for ATR systems.
method Markov Conditional pix2pix (MC-pix2pix) method.
result MC-pix2pix-generated data is almost indistinguishable from real sonar data.
Investigates the limits of cost-sensitive classification problems.
problem Cost-sensitive classification problem in mission-critical applications.
method Extending the minimax lower bound of balanced binary classification problem.
result Cost terms significantly impact the hardness of the problem.
The kind of realized mission inflows the sensitivity to risk. Among other factors, the risk results from decision about liquid assets investment level and liquid assets financing. The higher the risk exposure, the higher the level of liquid assets. If the specific risk exposure is smaller, the more aggressive could be …
This paper proposes using neural network sentiment measures to prioritize test inputs.
problem High cost of obtaining test oracle data limits testing efficacy of neural networks.
method Proposes using confidence, uncertainty, and surprise measures to prioritize test inputs.
result Sentiment measures can effectively flag inputs revealing DNN weaknesses.
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.
Robots learn material recognition from unlabeled data using GANs.
problem Difficulties in collecting labeled training data for robots.
method Semi-supervised learning with GANs for haptic features.
result Achieves ~90% accuracy in material estimation with 92% unlabeled data.
Reinforcement Learning optimizes low-thrust interplanetary trajectories under disturbances.
problem Designing robust interplanetary trajectories in the presence of disturbances.
method Reformulated as a Markov Decision Process, RL algorithm Proximal Policy Optimization trained on a deep neural network.
result Deep neural network provides robust nominal trajectory and guidance law.
Robot learns from human actions to perform complex tasks.
problem Learning complex skills from interaction data with embodiment differences.
method Formulated graphical model, treated action as observed variable, used domain-dependent prior.
result Robotic planning agent can learn tool use from human observations.
LIQSS method improves accuracy and efficiency for power system simulations.
problem Accurately modeling and simulating long-duration mission profiles of Naval power systems.
method Linear Implicit Quantized State System (LIQSS) method for stiff, nonlinear, differential algebraic equations.
result LIQSS1 method yields results within 1% accuracy of continuous methods and increases efficiency logarithmically with quantization size.
ORIL learns a reward function from unlabeled data to improve robot learning.
problem Leveraging unlabeled data for robot learning.
method ORIL learns a reward function from demonstrator and unlabeled trajectories, annotates data, and trains an agent via offline reinforcement learning.
result ORIL consistently outperforms BC agents on various robotic tasks.
Transfer learning improves dynamic model transfer for soft robotic hands.
problem Improving dynamic model transfer for underactuated soft robotic hands.
method Derive an upper bound on the Lyapunov exponent and use it to improve transfer.
result Significant improvement over traditional fine-tuning methods.
Differentiable Algorithm Networks (DAN) enable composable robot learning.
problem Training robots to learn from limited data and imperfect models.
method Composable architecture of neural network modules, each encoding a differentiable robot algorithm and model, trained end-to-end from data.
result DAN modules adapt to one another and compensate for imperfect models and algorithms, achieving best overall system performance.
Robots learn new tasks autonomously with minimal human intervention.
problem Lack of scalable data collection for robot learning.
method Multi-task imitation learning with autonomous data collection and one-shot generalization.
result Robots can continuously improve through autonomous data collection without reinforcement learning.
Novel path planning improves UAV detection of extreme anomalies.
problem Improper criteria for UAV anomaly detection.
method Mathematical criteria guiding UAV towards strong anomalies.
result Proposed approach outperforms traditional methods in various applications.
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.
Robotic clothing manipulation improved with fashion image analysis techniques.
problem Automated identification of clothing categories and landmarks for robotic tasks.
method Training data augmentation methods and rotation invariant convolutions.
result Our approach outperforms state-of-the-art models on unseen datasets.
Diffusion models enhance robotic manipulation through probabilistic multi-modal learning.
problem Enhancing robotic manipulation through robust and multi-modal learning.
method Probabilistic diffusion models integrating imitation and reinforcement learning.
result Diffusion models improve grasp learning, trajectory planning, and data augmentation in robotics.
A new optimizer d-AmsGrad improves deep learning for robot learning in non-stationary problems.
problem Noise and outliers in real-world data make deep learning challenging for robot learning.
method Proposed an improved version of AmsGrad optimizer that slowly decays the maximum second momentum to adapt to non-stationary problems.
result The new optimizer outperformed baseline optimizers in robotics problems.
Study detects anomalies in robot vision data to predict hazards.
problem Detecting unexpected hazards in robot exploration data.
method Anomaly detection using autoencoders at different scales.
result Autoencoders improve anomaly detection performance on diverse robot scenarios.
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.
Robot learns to imitate human interactions through deep learning.
problem Teaching robots to coordinate actions with human partners.
method Deep learning framework for motion embedding, prediction, and trajectory generation.
result Importance of predictive and adaptive components for successful imitation.
Developed a simulator and dataset for deep learning in robotic grasping.
problem Lack of sufficient data for deep learning in robotic grasping.
method Created a simulator and dataset for precise cylindrical grasps.
result Demonstrated the feasibility of deep learning for robotic grasping.
Robot learns to dress people safely using deep learning.
problem Robots lack common sense about physical interactions with clothing.
method Deep recurrent model predicts garment forces, used with MPC.
result Robot can better assist in dressing without high forces.
Researchers develop multi-agent systems for quadcopters to collaborate in missions.
problem Enable multiple quadcopters to work together in remote sensing tasks.
method Agent dynamics, network topologies, collective behaviors, agreement protocol, equations of motion for quadcopters.
result Multi-agent systems can successfully collaborate in remote sensing missions.
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.
Survey on algorithms for quick robot learning.
problem Efficiently learn robot controllers with limited data.
method Leverage prior knowledge and data-driven models.
result Combining prior knowledge and surrogate models improves learning.
Paper presents a method for efficient robot adaptation using fine-tuning.
problem Continuous adaptation of robot learning systems in real-world scenarios.
method Fine-tuning previously learned policies using off-policy reinforcement learning.
result Fine-tuning leads to substantial performance gains and adaptation to new conditions.
Deep RL for wheel-legged robots in complex environments.
problem Mobile robot navigation in complex and dynamic environments.
method Deep reinforcement learning to map height-map observations to motor commands.
result Significant improvement in data-efficiency, success rate, robustness, and maneuver quality.
Study classifies surface types for autonomous indoor robots using inertial data.
problem Classifying surface types for wheeled robots in indoor environments.
method Prepared a time series dataset of inertial measurements, used deep learning and ensemble machine learning models.
result Baseline model achieved over 68% accuracy on a nine-category surface type dataset.
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.
Paper learns robot's end-effector position without prior info.
problem Lack of prior robot structure or sensor info.
method Generates internal end-effector config from raw data.
result Can control robot without prior kinematic info.
Central to robot exploration and mapping is the task of persistent localization in environmental fields characterized by spatially correlated measurements. This paper presents a Gaussian process localization (GP-Localize) algorithm that, in contrast to existing works, can exploit the spatially correlated field measurem…
A robot learns environmental fields using physics-based models and Bayesian methods.
problem Accurately learning complex environmental fields from limited robot measurements.
method Bayesian framework with Gaussian processes to select and update physics-based models in real-time.
result The robot's learned flow field approximates real flow better than prior solutions and data-driven methods.
New algorithm scales model-based policy search for robotics to high-dimensional systems.
problem Inefficient scaling of model-based policy search algorithms in high-dimensional state/action spaces.
method Introduces parameterized black-box priors to scale up model learning and improve robustness to prior inaccuracies.
result Significantly more data-efficient than previous algorithms, learning gaits in 16-30 seconds.