Paper explores deep learning for translating motor imagery to robotic grasp synthesis.
problem Challenges in equipping machines with the ability to grasp objects based on sensory information.
method Investigates deep conditional generative models for learning integrated object-action representations.
result Demonstrates the capacity of generative models to capture and generate multimodal, multi-finger grasp configurations.
QT-Opt learns dynamic grasping strategies for robots.
problem Learning dynamic grasping for robots in real-world settings.
method Scalable self-supervised vision-based reinforcement learning.
result 96% grasp success on unseen objects with real-world learning.
Robot learns to grasp and adjust using vision and touch.
problem Robotic grasping relies solely on visual input, missing tactile feedback.
method End-to-end action-conditional model that learns from visuo-tactile data.
result Model predicts grasp adjustment outcomes and selects efficient actions.
Touch sensing improves grasp prediction accuracy.
problem Predicting grasp outcomes from indirect measurements like vision is challenging.
method Investigated touch sensing's value in multimodal grasping using visuo-tactile deep neural networks.
result Tactile readings significantly improve grasp prediction accuracy.
End-to-end learning for robot grasping using image data.
problem Robotic grasping using only monocular images.
method Two-stream architecture: ventral stream for object detection and classification, dorsal stream for grasp planning.
result End-to-end trained model outperforms non-end-to-end systems.
Enhanced GQ-CNN boosts robot grasp accuracy.
problem Improving grasp success rates for unknown objects.
method Proposed a new GQ-CNN architecture with practical improvements.
result Validation accuracy increased from 92.2% to 95.8% and from 85.9% to 88.0%.
TOG-Net optimizes grasping for tool manipulation in simulated self-supervised learning.
problem Optimizing grasping for tool manipulation in robots.
method Simulated self-supervised learning with Task-Oriented Grasping Network (TOG-Net).
result Achieved 71.1% task success rate for sweeping and 80.0% for hammering.
Robotic grasping improved using evolutionary computing and deep reinforcement learning.
problem Developing a robot capable of grasping objects as skillfully as humans.
method Position estimation using Genetic Algorithm and regression, orientation learning using deep reinforcement learning.
result Deep reinforcement learning model outperforms traditional methods for orientation learning.
Paper presents a semi-supervised grasp detection method using VQ-VAE.
problem Robotic grasp detection difficulty due to insufficient labelled data.
method Semi-supervised learning with VQ-VAE in a latent space.
result Model performs better than existing approaches using unlabelled images.
Graph neural network predicts grasp stability from tactile sensor data.
problem Predicting grasp stability from tactile sensor data.
method Graph Convolutional Network (GCN) trained on tactile sensor data.
result Graph neural network effectively predicts grasp stability.
Improved RL for grasping in cluttered scenes using state representation learning.
problem Poor performance of RL methods in grasping diverse objects from raw images.
method Employed state representation learning (SRL) with disentanglement of raw input images.
result Deep RL can learn grasping skills from varied visual inputs.
Robotic manipulation learns synergies between pushing and grasping from scratch.
problem Discovering complex synergies between pushing and grasping for efficient robotic manipulation.
method Self-supervised deep reinforcement learning with two convolutional networks.
result System learns pushing and grasping motions that improve picking success rates and efficiency.
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.
Study evaluates deep RL methods for robotic grasping, focusing on off-policy learning.
problem Identify the best deep RL methods for vision-based robotic grasping.
method Proposed a simulated benchmark for grasping tasks, evaluating Q-function estimation, Monte Carlo return, and off-policy correction methods.
result Several simple methods outperform popular algorithms like double Q-learning.
Robotic grasping system learns to target objects from a single image.
problem Robotic grasping in unstructured environments.
method Distributed reinforcement learning, active vision, synchronous SGD.
result System learns to grasp unseen objects without retraining.
Deep RL learns grasping from 2.5D images.
problem Grasping objects from 2.5D images.
method Deep Reinforcement Learning (DRL) in a simulated environment.
result Successfully learned grasping from 2.5D images.
TossingBot learns to throw objects accurately with residual physics.
problem Learning to throw arbitrary objects accurately and quickly.
method End-to-end formulation that learns control parameters from visual observations.
result TossingBot achieves 600+ grasps per hour with 85% throwing accuracy.
GRASP simplifies Bayesian regression with grouped predictors using an adaptive NBP prior.
problem Regression with grouped predictors and adaptive shrinkage.
method Normal Beta Prime (NBP) prior with tunable hyperparameters for flexible sparsity control.
result Empirical validation of robust and versatile GRASP across various sparsity and signal-to-noise ratios.
Enhances robotic grasping efficiency with learning-adaptive imagination.
problem Improving sample efficiency and performance in robotic grasping tasks.
method Learning-adaptive imagination approach using ensemble of local dynamics models in latent space.
result Significantly improves sample efficiency and achieves near-optimal performance.
Robotic grasp stability improved with fingertip slippage detection.
problem Improving grasp stability in robotic manipulation.
method Task-relevant feature extraction and efficient classifier design for fingertip slippage detection.
result The proposed method effectively detects object slippage with fingertips in an online fashion.
Q2-Opt improves robot grasping success and efficiency.
problem Improving robot grasping success and efficiency in vision-based tasks.
method Quantile QT-Opt, a distributional variant of Q-learning for continuous domains.
result Q2-Opt achieves superior grasping success and is more sample efficient.
GRASP tests goodness-of-fit for binary classifiers without parametric assumptions.
problem Assessing the fit of a binary classifier to the underlying conditional law of labels given features.
method Formulates a tolerance hypothesis testing problem and proposes a novel test called GRASP.
result Proposes GRASP and Model-X GRASP tests for assessing goodness-of-fit in finite sample settings.
This paper improves robot grasping by integrating meta-control and latent-space imagination.
problem Dual-system approaches fail to consider the reliability of the learned model when making multiple-step predictions.
method A meta-controller arbitrates between model-based and model-free decisions based on local reliability, encouraging actions that improve the model and generating imagined experiences for additional training.
result Our approach learns near-optimal grasping policies in dense- and sparse-reward environments, outperforming baseline and state-of-the-art methods.
Data mining enhances a heuristic for the Minimum Latency Problem.
problem Finding optimal solutions for the Minimum Latency Problem efficiently.
method Combining GRASP with data mining to find frequent patterns in high-quality solutions.
result Improved solution quality and reduced computational time compared to existing methods.
GraSP-RL uses graph neural networks to improve job shop scheduling.
problem Capturing machine-unit-job sequence relationships and managing state space growth.
method Graph neural networks for feature extraction, reinforcement learning for decision-making, decentralized optimization.
result GraSP-RL outperforms existing methods in minimizing makespan for complex production environments.
TACTO simulates high-resolution touch sensing for robotics.
problem Accurate simulation of touch sensing in robotics.
method Fast, flexible, open-source simulator for vision-based tactile sensors.
result Demonstrated TACTO's effectiveness in grasping stability prediction and marble manipulation control.
Machine learning optimizes polymer fiber synthesis.
problem Complex material synthesis requires impractical experimentation.
method Bayesian optimisation using machine learning.
result Efficiently directs synthesis to achieve material and process objectives.
Tree-based synthesis improves forecast accuracy in GDP and inflation.
problem Improving forecast accuracy in GDP and inflation.
method Developed a nonparametric synthesis function using regression trees.
result Tree-based synthesis leads to improved forecast accuracy.
Speech synthesis from EEG features using RNN.
problem Speech synthesis from EEG data.
method Recurrent Neural Network (RNN) regression model to predict acoustic features from EEG features.
result Feasibility of synthesizing speech directly from EEG features demonstrated.
Neural model synthesizes music with flexible timbre controls.
problem Creating audio samples with varied timbres from musical scores.
method Recurrent neural network conditioned on learned instrument embedding followed by WaveNet vocoder.
result Learned embedding space captures diverse timbres and enables interpolation for morphing.
Dataset of human-written problem statements and solutions for program synthesis.
problem Creating programs from natural language problem descriptions.
method Crowdsourced problem statements and solutions from programming competitions.
result Best model achieved 8.8% accuracy, indicating high complexity.
PureTS uses simple linear models to improve long-term time series forecasting.
problem Improving long-term time series forecasting with complex models.
method Developed PureTS with three pure linear layers.
result PureTS achieves state-of-the-art performance in long sequence prediction tasks.
SED integrates synthesis, execution, and debugging for neural program synthesis.
problem Challenges in synthesizing complex programs that match specifications.
method SED combines synthesis, execution, and debugging to improve neural program generation.
result SED reduces error rates and outperforms standard decoding methods.
System uses machine learning and automated reasoning to speed up PBE synthesis.
problem Slow synthesis in PBE due to domain-specific knowledge and large training datasets.
method Preprocess SyGuS PBE problems with a neural network to reduce search space, then use automated reasoning for faster solution.
result System outperforms all competing tools in the 2019 SyGuS Competition for the PBE Strings track by 47.65%.
New RGraSP framework for efficient non-convex optimization.
problem Large-scale non-convex sparsity-constrained optimization problems.
method Relaxed gradient support pursuit with semi-stochastic gradient hard thresholding.
result Our algorithms converge faster with lower per-iteration cost.
WaveCycleGAN2 improves speech synthesis quality by reducing aliasing.
problem Human ear can still distinguish synthesized speech from natural speech.
method WaveCycleGAN2 uses generators without down/up-sampling modules and combines discriminators from waveform and acoustic parameter domains.
result WaveCycleGAN2 achieves high-quality speech synthesis with comparable mean opinion scores to natural speech.
Automated synthesis planning from scientific literature using AI.
problem Accelerate materials design and discovery by connecting scientific literature to synthesis insights.
method Word embeddings from language models, named entity recognition, conditional variational autoencoder.
result The model predicts precursors for perovskite materials using historical data.
Deep reinforcement learning optimizes retrosynthetic planning for chemical synthesis.
problem Optimizing chemical synthesis plans from molecular targets to simpler starting materials.
method Deep reinforcement learning to estimate synthesis costs and values of molecules.
result Trained neural networks outperform heuristic approaches in synthesizing unfamiliar molecules.
Improved visual speech synthesis using adapted ASR acoustic models.
problem Lack of synchronized audio, video, and depth data for speaker-independent speech-driven visual speech synthesis.
method Adapted an ASR acoustic model trained on audio-only data to the visual speech synthesis domain.
result Viewers significantly prefer animations generated from the adapted ASR acoustic model.
Spatial GAN improves texture synthesis quality and scalability.
problem Texture synthesis quality and scalability issues.
method Spatial Generative Adversarial Networks (SGAN) with extended noise distribution.
result High quality textures, scalability, real-time generation, and fusion of diverse images.
Generative model improves audio synthesis from TF features.
problem Challenges in generating high-quality audio from TF features.
method Used a GAN to generate invertible TF features from short-time Fourier transforms.
result Generated TF features from GAN outperformed direct waveform generation.
A neural program synthesis method with iterative fix operations.
problem Creating correct programs from input-output examples.
method Combines encoder-decoder synthesis with a differentiable fixer.
result Improves synthesis accuracy by reducing discrepancies between outputs and desired outputs.
New approach generates better synthetic data for neural program synthesis.
problem Current approaches to neural program synthesis generalize poorly to real data.
method Adversarial approach to control synthetic data distributions.
result Proposed method outperforms current approaches.
Framework synthesizes geological images minimizing patch distribution discrepancy.
problem Synthesizing realistic geological images from a single exemplar.
method Uses kernel discrepancies and generative neural networks for efficient synthesis.
result Synthesized images match visual patterns and spatial statistics of the exemplar.
Generative model creates realistic scenes from pixel-wise labels.
problem Creating photo-realistic scenes from pixel-wise labels.
method Semantic bottleneck GAN model combining conditional and unconditional generation networks.
result Model outperforms state-of-the-art models in unsupervised image synthesis.
Enhanced Tacotron for Japanese speech synthesis improves naturalness.
problem Challenges in end-to-end Japanese speech synthesis due to pitch accents.
method Extended Tacotron with self-attention to capture pitch accent dependencies.
result Proposed systems show improvements but still lag behind traditional pipeline methods.
We prove that spherical spectral analysis and synthesis hold in Damek-Ricci spaces and derive two-radius theorems.
Inverse Drum Machine separates drum mixes using transcription and synthesis.
problem Separating individual drum tracks from mixed recordings.
method Analysis-by-synthesis framework combining deep learning and automatic transcription.
result Separation quality comparable to supervised methods requiring isolated stems.