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.
Robot learns word meanings from perception-action tasks.
problem Language acquisition for robots.
method Affordance network with temporal co-occurrence of speech and actions.
result Robot forms useful word-to-meaning associations.
New method allows a robot to perceive space dimensions without prior knowledge.
problem Limitation of previous methods in perceiving space dimensions with small movements.
method Non-linear dimension estimation method.
result Robots can now perceive space dimensions with larger movements.
Approach to develop visual perception in robots through sensorimotor interactions.
problem Developing autonomous perception in robots.
method Sensorimotor contingencies theory applied to robot exploration and learning.
result Captured sensorimotor regularities in a predictive model for visual field discovery.
A robot learns to classify images with limited perception using a layered reinforcement learning approach.
problem Image classification for robots with partial perception.
method Three-layer architecture using deep reinforcement learning, including meta-layer, action-layer, and classification-layer.
result The method achieves high accuracy on the MNIST dataset and provides explainability of the agent's decision-making process.
End-to-end method for robot localization in simulated and real environments.
problem Generating robot actions to maximize pose disambiguation in a reference map.
method Differentiable learning of perception and planning modules, using convolutional neural networks and deep reinforcement learning.
result The system outperforms traditional approaches for perception or planning.
STM maps improve terrain perception for autonomous robots.
problem Perception of terrain for autonomous robots in general environments.
method Stochastic triangular mesh (STM) technique for 2.5-D surface mapping.
result STM maps are more accurate than standard elevation maps.
Y-GAN uses multi-camera data to estimate depth maps without expensive hardware.
problem Depth perception for autonomous systems requires accurate 3D spatial information.
method Proposes Y-GAN, a deep convolutional generative adversarial network.
result Y-GAN estimates depth maps from multi-camera stereo images without ground truth data.
Machine learning enhances autonomous systems, especially perception modules.
problem Manual procedures based on prior knowledge are still used in robotics.
method Exploiting recent advances in computing, data, and models for learning.
result Learning is gaining importance in perception modules of autonomous systems.
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.
A robot learns object categories using multimodal data and selects actions efficiently.
problem Efficiently recognize object categories using multimodal data in real-time.
method Multimodal Hierarchical Dirichlet Process (MHDP) with information gain maximization and lazy greedy algorithm.
result The method selects actions that allow quick and accurate recognition of target objects.
This work creates a system for understanding human movement in spaces.
problem Simplify communication and interaction between robots and humans in spatial tasks.
method Uses unsupervised learning with neural autoencoding to learn continuous representations of spatio-temporal trajectory data.
result Proposes a method to form prototypical representations of movement based on spatial context.
This thesis models and approximates pose distributions in robot perception using quaternion and Gaussian methods.
problem Modeling and approximating probability distributions of poses in robot perception.
method Uses dual quaternions, unit quaternions, and Gaussian distributions to represent and approximate pose distributions.
result A framework for probabilistic modeling of poses in S3imesR3 that approximates various probability distributions. Robust collision prediction for robots using generative uncertainty.
problem Robots need to predict collisions safely in unexpected situations.
method Combines generative modeling and model uncertainty to handle out-of-distribution inputs.
result Improves collision prediction performance, especially for out-of-distribution inputs.
Robots learn spatial perception from sensorimotor invariants.
problem Developing autonomous robots that perceive space without human intuition.
method Study how a robot's motor commands relate to changes in exteroceptive inputs to deduce its spatial configuration.
result Robots can learn the configuration space of their sensors, revealing a planar position and orientation.
This paper bridges outlier-robust estimation in robotics and computer vision with robust statistics.
problem Outlier-robust estimation for geometric perception in robotics and computer vision.
method Adapting and extending robust linear regression and list-decodable regression to non-convex domains and vector-valued measurements.
result Performance guarantees for modern estimation algorithms in the presence of outliers.
Study how actions affect perception in embodied agents using group theory.
problem Understanding how actions influence perception in autonomous agents.
method Mathematical formalism of group theory applied to sensory commutativity of action sequences.
result Introduced Sensory Commutativity Probability (SCP) to measure action effects on perception.
New framework learns robot tasks quickly from simplified simulations.
problem Long training times and variable-length inputs in RL.
method Combines deep sets encoding with modular RL.
result Effective policies learned in minutes from simplified simulations.
Proposes Gaussian Processes for more accurate time-correlated measurement noise in robotics.
problem Time-correlated measurement noise in robotics applications.
method Gaussian Processes as a non-parametric model for correlated measurement noise.
result Improved performance of Kalman filtering with Gaussian Processes.
Paper tackles robust spatial perception by handling outliers efficiently.
problem Robust spatial perception is challenged by incorrect data association (outliers).
method Proposes adaptive trimming algorithm to remove outliers efficiently.
result Adaptive trimming algorithm outperforms state-of-the-art methods across applications.
This work tackles real-world robotic reinforcement learning challenges.
problem Limited success of reinforcement learning in real-world robotics.
method Proposes a system for autonomous real-world learning without instrumentation.
result Demonstrates a complete system that learns without human intervention.
Robot framework identifies unknown objects from symbolic descriptions.
problem Processing unmodeled objects in unstructured environments.
method Discriminative probabilistic model interpreting symbolic descriptions.
result Improved identification performance through ensemble learning.
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.
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.
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.
Machine learning assesses surgical skill in robotic-assisted surgery.
problem Subjective evaluation of surgeon skill in robotic-assisted surgery.
method Machine learning applied to six movement features for classification.
result Framework classifies surgical skill with 85.7% accuracy.
Robotic learning without reward engineering from images.
problem Manual reward engineering for reinforcement learning in robotics.
method Learning from examples and active solicitation of labels.
result Efficient learning of robotic skills from images without manual rewards.
Robots learn state representation from demonstrations.
problem Robots need a compact state representation for efficient interaction.
method Imitation learning using a multi-head neural network.
result Trained representation improves performance and efficiency in reinforcement learning.
Bayesian uncertainty from deep learning improves robot safety in unknown areas.
problem Improving robot safety in unknown or dangerous environments.
method Bayesian approximations of uncertainty from deep learning in a robot planner.
result Incorporating uncertainty leads to 18% less risky paths.
This paper evaluates various representations for robotics tasks, improving performance in lifting, stacking, and pushing.
problem Improving data-efficiency in reinforcement learning for robotics with limited data.
method Systematic evaluation of common representations in three robotics tasks: lifting, stacking, and pushing.
result Some representations can perform as well as simulator states as agent inputs, challenging common intuitions.
MGpi model predicts social actions in group interactions.
problem Social interaction among multiple agents and groups.
method Deep neural network with Kinesic-Proxemic-Message gate for social signal gating.
result Achieves state-of-the-art performance in group identification.
This paper shows that explicitly learning motion improves reinforcement learning in dynamic environments.
problem Learning controllers for dynamic environments without explicit motion representation.
method Explicitly learning motion representation using image difference or temporal stacks of frames.
result Explicit motion learning improves the quality of learned controllers in dynamic scenarios.
Hybrid RL combines simulated and real data for robust autonomous flight.
problem Challenges in training deep RL models for real-world robotic tasks.
method Combines real-world and simulated data to improve generalization.
result Quadrotor avoids collisions using only a monocular camera.
SELD-TCN improves sound event localization and detection efficiency.
problem Efficient sound event localization and detection on embedded hardware.
method Developed a novel temporal convolutional network (TCN) architecture.
result SELD-TCN outperforms state-of-the-art SELDnet on four datasets.
MIRO learns robust latent spaces by maximizing mutual information with future information.
problem Robust perception in complex, unstructured environments with low sample complexity.
method MIRO maximizes mutual information in a latent space for model-based reinforcement learning.
result MIRO outperforms reconstruction objectives in cluttered scenes.
Mixed likelihood GPs improve model performance in human-in-the-loop experiments.
problem Lack of auxiliary information in traditional GPs for human responses.
method Propose mixed likelihood variational GPs to leverage auxiliary information.
result Modeling performance improvements across diverse applications.
New CNN approach reduces overconfidence in object classification predictions.
problem Overconfident predictions from deep models, especially SoftMax layer.
method Introduces CNN probabilistic approach using Logit layer for Bayesian inference.
result Proposed approach shows promising performance compared to SoftMax.
PCI combines perception and control using Bayesian inference with object-based representations.
problem Separate perception and control in reinforcement learning.
method Joint Perception and Control as Inference (PCI) framework with Object-based Perception Control (OPC).
result OPC achieves good perceptual grouping quality and outperforms baselines in accumulated rewards.
Study the tradeoff between signal distortion and human perception over finite channels.
problem Characterize the distortion-perception tradeoff for finite channels with arbitrary metrics.
method Solve linear programming problems to compute the distortion-perception function and optimal reconstructions.
result DP function is piecewise linear in the perception index.
The paper uses Bayesian Surprise to identify unexpected structures in indoor environments.
problem Identifying unexpected structures in indoor environments.
method Bayesian Surprise applied to Isovist Analysis of 2D floor plans.
result Surprise regions in indoor environments can be used to focus on important areas in LBS.
LipKernel adds robustness to CNNs by enforcing Lipschitz bounds.
problem Improving robustness of CNNs in real-time applications.
method Dissipative layers parameterized by LMIs and 2-D Roesser model.
result Orders of magnitude faster run-time compared to state-of-the-art methods.
A framework isolates VQA reasoning from perception for better model evaluation.
problem Improper separation of visual perception and reasoning in VQA models.
method Introducing a framework and a top-down calibration technique to decouple reasoning from perception.
result Improved evaluation of VQA models by separating reasoning from perception.
End-to-end autonomous driving perception learns latent features for better performance.
problem Current autonomous driving systems are complex and require human engineering.
method Sequential latent representation learning for end-to-end perception.
result End-to-end perception model solves detection, tracking, localization, and mapping problems.
Deep RL policies can leak private information from trained policies.
problem Privacy leakage in deep reinforcement learning models.
method Environment dynamics search via genetic algorithm and candidate inference based on shadow policies.
result 95.83% average recovery rate of floor plans from trained Grid World navigation DRL agents.
Geometric model explains music perception combining neuroscience and acoustics.
problem Rationalize and predict psycho-acoustic phenomena in music perception.
method Combining neuroscientific theories with acoustic observations, a geometric model of the space of all chords is created.
result The geometric model allows for rigorous studies of psychoacoustic quantities like roughness and harmonicity.
Safe control for vehicles using learned perception from images.
problem Controlling autonomous vehicles with partial state information from images.
method Learned perception map and safe set design for a closed loop system.
result Generalization properties of the perception-control loop are favorable.
Bayesian deep learning integrates perception and inference for higher-level intelligence.
problem Integrating perception and inference for tasks requiring higher-level intelligence.
method Unified probabilistic framework combining deep learning and Bayesian models.
result Integrating perception and inference leads to improved performance in tasks like recommender systems and topic models.
RETR improves indoor radar perception with a novel transformer model.
problem Indoor radar perception lacks models tailored for multi-view radar settings.
method RETR extends DETR architecture with depth-prioritized feature similarity, tri-plane loss, and radar-to-camera transformation.
result RETR outperforms state-of-the-art methods by 15.38+ AP for object detection and 11.91+ IoU for instance segmentation.