Search Results for author: H. Jin Kim

Found 27 papers, 10 papers with code

Behavior Generation with Latent Actions

1 code implementation5 Mar 2024 Seungjae Lee, Yibin Wang, Haritheja Etukuru, H. Jin Kim, Nur Muhammad Mahi Shafiullah, Lerrel Pinto

Unlike language or image generation, decision making requires modeling actions - continuous-valued vectors that are multimodal in their distribution, potentially drawn from uncurated sources, where generation errors can compound in sequential prediction.

Autonomous Driving Decision Making +2

Diversify & Conquer: Outcome-directed Curriculum RL via Out-of-Distribution Disagreement

no code implementations30 Oct 2023 Daesol Cho, Seungjae Lee, H. Jin Kim

Reinforcement learning (RL) often faces the challenges of uninformed search problems where the agent should explore without access to the domain knowledge such as characteristics of the environment or external rewards.

Reinforcement Learning (RL)

Distributed multi-agent target search and tracking with Gaussian process and reinforcement learning

no code implementations29 Aug 2023 Jigang Kim, Dohyun Jang, H. Jin Kim

Deploying multiple robots for target search and tracking has many practical applications, yet the challenge of planning over unknown or partially known targets remains difficult to address.

Decision Making Multi-agent Reinforcement Learning +1

Safety-Critical Control under Multiple State and Input Constraints and Application to Fixed-Wing UAV

no code implementations8 Aug 2023 Donggeon David Oh, Dongjae Lee, H. Jin Kim

This study presents a framework to guarantee safety for a class of second-order nonlinear systems under multiple state and input constraints.

Collision Avoidance

Demonstration-free Autonomous Reinforcement Learning via Implicit and Bidirectional Curriculum

1 code implementation17 May 2023 Jigang Kim, Daesol Cho, H. Jin Kim

While reinforcement learning (RL) has achieved great success in acquiring complex skills solely from environmental interactions, it assumes that resets to the initial state are readily available at the end of each episode.

reinforcement-learning Reinforcement Learning (RL)

Object-based SLAM utilizing unambiguous pose parameters considering general symmetry types

no code implementations13 Mar 2023 Taekbeom Lee, Youngseok Jang, H. Jin Kim

Existence of symmetric objects, whose observation at different viewpoints can be identical, can deteriorate the performance of simultaneous localization and mapping(SLAM).

Object Tracking Pose Estimation +1

Outcome-directed Reinforcement Learning by Uncertainty & Temporal Distance-Aware Curriculum Goal Generation

1 code implementation27 Jan 2023 Daesol Cho, Seungjae Lee, H. Jin Kim

Current reinforcement learning (RL) often suffers when solving a challenging exploration problem where the desired outcomes or high rewards are rarely observed.

reinforcement-learning Reinforcement Learning (RL)

SNeRL: Semantic-aware Neural Radiance Fields for Reinforcement Learning

no code implementations27 Jan 2023 Dongseok Shim, Seungjae Lee, H. Jin Kim

As previous representations for reinforcement learning cannot effectively incorporate a human-intuitive understanding of the 3D environment, they usually suffer from sub-optimal performances.

3D Reconstruction Novel View Synthesis +2

SwinDepth: Unsupervised Depth Estimation using Monocular Sequences via Swin Transformer and Densely Cascaded Network

1 code implementation17 Jan 2023 Dongseok Shim, H. Jin Kim

Monocular depth estimation plays a critical role in various computer vision and robotics applications such as localization, mapping, and 3D object detection.

3D Object Detection Monocular Depth Estimation +1

DiffuPose: Monocular 3D Human Pose Estimation via Denoising Diffusion Probabilistic Model

1 code implementation6 Dec 2022 Jeongjun Choi, Dongseok Shim, H. Jin Kim

Thanks to the development of 2D keypoint detectors, monocular 3D human pose estimation (HPE) via 2D-to-3D uplifting approaches have achieved remarkable improvements.

Denoising Keypoint Detection +1

DHRL: A Graph-Based Approach for Long-Horizon and Sparse Hierarchical Reinforcement Learning

1 code implementation11 Oct 2022 Seungjae Lee, Jigang Kim, Inkyu Jang, H. Jin Kim

Hierarchical Reinforcement Learning (HRL) has made notable progress in complex control tasks by leveraging temporal abstraction.

Hierarchical Reinforcement Learning reinforcement-learning +1

S2P: State-conditioned Image Synthesis for Data Augmentation in Offline Reinforcement Learning

1 code implementation30 Sep 2022 Daesol Cho, Dongseok Shim, H. Jin Kim

Offline reinforcement learning (Offline RL) suffers from the innate distributional shift as it cannot interact with the physical environment during training.

Data Augmentation Image Generation +3

Unsupervised Reinforcement Learning for Transferable Manipulation Skill Discovery

no code implementations29 Apr 2022 Daesol Cho, Jigang Kim, H. Jin Kim

Current reinforcement learning (RL) in robotics often experiences difficulty in generalizing to new downstream tasks due to the innate task-specific training paradigm.

reinforcement-learning Reinforcement Learning (RL) +1

Automating Reinforcement Learning with Example-based Resets

1 code implementation5 Apr 2022 Jigang Kim, J. Hyeon Park, Daesol Cho, H. Jin Kim

Deep reinforcement learning has enabled robots to learn motor skills from environmental interactions with minimal to no prior knowledge.

Continuous Control reinforcement-learning +1

Learning a Domain-Agnostic Visual Representation for Autonomous Driving via Contrastive Loss

no code implementations10 Mar 2021 Dongseok Shim, H. Jin Kim

Deep neural networks have been widely studied in autonomous driving applications such as semantic segmentation or depth estimation.

Autonomous Driving Contrastive Learning +4

Gaussian RAM: Lightweight Image Classification via Stochastic Retina-Inspired Glimpse and Reinforcement Learning

1 code implementation12 Nov 2020 Dongseok Shim, H. Jin Kim

Previous studies on image classification have mainly focused on the performance of the networks, not on real-time operation or model compression.

Classification General Classification +4

Learning a Geometric Representation for Data-Efficient Depth Estimation via Gradient Field and Contrastive Loss

1 code implementation6 Nov 2020 Dongseok Shim, H. Jin Kim

In this paper, we show that existing self-supervised methods do not perform well on depth estimation and propose a gradient-based self-supervised learning algorithm with momentum contrastive loss to help ConvNets extract the geometric information with unlabeled images.

Monocular Depth Estimation object-detection +2

Moving object detection for visual odometry in a dynamic environment based on occlusion accumulation

no code implementations18 Sep 2020 Haram Kim, Pyojin Kim, H. Jin Kim

The proposed algorithm allows to separate the moving object detection and visual odometry (VO) so that an arbitrary robust VO method can be employed in a dynamic situation with a combination of moving object detection, whereas other VO algorithms for a dynamic environment are inseparable.

Moving Object Detection Object +2

Pose Correction Algorithm for Relative Frames between Keyframes in SLAM

no code implementations18 Sep 2020 Youngseok Jang, Hojoon Shin, H. Jin Kim

With the dominance of keyframe-based SLAM in the field of robotics, the relative frame poses between keyframes have typically been sacrificed for a faster algorithm to achieve online applications.

Detection-Aware Trajectory Generation for a Drone Cinematographer

no code implementations3 Sep 2020 Boseong Felipe Jeon, Dongseok Shim, H. Jin Kim

The proposed method actively guides the motion of a cinematographer drone so that the color of a target is well-distinguished against the colors of the background in the view of the drone.

object-detection Object Detection

Integrated Motion Planner for Real-time Aerial Videography with a Drone in a Dense Environment

no code implementations21 Nov 2019 Boseong Jeon, H. Jin Kim

The proposed system includes 1) a target motion prediction module which can be applied to dense environments and 2) a hierarchical chasing planner based on a proposed metric for visibility.

Robotics

Robust Real-time RGB-D Visual Odometry in Dynamic Environments via Rigid Motion Model

no code implementations19 Jul 2019 Sangil Lee, Clark Youngdong Son, H. Jin Kim

Further, we use a dual-mode motion model to consistently distinguish between the static and dynamic parts in the temporal motion tracking stage.

Motion Segmentation Segmentation +1

Edge Detection for Event Cameras using Intra-pixel-area Events

no code implementations17 Jul 2019 Sangil Lee, Haram Kim, H. Jin Kim

In this work, we propose an edge detection algorithm by estimating a lifetime of an event produced from dynamic vision sensor (DVS), also known as event camera.

Robotics

Online Trajectory Generation of a MAV for Chasing a Moving Target in 3D Dense Environments

no code implementations6 Apr 2019 Boseong Felipe Jeon, H. Jin Kim

This work deals with a moving target chasing mission of an aerial vehicle equipped with a vision sensor in a cluttered environment.

Robotics

Linear RGB-D SLAM for Planar Environments

no code implementations ECCV 2018 Pyojin Kim, Brian Coltin, H. Jin Kim

We propose a new formulation for including orthogonal planar features as a global model into a linear SLAM approach based on sequential Bayesian filtering.

Indoor RGB-D Compass From a Single Line and Plane

no code implementations CVPR 2018 Pyojin Kim, Brian Coltin, H. Jin Kim

We propose a novel approach to estimate the three degrees of freedom (DoF) drift-free rotational motion of an RGB-D camera from only a single line and plane in the Manhattan world (MW).

Cannot find the paper you are looking for? You can Submit a new open access paper.