arXiv subjects

Young J. Kim

Publications and source records attributed to Young J. Kim.

14 recordsLinked to original sources

arXiv2026

DevGRU: Depth-guided Visual Navigation using a Collision-aware Recurrent Model

Existing visual navigation models often aim to develop foundation models that can generalize robot navigation across diverse platforms. However, many of these models are prone to collisions when deployed in complex indoor environments, particularly in structured layouts and narrow passages. To address this problem, we propose a depth image- and point-goal-conditioned navigation system, DevGRU. The proposed system employs an action predictor (AP) that generates collision-aware future trajectories, enabling effective avoidance of immediate obstacles. In conjunction with a collision predictor, the AP further compensates for errors accumulated in the goal pose estimation and proactively mitigates future deviations. To evaluate our method, we conducted experiments across nine different scenes and three state-of-the-art approaches - ViNT, NoMaD, and NavDP - as well as four additional variants of ViNT and NoMaD. In terms of navigation performance, DevGRU significantly outperforms ViNT and NoMaD by a large margin. In addition, the proposed model has a relatively small number of trainable parameters, resulting in the fastest inference time among the baselines, particularly outperforming NavDP by 7x in model size and 17x in inference time.

cs.RO↗

arXiv2026

Kinodynamic Task and Motion Planning using VLM-guided and Interleaved Sampling

Task and Motion Planning (TAMP) integrates high-level task planning with low-level motion feasibility, but existing methods are costly in long-horizon problems due to excessive motion sampling. While LLMs provide commonsense priors, they lack 3D spatial reasoning and cannot ensure geometric or dynamic feasibility. We propose a kinodynamic TAMP planner based on a hybrid state tree that uniformly represents symbolic and numeric states during planning, enabling task and motion decisions to be jointly decided. Kinodynamic constraints embedded in the TAMP problem are verified by an off-the-shelf motion planner and physics simulator, and a VLM guides exploring a TAMP solution and backtracks the search based on visual rendering of the states. Experiments on the simulated domains and in the real world show 32.14% - 1166.67% increased average success rates compared to traditional and LLM-based TAMP planners and reduced planning time on complex problems, with ablations further highlighting the benefits of VLM backtracking. More details are available at https://graphics.ewha.ac.kr/kinodynamicTAMP/.

cs.RO↗

arXiv2026

A Dataset and Benchmark for Robotic Cloth Unfolding Grasp Selection: The ICRA 2024 Cloth Competition

Robotic cloth manipulation suffers from a lack of standardized benchmarks and shared datasets for evaluating and comparing different approaches. To address this, we created a benchmark and organized the ICRA 2024 Cloth Competition, a unique head-to-head evaluation focused on grasp pose selection for in-air robotic cloth unfolding. Eleven diverse teams participated in the competition, utilizing our publicly released dataset of real-world robotic cloth unfolding attempts and a variety of methods to design their unfolding approaches. Afterwards, we also expanded our dataset with 176 competition evaluation trials, resulting in a dataset of 679 unfolding demonstrations across 34 garments. Analysis of the competition results revealed insights about the trade-off between grasp success and coverage, the surprisingly strong achievements of hand-engineered methods and a significant discrepancy between competition performance and prior work, underscoring the importance of independent, out-of-the-lab evaluation in robotic cloth manipulation. The associated dataset is a valuable resource for developing and evaluating grasp selection methods, particularly for learning-based approaches. We hope that our benchmark, dataset and competition results can serve as a foundation for future benchmarks and drive further progress in data-driven robotic cloth manipulation. The dataset and benchmarking code are available at https://airo.ugent.be/cloth_competition.

cs.RO↗

arXiv2025

Adaptive Trajectory Refinement for Optimization-based Local Planning in Narrow Passages

Trajectory planning for mobile robots in cluttered environments remains a major challenge due to narrow passages, where conventional methods often fail or generate suboptimal paths. To address this issue, we propose the adaptive trajectory refinement algorithm, which consists of two main stages. First, to ensure safety at the path-segment level, a segment-wise conservative collision test is applied, where risk-prone trajectory path segments are recursively subdivided until collision risks are eliminated. Second, to guarantee pose-level safety, pose correction based on penetration direction and line search is applied, ensuring that each pose in the trajectory is collision-free and maximally clear from obstacles. Simulation results demonstrate that the proposed method achieves up to 1.69x higher success rates and up to 3.79x faster planning times than state-of-the-art approaches. Furthermore, real-world experiments confirm that the robot can safely pass through narrow passages while maintaining rapid planning performance.

cs.RO↗

arXiv2025

Scanning Bot: Efficient Scan Planning using Panoramic Cameras

Panoramic RGB-D cameras are known for their ability to produce high quality 3D scene reconstructions. However, operating these cameras involves manually selecting viewpoints and physically transporting the camera, making the generation of a 3D model time consuming and tedious. Additionally, the process can be challenging for novice users due to spatial constraints, such as ensuring sufficient feature overlap between viewpoint frames. To address these challenges, we propose a fully autonomous scan planning that generates an efficient tour plan for environment scanning, ensuring collision-free navigation and adequate overlap between viewpoints within the plan. Extensive experiments conducted in both synthetic and real-world environments validate the performance of our planner against state-of-the-art view planners. In particular, our method achieved an average scan coverage of 99 percent in the real-world experiment, with our approach being up to 3 times faster than state-of-the-art planners in total scan time.

cs.RO↗

arXiv2025

Fast and Accurate Task Planning using Neuro-Symbolic Language Models and Multi-level Goal Decomposition

In robotic task planning, symbolic planners using rule-based representations like PDDL are effective but struggle with long-sequential tasks in complicated environments due to exponentially increasing search space. Meanwhile, LLM-based approaches, which are grounded in artificial neural networks, offer faster inference and commonsense reasoning but suffer from lower success rates. To address the limitations of the current symbolic (slow speed) or LLM-based approaches (low accuracy), we propose a novel neuro-symbolic task planner that decomposes complex tasks into subgoals using LLM and carries out task planning for each subgoal using either symbolic or MCTS-based LLM planners, depending on the subgoal complexity. This decomposition reduces planning time and improves success rates by narrowing the search space and enabling LLMs to focus on more manageable tasks. Our method significantly reduces planning time while maintaining high success rates across task planning domains, as well as real-world and simulated robotics environments. More details are available at http://graphics.ewha.ac.kr/LLMTAMP/.

cs.RO↗

arXiv2024

TSP-Bot: Robotic TSP Pen Art using High-DoF Manipulators

TSP art is an art form for drawing an image using piecewise-continuous line segments. We present TSP-Bot, a robotic pen drawing system capable of creating complicated TSP pen art on a planar surface using multiple colors. The system begins by converting a colored raster image into a set of points that represent the image's tone, which can be controlled by adjusting the point density. Next, the system finds a piecewise-continuous linear path that visits each point exactly once, which is equivalent to solving a Traveling Salesman Problem (TSP). The path is simplified with fewer points using bounded approximation and smoothed and optimized using Bezier spline curves with bounded curvature. Our robotic drawing system consisting of single or dual manipulators with fingered grippers and a mobile platform performs the drawing task by following the resulting complex and sophisticated path composed of thousands of TSP sites. As a result, our system can draw complicated and visually pleasing TSP pen art.

cs.RO↗

arXiv2023

Stroke-based Rendering and Planning for Robotic Performance of Artistic Drawing

We present a new robotic drawing system based on stroke-based rendering (SBR). Our motivation is the artistic quality of the whole performance. Not only should the generated strokes in the final drawing resemble the input image, but the stroke sequence should also exhibit a human artist's planning process. Thus, when a robot executes the drawing task, both the drawing results and the way the robot executes would look artistic. Our SBR system is based on image segmentation and depth estimation. It generates the drawing strokes in an order that allows for the intended shape to be perceived quickly and for its detailed features to be filled in and emerge gradually when observed by the human. This ordering represents a stroke plan that the drawing robot should follow to create an artistic rendering of images. We experimentally demonstrate that our SBR-based drawing makes visually pleasing artistic images, and our robotic system can replicate the result with proper sequences of stroke drawing.

cs.RO↗

arXiv2021

Synthesizing Human Faces using Latent Space Factorization and Local Weights (Extended Version)

We propose a 3D face generative model with local weights to increase the model's variations and expressiveness. The proposed model allows partial manipulation of the face while still learning the whole face mesh. For this purpose, we address an effective way to extract local facial features from the entire data and explore a way to manipulate them during a holistic generation. First, we factorize the latent space of the whole face to the subspace indicating different parts of the face. In addition, local weights generated by non-negative matrix factorization are applied to the factorized latent space so that the decomposed part space is semantically meaningful. We experiment with our model and observe that effective facial part manipulation is possible and that the model's expressiveness is improved.

cs.GR↗

arXiv2021

Solving Footstep Planning as a Feasibility Problem using L1-norm Minimization (Extended Version)

One challenge of legged locomotion on uneven terrains is to deal with both the discrete problem of selecting a contact surface for each footstep and the continuous problem of placing each footstep on the selected surface. Consequently, footstep planning can be addressed with a Mixed Integer Program (MIP), an elegant but computationally-demanding method, which can make it unsuitable for online planning. We reformulate the MIP into a cardinality problem, then approximate it as a computationally efficient l1-norm minimisation, called SL1M. Moreover, we improve the performance and convergence of SL1M by combining it with a sampling-based root trajectory planner to prune irrelevant surface candidates. Our tests on the humanoid Talos in four representative scenarios show that SL1M always converges faster than MIP. For scenarios when the combinatorial complexity is small (< 10 surfaces per step), SL1M converges at least two times faster than MIP with no need for pruning. In more complex cases, SL1M converges up to 100 times faster than MIP with the help of pruning. Moreover, pruning can also improve the MIP computation time. The versatility of the framework is shown with additional tests on the quadruped robot ANYmal.

cs.RO↗

arXiv2020

Accelerating Probabilistic Volumetric Mapping using Ray-Tracing Graphics Hardware

Probabilistic volumetric mapping (PVM) represents a 3D environmental map for an autonomous robotic navigational task. A popular implementation such as Octomap is widely used in the robotics community for such a purpose. The Octomap relies on octree to represent a PVM and its main bottleneck lies in massive ray-shooting to determine the occupancy of the underlying volumetric voxel grids. In this paper, we propose GPU-based ray shooting to drastically improve the ray shooting performance in Octomap. Our main idea is based on the use of recent ray-tracing RTX GPU, mainly designed for real-time photo-realistic computer graphics and the accompanying graphics API, known as DXR. Our ray-shooting first maps leaf-level voxels in the given octree to a set of axis-aligned bounding boxes (AABBs) and employ massively parallel ray shooting on them using GPUs to find free and occupied voxels. These are fed back into CPU to update the voxel occupancy and restructure the octree. In our experiments, we have observed more than three-orders-of-magnitude performance improvement in terms of ray shooting using ray-tracing RTX GPU over a state-of-the-art Octomap CPU implementation, where the benchmarking environments consist of more than 77K points and 25K~34K voxel grids.

cs.RO↗

arXiv2019

A Penetration Metric for Deforming Tetrahedra using Object Norm

In this paper, we propose a novel penetration metric, called deformable penetration depth PDd, to define a measure of inter-penetration between two linearly deforming tetrahedra using the object norm. First of all, we show that a distance metric for a tetrahedron deforming between two configurations can be found in closed form based on object norm. Then, we show that the PDd between an intersecting pair of static and deforming tetrahedra can be found by solving a quadratic programming (QP) problem in terms of the distance metric with non-penetration constraints. We also show that the PDd between two, intersected, deforming tetrahedra can be found by solving a similar QP problem under some assumption on penetrating directions, and it can be also accelerated by an order of magnitude using pre-calculated penetration direction. We have implemented our algorithm on a standard PC platform using an off-the-shelf QP optimizer, and experimentally show that both the static/deformable and deformable/deformable tetrahedra cases can be solvable in from a few to tens of milliseconds. Finally, we demonstrate that our penetration metric is three-times smaller (or tighter) than the classical, rigid penetration depth metric in our experiments.

cs.CG↗

arXiv2017

CanvoX: High-resolution VR Painting in Large Volumetric Canvas

With virtual reality, digital painting on 2D canvases is now being extended to 3D spaces. Tilt Brush and Oculus Quill are widely accepted among artists as tools that pave the way to a new form of art - 3D emmersive painting. Current 3D painting systems are only a start, emitting textured triangular geometries. In this paper, we advance this new art of 3D painting to 3D volumetric painting that enables an artist to draw a huge scene with full control of spatial color fields. Inspired by the fact that 2D paintings often use vast space to paint background and small but detailed space for foreground, we claim that supporting a large canvas in varying detail is essential for 3D painting. In order to help artists focus and audiences to navigate the large canvas space, we provide small artist-defined areas, called rooms, that serve as beacons for artist-suggested scales, spaces, locations for intended appreciation view of the painting. Artists and audiences can easily transport themselves between different rooms. Technically, our canvas is represented as an array of deep octrees of depth 24 or higher, built on CPU for volume painting and on GPU for volume rendering using accurate ray casting. In CPU side, we design an efficient iterative algorithm to refine or coarsen octree, as a result of volumetric painting strokes, at highly interactive rates, and update the corresponding GPU textures. Then we use GPU-based ray casting algorithms to render the volumetric painting result. We explore precision issues stemming from ray-casting the octree of high depth, and provide a new analysis and verification. From our experimental results as well as the positive feedback from the participating artists, we strongly believe that our new 3D volume painting system can open up a new possibility for VR-driven digital art medium to professional artists as well as to novice users.

cs.GR↗

arXiv2015

PolyDepth: Real-time Penetration Depth Computation using Iterative Contact-Space Projection

We present a real-time algorithm that finds the Penetration Depth (PD) between general polygonal models based on iterative and local optimization techniques. Given an in-collision configuration of an object in configuration space, we find an initial collision-free configuration using several methods such as centroid difference, maximally clear configuration, motion coherence, random configuration, and sampling-based search. We project this configuration on to a local contact space using a variant of continuous collision detection algorithm and construct a linear convex cone around the projected configuration. We then formulate a new projection of the in-collision configuration onto the convex cone as a Linear Complementarity Problem (LCP), which we solve using a type of Gauss-Seidel iterative algorithm. We repeat this procedure until a locally optimal PD is obtained. Our algorithm can process complicated models consisting of tens of thousands triangles at interactive rates.

cs.GR↗