Research @ RLLAB


Safety Guided Policy Optimization


  • Dohyeong Kim and Songhwai Oh, "Safety Guided Policy Optimization," in Proc. of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Oct. 2022.

SafeTAC: Safe Tsallis Actor-Critic Reinforcement Learning for Safer Exploration


Towards Defensive Autonomous Driving: Collecting and Probing Driving Demonstrations of Mixed Qualities


RIANet: Road Graph and Image Attention Network for Urban Autonomous Driving


Grasp Planning for Occluded Objects in a Confined Space with Lateral View Using Monte Carlo Tree Search 

Efficient Off-Policy Safe Reinforcement Learning Using Trust Region Conditional Value at Risk

Unsupervised 3D Link Segmentation of Articulated  Objects With a Mixture of Coherent Point Drift

TRC: Trust Region Conditional Value at Risk for Safe Reinforcement Learning

Dynamics-Aware Metric Embedding: Metric Learning in a Latent Space for Visual Planning


Texture Generation Using Dual-Domain Feature Flow with Multi-View Hallucinations


Visual Graph Memory with Unsupervised Representation for Visual Navigation

Road Graphical Neural Networks for Autonomous Roundabout Driving



MixGAIL: Autonomous Driving Using Demonstrations with Mixed Qualities

Pedestrian Intention Prediction for Autonomous Driving Using a Multiple Stakeholder Perspective Model

No-Regret Shannon Entropy Regularized Neural Contextual Bandit Online Learning for Robotic Grasping

Learning to Walk a Tripod Mobile Robot Using Nonlinear Soft Vibration Actuators with Entropy Adaptive Reinforcement Learning

Hierarchical 6-DoF Grasping with Approaching Direction Selection


Generative Autoregressive Networks for 3D Dancing Move Synthesis from Music

Unsupervised 3D Reconstruction Networks

Deep Predictive Autonomous Driving Using Multi-Agent Joint Trajectory Prediction and Traffic Rules

Soft Action Particle Deep Reinforcement Learning for a Continuous Action Space


Interactive Text2Pickup Networks for Natural Language based Human-Robot Collaboration

Uncertainty-Aware Learning from Demonstration Using Mixture Density Networks with Sampling-Free Variance Modeling

A Nonparametric Motion Flow Model for Human Robot Cooperation

Learning-Based Model Predictive Control under Signal Temporal Logic Specifications

Sparse Markov Decision Processes with Causal Sparse Tsallis Entropy Regularization for Reinforcement Learning


Text2Action: Generative Adversarial Synthesis from Language to Action

Online Learning to Approach a Person with No-Regret

Scalable Robust Learning from Demonstration with Leveraged Deep Neural Networks

Cost-Aware Path Planning under Co-Safe Temporal Logic Specifications

Chance-Constrained Target Tracking Using Sensors with Bounded Fan-Shaped Sensing Regions


Inverse Reinforcement Learning with Leveraged Gaussian Processes

Robust Modeling and Prediction in Dynamic Environments Using Recurrent Flow Networks

Gaussian Random Paths for Real-Time Motion Planning


Multiple-Hypothesis Chance-Constrained Target Tracking Under Identity Uncertainty


Complex Non-Rigid 3D Shape Recovery Using a Procrustean Normal Distribution Mixture Model


Vision-Based Coordinated Localization for Mobile Sensor Networks


Energy-Efficient Motion Planning for Higher Dimensional Problems Using Stochastic Optimization


Leveraged Non-Stationary Gaussian Process Regression


Robust Structured Low-Rank Matrix Approximation in GPR


Chance-Constrained Target Tracking for Mobile Robots



Smartphone-Controlled Telerobotic Systems

  • Hyemin Ahn, Hyunjun Kim, Yoonseon Oh, and Songhwai Oh, "Smartphone-Controlled Telerobotic Systems," in Proc. of the IEEE International Conference on Cyber-Physical Systems, Networks, and Applications (CPSNA), Aug. 2014.

SmartPTA: A Smartphone-Based Human Motion Evaluation System


A Robust Autoregressive GPMM Using l1-Norm Based Low-Rank Kernel Matrix Approximation

Playing Alkagi with a Humanoid Robot Nao

Action Classification Using Body Sensor Networks


Robust Action Recognition Using Local Motion and Group Sparsity

Real-Time Gaussian Process Motion Control

Before 2013

Nao Dancing to SNSD's Dancing Queen


PASU | Personal Area Situation Understanding System


VibePhone for Surface Recognition


VibeComm for Communication between Smart Devices without Radios


Multi-Robot Coordination

Kinect-Based Teleoperation of Willow Garage's PR2 Robot

Cooperative Indoor Localization Using Multiple Robots


Topological Mapping and Navigation for iRobot Create


Virtual Lock: A Smartphone Application for Personal Surveillance Using Camera Sensor Networks


NEST Final Experiment